Center for sensing technologies

Center for Information Technologies

Center for Product Development

Project aim: The digital platform AgroSense APV consists of a web and mobile application that enables monitoring of the implementation of the competition for the award of grants announced by the Provincial Secretariat for Agriculture, Water Management and Forestry.
&nbsp;
About the project: Thanks to this project, it is possible to automatically rank applications for competitions, as well as to generate contracts and various solutions. By automatically generating accounts for the control of applications for the competition and assigning orders to the advisory services, which then use mobile phones to control and verify in the field, the work of the advisory professional services has been improved. Satellite verification of data obtained from the field is enabled through the AgroSense APV platform. With the help of satellite monitoring of each cadastral parcel and in accordance with the resolution and technical capabilities of the Sentinel recordings, it is possible to further verify the realization of the Competition.
&nbsp;
This platform also enables the management of land fertility control by agricultural experts and advisory services. By creating tasks for soil sampling, advisors are enabled to create a sample via mobile phone and define its geo-location. Recording laboratory results of soil samples provides insight into the state of soil fertility. Also, the sowing structure for the Autonomous Province of Vojvodina, from 2013 until today, is available through the digital platform AgroSense.
&nbsp;
&nbsp;
<img decoding="async" loading="lazy" class="alignnone size-full wp-image-547" src="https://api.biosens.rs/wp-content/uploads/2021/06/Logo-ENG-1.png" alt="" width="296" height="65" />

Principal Research Fellow

Vladimir Crnojević

Milijana Vujasinović

Milan Stanojković has been holding the position of Junior Associate at BioSense Institute since February 2023. He received a bachelor’s (2018) and master’s (2022) degree from the Faculty of Sciences, University of Novi Sad, Serbia in the area of Information technologies, his main responsibility within the BioSense Institute is developing web applications. He is developing the backend in Java frameworks (Spring, EJB). For the frontend part of applications, he is working with Angular and AngularJS. He also works with databases and servers (Wildfly and Tomcat).

Milan Stanojković

Goran Adžić works at the position of the senior associate in the Centre for Product Development. He graduated his Msc (2015) and BSc (2013) from the Faculty of Tehcnical Science in Novi Sad, Department of Geodesy and Geoinformatics. Since 2014, he was working on the development of many gis applications and software for public administration and local self-government. At BioSense, he works on the development of web applications, for which he uses Java, Angular and PostgreSQL database. He enrolled in a PhD program in 2020.

Goran Adžić

Slobodan Birgermajer is research associate in the Center for Sensing Technologies at the BioSense Institute. Mr. Birgermajer received his PhD in microware electronics form the Faculty of Technical Sciences, University of Novi Sad, in 2019. He is currently working on development and application of the sensors in agriculture, food industry, and environmental monitoring, and he is actively involved in many H2020 projects such as ANTARES, IPANEMA SHealty, etc. His main research interest includes microwave passive devices, photonic crystals, microfluidic sensors, and 3D and 4D printing.

Slobodan Birgermajer

Mina Mirović is a junior reseacher at BioSense Institute. She holds a BSc in Mechatronics from Faculty of Novi Sad and MSc in Mechatronics, Robotics and Embedded Systems from London South Bank University.

&nbsp;

Mina Mirović

Željko Bajić obtains MSc in Computer science at Faculty of Sciences, University of Novi Sad in 2012. He works as a senior associate at BioSense institute since 2018. His expertise covers full stack technologies mostly based on Java programming language and Web development. He participates in several national and international research projects.

Željko Bajić

Vladan Minić is a Manager of the Product Development Center at BioSense Institute. He received an M.Sc. degree in the Faculty of Technical Sciences in 2007. His career started at the Faculty of Technical Sciences, as a member of BioSense Center. When the Center grew into an Institute, he moved to a newly established institution. He participates in many national and international projects within BioSense Institute. His main research interests are wireless sensor networks and image processing, but he also performed the duties of a system administrator. His expertise covers Linux and Windows system; Web development – WordPress, Joomla, PHP, HTML; Programming languages: Python. C/C++ (OpenCV), Matlab; Databases: MySQL, PostgreSQL, MS SQL, SQLite; GIS tools: ArcGIS, QGIS. He also likes hardware and embedded systems.

Vladan Minić

Mina Bjelica works as a junior associate in the product development center at the BioSense Institute. She graduated in 2019 at the University of Novi Sad, at the Faculty of Science on Information Technology department. At BioSense, she is currently working on the development and maintenance of several web applications in the programming language for backend – Java (EJB and Spring framework), for frontend: TypeScript (Angular framework), AngularJS framework, HTML, CSS, languages for datebase: SQL and HQL, and servers: wildfly and tomcat.

&nbsp;

Mina Bjelica

Milijana Vujasinović is the head of Product Development Center. She has many years of experience in development and implementation of software solutions. In the development of software solutions, she was initially involved as a programmer and business analyst, and later as a solution designer and product manager. She gained a lot of experience working as an ERP consultant and project manager in implementation of software solutions in different industries – agriculture, wholesale and retail chains, food, textile, metallurgy, tool and cable, construction, service industry, metallurgy and public companies. She has SAP Financial Accounting certificate and SAP Project Manager certificate. For more than 3 years, she managed PMO (Project Management Office), the department that controls and improves the project management process.

Milica Milovanović works as junior associate at BioSense Institute since October 2019. She received a bachelor's degree from the Faculty of Sciences, University of Novi Sad, Serbia in 2019 in the area of Information technologies. Currently, her main responsibility within the BioSense Institute is developing web applications. She is developing backend in Java and Python frameworks (Spring, EJB and Django). For frontend part of applications she is working with Angular and AngularJS. She also works with databases and servers (Wildfly and Tomcat).

Milica Milovanović

Predrag Lugonja is a researcher at BioSense Institute. He graduated from the Faculty of Technical Sciences, University of Novi Sad, Department of Power, Electronic and Telecommunication Engineering. He is currently in the final year of his PhD studies at the Faculty of Technical Sciences. He has been working in the fields of GIS and remote sensing

Predrag Lugonja

Oskar Marko, Ph.D. is the Head of the Center for Information Technologies and the Assistant Director for Innovation and Cooperation with the Economy at the BioSense Institute. His research focuses on applying advanced machine learning and evolutionary algorithms in agriculture. He spent the 3rd year of his undergraduate studies at City University London, where he did his final BEng project in signal processing. He led BioSense’s team that developed novel Big Data algorithms for yield prediction, seed distribution, and optimization of sowing strategies, which secured the 1st prize for BioSense at the Syngenta Crop Challenge and CGIAR Inspire Challenge. He is actively involved in many Horizon 2020 projects including Antares, Cybele, Dragon, and Flexigrobots, and industrial projects with partners such as Krivaja, MK Agriculture, Delta, and other farming and insurance companies.

Oskar Marko

Nastasija Grujić is a junior research assistant at the BioSense Institute and a PhD student in Geoinformatics at the University of Novi Sad, Faculty of Technical Sciences. She finished her MSc (2018) and BSc (2017) studies in Geodesy and Geomatics Engineering. During the studies, she received two Dositeja awards for the top 800 and 400 students in the country (school years 2016/2017 and 2017/2018, respectively). In late 2018, she enrolled in PhD studies and started working at the BioSense Institute. During the studies, she was twice a guest researcher at the University of Wageningen, where she got acquainted with modeling complex and stochastic systems through agent-based simulation. Her particular research interest span a wide range of data analytics, machine learning, and geoinformatics which are used for better understanding and simulating the complex spatial systems through individual and agent-based simulations. She is involved in various national and international projects, including H2020 projects ANTARES, DRAGON, and BESTMAP.

Nastasija Grujić

Mirjana Radulović is a Junior Research Assistant at the BioSense Institute with interests in remote sensing, geoinformatics, water resource management, agriculture, and the environment. She is currently enrolled as a Ph.D. student of Geosciences at the Faculty of Sciences, the University of Novi Sad where she also received her BSc (2017) and MSc (2018) in the field of hydrology and geoinformatics. During master studies, she spent five months at the Palacký University in Olomouc (Czech Republic) where she studied as a scholarship holder of the Erasmus+ Exchange Program. In March 2019 she joined the BioSense Institute where she works on applying geographical information systems and remote sensing tehnology for monitoring of irrigation, drought monitoring, crop monitoring, land use classification, groundwater monitoring, etc. She participates in several national and international projects related to these topics. Mirjana authored and co-authored several scientific papers and attended several scientific conferences.

Mirjana Radulović

Miloš Pandžić is a Junior Research Assistant whose interest includes several research fields: Earth observation, remote sensing, image processing and data analytics. He is currently enrolled as a PhD student of Geodesy and Geoinformatics at the Faculty of Civil Engineering, University of Belgrade, where he also obtained his master and bachelor degree. In 2015 he received scholarship from the Government of Austria (OeAD) and spent 4 months at TU Vienna where he analysed geometric quality of Sentinel-2 satellite multispectral images. Outcome of this work was his master thesis. After graduation he worked at the Finnish Geospatial Research Institute (FGI) on several projects funded by Academy of Finland and European Space Agency (ESA). His main occupation was segmentation and change detection in satellite imagery related to agricultural activity, urbanization and deforestation. In 2018 he joined BioSense Institute where he works on data fusion of optical and radar images for yield prediction, crop classification, crop monitoring, etc. He is involved in several national and international projects including Antares, Cybele, Dragon, PARSEC, agROBOfood.

Miloš Pandžić

Gordan Mimić is a research associate at Biosense Institute. Gordan Mimić received BSc (2011), MSc (2012) and PhD (2016) degrees in Physics-Meteorology at the University of Novi Sad, Faculty of Sciences. He was working at Republic Hydrometeorological Service of Serbia during the period 2011-2012, in the division for Numerical Weather Prediction. Gordan Mimić was teaching assistant for the various courses in meteorology at the University of Novi Sad (Faculty of Sciences and Faculty of Agriculture) in the period 2012-2017. His current research interest is data analytics in the field of agrometeorology and biometeorology. He was the leader of the BioSense team that developed a novel algorithm for the classification of maize hybrids tolerant to drought and heat stress, which won the third prize at Syngenta Crop Challenge in Analytics 2019. He participated in several national and international projects. Gordan Mimić has co-authored 20 journal articles, 4 conference papers and 1 book chapter.

Gordan Mimić

Dragana Blagojević obtained BSc (2017) and MSc (2018) degrees in geography at the Faculty of Sciences in Novi Sad with a focus on geographic information systems and their use in the hydrological and geomorphological analysis. In October 2018, she enrolled in Ph.D. studies in Geosciences at the same faculty. She spent the summer semester of the master studies at the Palacký University in Olomouc (UPOL) in the Czech Republic, as a scholarship holder of the Erasmus+ Exchange Program where she studied at the Department of Geoinformatics. In January 2019 she joined BioSense Institute where she works as a Junior Research Assistant in the Centre for Information Technologies. Her research area is in the field of remote sensing, precision agriculture, yield monitoring, and mapping as well as filed work analyses. Her research aim is an integration of these techniques to get complete and precise information about filed, crops, terrain, and soil characteristics.

Dragana Blagojević

Dejan Pavlović is a researcher at BioSense Institute and a PhD student of System Control and Signal Processing at School of Electrical Engineering, University of Belgrade. His research interests cover signal processing and machine learning application, particularly focused on the field of precision agriculture. Dejan received his bachelor’s degree in Biomedical Engineering from the Faculty of Technical Sciences, University of Novi Sad and master’s degree in Electrical and Computer Engineering from School of Electrical Engineering, University of Belgrade. He is currently working in the field of data analytics developing an algorithm for the classification of multiple-behaviour patterns in cattle using Convolutional Neural Networks. He is actively involved in many projects, including Horizon 2020 projects, Antares and Dragon.

Dejan Pavlović

Branislav Pejak is a PhD student of Electrical Engineering at the Faculty of Technical Sciences, the University of Novi Sad, where he also received his BSc (2017) and MSc (2018) in the field of Biomedical Engineering. During his bachelor and master studies, he held a scholarship from the Ministry of Education, Science and Technological Development, Republic of Serbia. Since March 2018, Branislav has been working as a Junior Research Assistant at the Center for Information Technologies, BioSense Institute. His main research is data analytics on satellite images. Currently he is working on crop classification and crop yield prediction using time series of multispectral images and GAN machine learning framework. Within the project he is also working on many practical usages of ICT in agriculture such as smart soil sampling and fertilization, irrigation zone mapping, grain yield and protein content prediction etc. He is actively involved in many Horizon 2020 projects including Antares, Cybele, Dragon and AgRoboFood.

Branislav Pejak

Dr Nataša Ljubičić (F) Research associate, received the Ph.D. degrees from the Faculty of Agriculture, University of Novi Sad, in Serbia in the field of Genetics and Plant Breeding. She holds her Master thesis with the name: ”Multivariate analysis of wheat genotypes grown on meliorated Solonjec soil”, where she investigated different plant responses through genotype/environment interaction caused by different types of soil melioration. Dr Nataša Ljubičić is a Research associate at BioSense Institute, University of Novi Sad, Serbia. Her research interests include using and implementing innovative and smart technology in agricultural and environmental investigations, following genotype/environment interaction, plant response within different mineral nutrition, nutrition, plant stress, phenotypic variability of the plant traits of the agricultural crops. Her investigation involved research from plant scale to large-scale evaluation with the main aim to improve agricultural production. Dr Ljubičić is a member of the EUCARPIA - European Association for Research on Plant Breeding and was involved in several Serbian national projects. She is the author and co-author of more than 50 journal and conference papers on international and national levels and 2 Technical solutions with total citations: 81; h-index: 6 (Google Scholar).

&nbsp;

Nataša Ljubičić

Bojana Ivošević is working on utilizing Unmanned Aerial Vehicles (UAV) for efficient monitoring of croplands, freshwaters, and terrains. She hails from a background in biology and ecology. She initiated her PhD in Kyungpook National University, South Korea, where she gained 2 years of experience with UAVs. She continued to pursue her field of interest at the Faculty of Sciences, University of Novi Sad, Serbia. Her current research focus is to implement UAV technology in precision agriculture to calculate vegetation indices important for agricultural crop yield production, disease detection and crop management. She is also interested in enforcing UAVs for animal detection and counting, monitoring algae bloom, land cover classification, and seasonal effects on the ecosystems.

Bojana Ivošević

National

BioSense has excellent ties with the Serbian Ministry of Agriculture and Provincial Secretariat for Agriculture, Water Management and Forestry of Vojvodina. We are providing a range of solutions that help public administration get a better insight into agricultural production, achieve more efficient control of the subsidies and detect irresponsible use of farmland.

&nbsp;

Our solutions are mainly based on remote sensing and GIS and involve large databases of fields, farmers and acquired data. Services such as crop mapping over the region of interest are developed using Sentinel 2 satellite images and come at a 10m resolution. Crop mapping, in particular, has various purposes, from verification of subsidies to identifying burning of the fields or illegal occupation of state-owned farmland.

&nbsp;

Subsidies are issued for growing particular crops, constructing greenhouses or installing irrigation systems. They are numerous and in-person inspections would require large teams of government officials. Furthermore, it is very time-consuming to check the whole field, which can be tens or hundreds of hectares in size. Using our system, verifications are done remotely, using satellite image processing coupled with advanced machine learning algorithms.

&nbsp;

Similar technology is employed for detection of illegal activities. Traditionally, farmers had often burnt crop residues on their fields to save time and fuel needed for ploughing. This practice was abandoned in the past decades and was declared illegal, as it poses danger to humans and the environment. Also, there have been instances of occupation of state-owned farmland without bidding and paying for the rent. These and other offences are detected using satellite technology and have decreased in occurrence, thus securing safer and more eco-friendly farming, as well as higher revenues for the government.

&nbsp;

Other services include systems set up for various other public stakeholders, most notably for extension services. Extension services give advisory support to farmers and collect large amounts of field data. A dedicated platform based on AgroSense was set up where all the data is stored and visualised using a GIS engine. In this way, thousands of new records, as well as the historical database of field observation were digitised and gathered under one roof.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1871 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/07/xyz.png" alt="" width="680" height="283" />

<img class="alignnone wp-image-1872 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/07/xy.png" alt="" width="844" height="346" />

Government

One of the areas that are going through the most dramatic change in the break of the Fourth Industrial Revolution is agriculture. Today, more than ever, manufacturers are under huge pressure to increase yields, reduce costs and grow quality products. This is not an easy task and requires dedication, hard work and investments, and the only way to succeed is to make the decisions exceptionally efficient and timely. In the era of satellites, powerful computers and the internet, we finally have the opportunity to make decisions based on facts, and the key to success lies in data.

&nbsp;

Sensors, yield monitors, drones and soil sampling probes have become a common sight on our fields, and they all are nothing more than different platforms for obtaining the data. Using them, we are getting information about the soil type, terrain elevation, crops growth and yields, and counting in the specifics of a particular field, we are optimising the choice of varieties and hybrids, planting date, amount and type of fertiliser, as well as the right moment for irrigation. In this way, we are providing all the necessary conditions for good plant growth and preventing excessive use of agrochemicals. However, a huge data problem with data is that until now the most of them have been hardly available for the farmers. They were located in different corners, in different formats, and some were not even available in the digital form. Today these problems are past. Satellite, meteorological and other data are widely available to Serbian farmers through AgroSense, the web platform of digital agriculture of Serbia, which gives them the opportunity to run their farms digitally, professionally and efficiently, completely free of charge.

&nbsp;

AgroSense is a platform developed to ensure that the farmers have a quick and easy access to data, but also to let the community benefit from BioSense’s top class research in the domain of artificial intelligence, satellite image processing and the development of sensor networks. Since the platform launch in October 2017, we have gained more than 10,000 satisfied users, which confirms that Serbian farmers have recognised the importance of digital transformation in their area. The platform consists of a number of modules and their number is increasing constantly from one month to the other, to answer to the requirements in the production.

&nbsp;

&nbsp;

Using the service

&nbsp;

Everyone interested in AgroSense can register at <a href="https://www.agrosens.rs/#/app-h/welcome">www.agrosense.rs</a> completely free of charge, for what you they only need to have the e-mail address. The first step after the registration is creating the production parcel. This can be done through the cadastre, if the user possesses the data about the municipality and the cadastral ID. The user can also select more than one parcel, if the crop production spans over a few of them. On the other hand, it often happens that multiple crops are produced on one cadastral parcel, which is why there is a possibility for the user to draw the boundaries of the production parcel using the map and a simple drawing tool. The user can have an unlimited number of production parcels on its profile and immediately after creating the parcel in the system, the whole range of modules become available. These modules are described in detail in the following chapters.

&nbsp;

&nbsp;

Meteorological data

&nbsp;

Meteorological data are one of the key indicators of the state of the field and many activities are planned based on them. Soil temperature is a decisive parameter for sowing, rain forecast determines the optimal moment for the application of fertilisers and pesticides and solar radiation and air temperature are influencing the plant development. There are two modules in AgroSense that are dealing with meteorology. The first is devoted to the historical weather records. Data from the Nation Hidro-meteorological Agency are uploaded to the system and the user can choose up to 3 weather stations of interest, for which he can observe the soil and air meteorological parameters in the previous 7 days and get an insight about the state of the field. The second module is devoted to the weather forecast. Researchers at BioSense Institute have a long history of using the forecast issued by the Norwegian Meteorological Institute, as it is by our experience the most accurate one. What is more, it is given at a resolution of 2 km, which allows the user to have an accurate forecast for the location of its field.

&nbsp;

&nbsp;

Satellites

&nbsp;

Thanks to the involvement of BioSense in the European scientific projects and the success it had in its research, Serbia has become the only country outside of the EU that has the wideband access to imagery from Sentinel satellites of the European Space Agency, and AgroSense is fully utilising this opportunity. Sentinel satellites are taking footage of crops every 5 days at a resolution of 10 m and allowing the user to monitor its fields from a completely new perspective. Just as the human eye recognises 3 components of light (red, green and blue), Sentinels recognise 13 spectral components. This means that they see what we do not see and sometimes it is the infrared and thermal bands that are telling the most about the “health status” of the plants. Using 13 spectral channels, we are calculating vegetation indices that are telling us about the growth of crops, drought intensity, dispersion of plant diseases and the plants’ needs for irrigation and fertilisation. In this way, farmers can see which parts of the field are growing better and which are growing worse, and they can distribute the fertiliser according to the actual needs of crops in different parts of the field.

&nbsp;

&nbsp;

Digital field records (ili Digital diary of the production)

&nbsp;

Every proper production should be well-documented. In agriculture, it is a practice to keep the field records and, as Serbia is transitioning towards the EU legislation, it will soon be obligatory. From the data analytics point of view, paper field records are a huge missed opportunity. Datasets regarding sowing, application of fertilisers and pesticides and harvesting are a “gold mine” for BioSense, but, as a rule, they are written in notebooks and planners and remain on the shelves, hidden from everyone’s eyes. With digital data, through application of advanced methods of artificial intelligence, machine learning and Big Data analytics, we are able to process huge amounts of data, find hidden dependencies within them, give automatic recommendations to the farmers and make their decisions more efficient. An old Chinese proverb says: “the best time to plant a tree was 20 years ago. The second best time is now”. Currently we do not have Big Data about agricultural production, but keeping digital field records is an ideal chance to start gathering information, based on which BioSense will develop new modules for the farmers. AgroSense’s Activities module allows users to enter the information about the date of the activities conducted on the field and specify details about the type of tillage, applied pesticides, yields and operation costs, while all these activities can be also documented with photographs using AgroSense mobile app. Besides the module with activities, there is a separate module for soil analysis that displays the soil data acquired through the years, and a module that consists of photos that the user has acquired using smartphone and their map based on their GPS locations.

&nbsp;

&nbsp;

Parameter maps

&nbsp;

Besides satellites that are covered by a separate module, there are many other sources of data about the parcel, such as yield, elevation and soil electrical conductivity maps and drone footage. These maps are additional layers of information that can be extremely important in planning and monitoring the growth of crops. There is a possibility to import these maps into AgroSense and to compare them with one another. The image below is an example how the soil electrical conductivity maps are corresponding to the yield and it also shows the clear influence of centre-pivot irrigation system. On the other hand, drones are allowing us to observe crops on a resolution of just a couple of centimetres and spot the finest changes in crop growth. Additional parameter maps are giving us a new insight into the agricultural production, and AgroSense is giving us an opportunity to show them and analyse adequately.

&nbsp;

&nbsp;

Sensors and meteo stations

&nbsp;

Scientific results are telling us that the weather is responsible for 70 % of the variability in yield. Due to the climate change, extreme weather events such as droughts and floods have become very frequent and have a distinctively local character. National Hidro-meteorological Agency’s network covers around 30 geographic locations, but this number is far from sufficient. It often happens that weather events occur between two weather stations and remain unregistered, which is a serious problem for farmers, who base their decisions in production on soil moisture, soil and air temperature and other parameters. For this reason, BioSense will deploy a staggering number of 500 weather stations throughout the Republic of Serbia, that will allow for measurements of meteorological parameters on a high spatial resolutions. When it comes to wireless integration of sensors and meteo stations, today’s state-of-the-art are LORA systems and such networks are often called IoT (the Internet of Things). Just as the mobile network is optimised for sending large files, such as high-quality images and video clips, LORA is optimised for sending small batches of data (sensory readings) over vast distances with small energy consumption. In this way, a sensor battery can last throughout the whole growing season and data logging is possible from fields up to 30 km away from the base station. Based on the readings from sensors and weather stations, farmers can have a precise insight into the state of the field through AgroSense and make optimal decisions in their production.

&nbsp;

&nbsp;

Cost analysis

&nbsp;

One of the direct benefits of keeping comprehensive digital field records is that the cost analysis can be conducted by a single click of the mous. This module uses the information about the activities and their prices and lists the costs according to the crop type or the total costs for the whole farm. The cost analysis is supported by graphs that visually represent the numbers in a clear and understandable way, and which are helping the farmer get a better insight in the financial aspect of the production.

&nbsp;

&nbsp;

Services

&nbsp;

Consultancy is one of the fields that will undergo the biggest change due to the digital transformation, as the precise field data will allow advisory services and experts to give more accurate and more efficient advice to the farmer. Based on this module, advisors and farmers will be able to connect more efficiently and, upon the signing of the contract, the advisor will get a full range of information about the crops, from satellite images and parameter maps, over photographs from the field, all the way to the digital field records. Such a detailed dataset leaves a possibility to the expert to perceive the problem from multiple angles and determine the optimal steps in the production, often even without the field visit. Besides the module for advisors, drone pilots will also have their section within the Services module. Conducting business over AgroSense even eliminates the need for any personal contact between the providers and receivers of UAV imaging services. After establishing the contact, the pilot gets GPS coordinates and boundaries of the parcel, while the images are digitally uploaded to the platform. This makes the business run faster and more efficient and promotes the use of high-tech in agriculture. Service providers can limit the area of their operation to Serbian counties of interest, so that they could avoid deals from remote locations that are not financially justifiable, due to high travel costs. Another factor for choosing a service provider is the price. Namely, we set up a system for giving ratings to the providers that allows farmers to rate advisors and drone pilots based on the quality of work conducted.

This system puts quality service providers on top and allows them to set up their prices according to the quality of their service and the demand. Besides advisors and UAV pilots, we are planning to include sections for laboratories for soil analysis, companies for electrical conductivity scanning of the fields and others. This network will gather different actors in agricultural production and integrate them under one roof – the AgroSense platform.

&nbsp;

&nbsp;

Pest alarms

&nbsp;

Plant diseases and pests near the parcel are a serious threat to the production and farmers need to act urgently upon information about their occurrence. This module logs the warnings issued by the Agricultural Prognostic and Reporting Agency of Serbia and sends them to the farmer. Warnings are filtered and the user sees only those related to diseases that affect the crops he is cultivating. In this way, the farmer is alarmed and warned that he needs to act according to the recommended procedures.

&nbsp;

&nbsp;

Tools

&nbsp;

During the preparation for every operation on the field, farmers must calculate the necessary amounts of raw materials and calibrate the sprayers and fertiliser spreaders. This module allows them to do this precisely and quickly.

&nbsp;

&nbsp;

Technologies

&nbsp;

BioSense sees itself as a leader in the digital transformation of Serbian agriculture. AgroSense contains a large number of practical functionalities, but education is another important aspect. The Technologies module has a role to direct the farmer to the latest trends in agriculture. It contains articles about the modern fertiliser spreaders, tractors, irrigation systems and other products that have recently found their way to the market and represent today’s state-of-the-art.

AgroSense

At Biosense Institute we are using quadcopter DJI Inspire 1 to gain better insight into crop production and plan and manage agricultural operations more accurately. The technology can collect very high-resolution imagery below cloud level, with much more detail than the satellite imagery. The datasets include images captured with RGB and modified NDVI camera, but we are also using Flir thermal camera to make temperature measurements over large areas of heterogeneous terrain. Unmanned aerial vehicles are easy to use, as most mapping and data-collection missions are now conducted autonomously, by feeding the shape file of the desired area into the dedicated software.

&nbsp;

For image stitching we use Pix4D and AgisoftPhotoscan software to generate high-resolution orthomosaics, vegetation index maps and DSMs (Digital Surface Models). These orthomaps are important layers of information and they can be integrated into GIS systems along with other layers derived from additional sources. These datasets are then processed and used for training of advanced machine learning algorithms.

&nbsp;

BioSense uses UAS (Unmanned Aerial Systems) to detect nutrient deficiencies, pest infestations, water stress or excess and other conditions that affect crop development and improve the management of crops. They are especially useful for fields of a few dozens of hectares, such as orchards or vineyards, as scanning large fields of arable crops requires a lot of time. UAVs have also proven as effective tools for environmental monitoring, as they can cover medium-sized habitats and tell us more about the type of surroundings that insects and mammals grow in. The use of UAVs revolutionized spatial ecology and agriculture and allowed us to get high-resolution data and make optimal decisions with high accuracy.

&nbsp;

<img class="alignnone wp-image-1853 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/slika5.png" alt="" width="775" height="444" />

NDVI map of sugar beet crop

Drone Imaging

BioSense is the location of a Sentinel Data Hub and we are an active user of products from the ESA’s Copernicus programme. Before the launch of Sentinel satellites, our research was based on Landsat 7 and 8 and RapidView images, but today, it is mainly focused on data coming from Sentinel 1 and 2 missions. Images from Sentinel 2 are coming in 13 spectral bands, approximately every 5 days, depending on the cloud coverage, while Sentinel 1’s synthetic aperture radar allows for monitoring even in the case of clouds. This ensures continuous high-resolution monitoring of the environment and agricultural production in particular, throughout the growing season.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1495 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/52.png" alt="" width="960" height="600" />

&nbsp;

Since 2012, we have been producing land-cover maps for the Serbian province of Vojvodina, which distinguish fields of different crops, urban areas, forests and water bodies. This allowed us to map animal habitats, observe their change and capture the trends in crop rotation. Using the principles of data fusion, we reached the sub-pixel resolution using data sources with heterogeneous pixel grids. The second line of research is concerned with yield prediction. Based on the ground truth coming from field records, crowdsourced data and yield maps, we are training advanced machine learning models to estimate the yield. These models are based on more than 30 satellite vegetation indices, that incorporate the domain knowledge about the crops, and their accuracy is increased as plants progress through phenological stages. Vegetation indices are also excellent proxies for the damage assessment, as some of them are excellent proxies for damage caused by hail, drought or fire. This puts insurance companies among our partners, along with the government, research institutions and, nevertheless, the farmers, who are using our results to optimise the decisions concerning the time and amount of irrigation and distribution of fertilisers and pesticides.

&nbsp;

Satellite imaging

European Space Agency (ESA) has launched a constellation of Sentinel satellites through Copernicus programme. With €7 bn investment, it is the most ambitious programme of Earth observation in the history of space exploration and the satellite data have found wide application in climate change monitoring, civil engineering, and emergency response during extreme weather events. Data generated through this project are completely free and open for everyone. It is also believed that the European economy will generate €30 bn by 2030 through companies based on satellite data analytics. Due to the huge boost that Copernicus will give to high-tech start-ups and companies, people are often talking about the “Copernicus economy”.

&nbsp;

In 2017 Serbia has become the only country that as an associated member of the EU has a wideband access to ESA’s images. “Sentinel Data Hub” founded at BioSense Institute receives the data from satellites and these data are processed on high-performance servers. For the dissemination of satellite images, DHuS (Data Hub Software), a Java-based software, is used. It is an open-source software that enables user-friendly web environment for interactive discovery and download of data, as well as an excellent application programming interface (API), that allows users to access the data through their programs, scripts and client applications. In this way, the download is automated and the imagery became available to everyone around the world.

&nbsp;

ESA’s images have been widely used at the Institute for development of crop classification maps, yield prediction and growth monitoring using numerous vegetation indices, with Normalised Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and Soil-adjusted Vegetation Index (SAVI) being the most popular ones. We are expecting that Serbian companies will also use this opportunity to develop industrial solutions based on Sentinel data and come out to the global market with their innovations.

&nbsp;

Sentinel Data Hub

Big data analytics is based on heterogeneous data sources coming at different velocity and at a different resolution. Besides satellite images, BioSense’s AI group uses probes for soil electrical conductivity, handheld devices and information coming from agricultural machinery. Electrical conductivity of the soil is an excellent indicator of soil texture, compaction and chemical content and these parameters are scanned at various depths, depending on the setup and the plants of interest. Elevation maps are not less important, as they determine the flow of nutrients and often correspond to the yield, while the handheld devices, such as the BioSense’s Plant-O-Meter, are allowing for continuous growth monitoring.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1486" src="https://api.biosens.rs/wp-content/uploads/2021/06/46-212x300.jpg" alt="" width="220" height="311" /><img class="alignnone wp-image-2435" src="https://api.biosens.rs/wp-content/uploads/2021/06/prostorna-212x300.jpg" alt="" width="220" height="311" />

<img class="alignnone wp-image-1489" src="https://api.biosens.rs/wp-content/uploads/2021/06/48-212x300.jpg" alt="" width="220" height="311" /> <img class="alignnone wp-image-1490" src="https://api.biosens.rs/wp-content/uploads/2021/06/9-212x300.jpg" alt="" width="220" height="311" />

&nbsp;

Using the techniques of data fusion, heterogeneous data are aggregated into a single dataset and used for the delineation of management zones. Zone delineation is done by applying clusterization algorithms on data, either in normalised or weighted form, depending on the relative importance of input features. These management zones have different properties between one another, but soil can be considered homogeneous within each of them. This allows for issuing recommendations concerning agricultural production separately for each zone, depending on its specifics. Such localised decision-making is the essence of the precision agriculture and it is also a necessary first step in determining the optimal sensor locations, which maximise their effectiveness.

Geospatial data analytics

With the occurrence of non-parametric machine learning models and especially with the rising popularity of deep neural networks, most of classifiers and regressors used today are essentially black boxes. Their accuracy is often unmatchable by any conventional model, and although we know the principles and mathematics behind them, we cannot directly infer the complex relationships between input and output features. Having an accurate model has a huge practical value, but in order to have richer knowledge about the problem and push the boundaries of science, we need to delve deeper into the black box.

&nbsp;

<img class="alignnone wp-image-1474 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/39-1.jpg" alt="" width="1187" height="1028" />

&nbsp;

There are a few techniques we are relying on in knowledge discovery and all of them are based on indirect observations of the machine learning models. One of them is the random permutation test, which estimates the feature importance based on the decrease in model accuracy in case of random permutation of its values in the dataset. Morris’s and Sobol’s uncertainty and sensitivity analyses on the other hand are telling us more about the possible outputs of the system and the interaction between the input parameters. Model explanation analysis even goes a step further. For each feature used in predictive model, through sampling-based approximation it gives the estimate of feature’s positive or negative contribution to the output, which enables us to direct the domain researcher to where it’s the most effective. These and other methods allowed us to determine the influence of various soil and weather parameters on the yield and to characterise drought resistant maize hybrids or varieties of soya with stable yield.

&nbsp;

<img class="alignnone wp-image-1476 " src="https://api.biosens.rs/wp-content/uploads/2021/06/40-1024x768.jpg" alt="" width="351" height="263" /><img class="alignnone wp-image-1477 " src="https://api.biosens.rs/wp-content/uploads/2021/06/41-1024x768.jpg" alt="" width="351" height="263" />

Knowledge discovery

The goal of BioSense’s AI Group is to get a comprehensive and accurate overview of biosystems, make phenotyping and plant breeding more efficient, understand molecular biology better and offer optimal and automatic decision-making to the farmer. Our research starts with the problem and requires innovative application of state-of-the-art algorithms and development of the novel ones. Machine learning algorithms extensively used in BioSense applications include Random Forest, SVM, Decision Trees, Ridge Regression, Spectral Clustering and many others including special family of machine learning algorithms- Deep Learning, and where the complexity of the problem goes beyond the available algorithms, BioSense researchers develop the novel ones.

&nbsp;

Example of novel algorithm is include weighted histograms regression (WHR). WHR is based on a voting mechanism, where training samples are voting for the output value of a test sample. The votes are weighted according to the similarity of features and used to form a histogram that essentially represents the PDF of the output, while the expectation of the PDF is essentially the predicted value. This algorithm proved very useful for yield prediction, where it outperformed random forest, SVM and artificial neural networks.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1478 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/42.png" alt="" width="503" height="504" />

&nbsp;

&nbsp;

Another novel algorithm is integrative clustering based on Nonnegative matrix factorization. Combining results of individual clusterings together into an ensemble leverages evidence accumulation in order to improve the results of clustering. Individual clustering results are merged into a joint cluster membership matrix that is further factorized into matrices of encodings and basis. Algorithm can integrate clusterings stemming from different data sets, different data preprocessing steps or different subsamples of features or objects.

&nbsp;

This algorithm proved very useful for functional genomics. Proposed approach based on nonnegative matrix factorization can fuse diverse data sources and infer gene clusters with high functional enrichment and improved gene coverage.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1480 size-large" src="https://api.biosens.rs/wp-content/uploads/2021/06/43-1024x419.png" alt="" width="1024" height="419" />

Machine Learning

Machine learning and domain expertise are often viewed as two competing approaches for solving problems in any area, including agriculture. Our strategy is to use the best from both worlds. Machine learning algorithms show excellent performance in finding hidden dependencies within the data, but there are already well-established theories that explain the natural processes and they have been proven in practice. We are fully exploiting this fact by incorporating the domain knowledge in our models. This is usually done in the process of feature selection and feature engineering.

&nbsp;

One of the examples of feature engineering, based on the domain expertise, was used for the selection of stress-tolerant maize hybrids in Syngenta Crop Challenge in Analytics 2019. Drought is a phenomenon related to longer period of time without precipitation accompanied with high temperatures and low air humidity. However, there is no strict mathematical formulation of drought and many indicators have been used in practice.

&nbsp;

Based on daily values of maximum and minimum temperature, precipitation and vapor pressure in several stages throughout the growing season, we designed features indicating to drought and heat stress at the specific environment. They included maximum number of consecutive dry days, low precipitation sum in a certain growth stage and vapor pressure deficit. In this problem, the engineered features helped us to determine the drought-resistant hybrids that should be planted to maximise the yield and minimise the risk of low income for the farmer, but they can be used in other as well. Other examples include engineering of meteorological features for prediction of airborne pollen concentrations, engineering of elevation features to better predict the flow of nutrients in the field and engineering of features that describe the animal behaviour for prediction of disease and mammary inflammation.

<img class="alignnone wp-image-1471 size-large" src="https://api.biosens.rs/wp-content/uploads/2021/06/38-1024x768.jpg" alt="" width="1024" height="768" />

<img class="alignnone wp-image-1473 size-large" src="https://api.biosens.rs/wp-content/uploads/2021/06/39-1024x768.jpg" alt="" width="1024" height="768" />

Feature Engineering

Deep learning is a rather new method of machine learning, that is due to its specifics and excellent performance in image processing often considered as a separate field within artificial intelligence. It works best with big datasets which have multi-dimensional characteristics, and there are a number of such datasets processed at BioSense.

&nbsp;

The first group of datasets are hyperspectral, multispectral and thermal images acquired in the lab or during the outdoor field experiments. Here, the the goal was to segment the images and recognise characteristic patterns within them, such as bruises and scratches on apples, infected tomato sepals or ears in images of wheat. Different architectures were tested with various parameters, which included the number of convolutional and fully connected layers, type of activation functions and position of dropout layers. They all were optimised for a particular problem, concerning the size of input images and the number of samples in the database.

&nbsp;

<img class="alignnone wp-image-1469 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/337.jpg" alt="" width="640" height="480" />

&nbsp;

The second group consists of airborne particle measurements acquired with Rapid-E, the ﬁrst automated particle detector based on laser-induced ﬂuorescence technology, which records scattered light and laser-induced fluorescence patterns, representing the shape and chemical footprint of the particles. This is one of the examples of deep neural networks (DNNs) that relied heavily on convolutional layers, due to their ability to deal with datasets fused from different data sources.

&nbsp;

In both applications, preprocessing is perhaps the most vital task, as the noisy and non-standardised inputs are very difficult to analyse. Also, an important thing to note is that every problem requires a customised solution, whose complexity corresponds to the richness of the dataset and whose accuracy justifies its learning and execution times.

Deep Learning

The most of BioSense’s research in Big Data is currently concerned with two types of datasets that require huge storage capacity and extremely efficient algorithms that will process them in the specified time requirements.

&nbsp;

The first of them are satellite images. Sentinel 2 satellites are releasing new 13-band images of any given point on Earth approximately every 5 days. These images come in 100x100 km2 tiles, with a 10 m resolution. Within Cybele project, for example, we are analysing satellite images of the whole Europe to classify soya fields, meaning that we need to go through hundreds of tiles and apply the classification algorithm. In such situations, we are parallelising the code to better suit the multi-core server architecture, speeding up its parts using Cython, but also adjusting the implementations to lower the computational complexity of the algorithm.

&nbsp;

Another type of data are call detail records of mobile phone users and they satisfy all the V’s of big data analytics. These records consist of lists of established calls, exchanged text messages and registered internet traffic and are enormous in size. An important issue that needs to be addressed is concerned with privacy and it is a huge challenge to extract useful information from anonymised or aggregated datasets. Also, although the data is semi-structured, the traditional RDBMS technology for data analytics is not applicable to datasets of this volume, so we are developing processing workflows using Apache family of technologies, such as Spark, Hadoop and Hive. They allow us to get a deeper insight into human behaviour and mobility patterns and infer the interaction between rural and urban areas.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1465 size-large" src="https://api.biosens.rs/wp-content/uploads/2021/06/35-1024x578.jpg" alt="" width="1024" height="578" />

Big Data Analytics

AgroSense APV

Centar za senzorske tehnologije

Centar za Informacione Tehnologije

Centar za razvoj proizvoda

Cilj projekta: Digitalna platforma AgroSens APV sastoji se od web i mobilne aplikacije koje omogućavaju praćenje realizacije konkursa za dodelu bespovratnih sredstava koje raspisuje Pokrajinski sekretarijat za poljoprivredu, vodoprivredu i šumarstvo.
&nbsp;
Opis projekta: Omogućeno je automatsko rangiranje prijava na Konkurse kao i generisanje ugovora i raznih rešenja. Automatskim generisanjem naloga za kontrolu prijava na konkurs I dodeljivanjem naloga savetodavnim službama, koje onda pomoću mobilnih telefon vrše kontrolu i verifikaciju na terenu, unapređen je rad i savetodavnih stručnih službi. Kroz AgroSens APV platformu omogućena je satelitska verifikacija podataka dobijenih sa terena. Pomoću satelitskog nadzora svake katastarske parcele i u skladu sa rezolucijom i tehničkim mogućnostima Sentinel snimaka, moguće je dodatno verifikovati realizaciju Konkursa.
&nbsp;
Ova platforma omogućava i upravljanje kontrolom plodnosti zemljišta od strane poljoprivrednih stručnih i savetodavnih službi. Kreiranjem zadataka za uzorkovanje zemljišta omogućeno je savetodavcima da putem mobilnog telefona kreiraju uzorak i definišu njegovu geo-lokaciju. Evidentiranjem laboratorijskih rezultata uzoraka zemljišta omogućava se uvid u stanje plodnosti zemljišta. Takođe, setvena struktura za Autonomnu pokrajinu Vojvodinu, od 2013. pa do danas, dostupna je kroz digitalnu platformu AgroSens.
&nbsp;
&nbsp;
<img decoding="async" loading="lazy" class="alignnone size-full wp-image-548" src="https://api.biosens.rs/wp-content/uploads/2021/06/Logo-SRb-1-1.png" alt="" width="295" height="65" />

Naučni savetnik

Milan Stanojković zaposlen je na poziciji mlađeg saradnika u Centru za razvoj proizvoda Instituta BioSens. Osnovne (2018) i master (2022) akademske studije je završio na Prirodno-matematičkom fakultetu Univerziteta u Novom Sadu, na smeru Informacione tehnologije. Na Institutu BioSens trenutno radi na razvijanju web aplikacija. Backend implementira u Java okruženjima (Spring, EJB). Za frontend koristi Angular i AngularJS. Takođe radi sa bazama podataka i serverima (Wildfly i Tomcat).

Goran Adžić je zaposlen na poziciji starijeg saradnika u centru za razvoj proizvoda. Završio je master (2015) i osnovne akademske studije (2013) na Fakultetu tehničkih nauka u Novom Sadu, smer geodezija i geomatika. Od 2014. radi na razvoju gis aplikacija i softverskih rešenja namenjenih državnoj upravi i lokalnoj samoupravi. U BioSensu radi na razvoju web aplikacija, za koje koristi Javu, Angular i PostgreSQL bazu podataka. Upisao je doktorske studije 2020. godine.

&nbsp;

Slobodan Birgermajer je naučni saradnik u Centru za Senzorske Tehnologije pri Institutu BioSens. Doktorat iz mikrotalasne elektronike odbranio je 2019. godine na Fakultetu Tehničkoih Nauka, Univerziteta u Novom Sadu. Trenutno radi na razvoju i primeni senzora u poljprivredi, prehrambenoj industriji i monitoringu životne sredine, i aktivno je uključena na više međunarodnih projekata iz poziva H2020, kao što su ANTARES, SHEALTY, IPANEMA, i drugi. Takođe, domen istraživanja obuhvata razvoj i fabrikaciju mikrotalasnih pasivnih kola, fotonskih kristala, mikrofludinih senzora, kao i 3D i 4D tehnologiju štampe.

&nbsp;

Mina Mirović je zaposlena kao mlađi istraživač na BioSense Institutu. Osnovne studije iz oblasti mehatronike završila na Univerzitetu u Novom Sadu a Master studije iz oblasti mehatronike, robotike i embeded sistema završila je na London South Bank Univerzitetu.

Željko Bajić je masterirao 2012. godine na Prirodno matematičkom fakultetu u Novom Sadu. Na Biosense institutu radi kao stariji saradnik. Bavi se programiranjem na svim nivoima uglavnom bazirano na Java programskom jeziku i raznim web tehnologijama. Aktivno učestvuje na nekoliko nacionalnih i međunarodnih projekata.

Vladan Minić je menadžer Centra za razvoj proizvoda na Institutu BioSens. Zvanje Master elektrotehnike i računarstva je stekao na Fakultetu tehničkih nauka u Novom Sadu 2007 godine. Karijeru je započeo u BioSens centru pri istom fakultetu. Kada je centar prerastao u Institut, prelazi u novoosnovanu instituciju. Učestvovao je u brojnim domaćim i internacionalnim projektima u okviru BioSensa. Glavna interesovanja su mu vezana za bežične senzorske mreže, obradu slike, ali je obavljao i poslove sistem administratora. Njegova ekspertiza pokriva Linux i Windows sisteme; web razvoj - WordPress, Joomla, PHP, HTML; programski jezici: Python. C/C++ (OpenCV), Matlab; baze podataka: MySQL, PostgreSQL, MS SQL, SQLite; GIS alati: ArcGIS, QGIS. Takođe je zaljubljenik u hardware i embedded sisteme.

Mina Bjelica radi kao mlađi saradnik u centru za razvoj proizvoda na BioSense Institutu. Diplomirala je 2019. godine na Univerzitetu u Novom Sadu, na Prirodno – matematičkom fakultetu, na smeru Informacione tehnologije. U BioSensu trenutno radi na razvoju i održavanju nekoliko web aplikacija u programskom jeziku Java (EJB I Spring okruženja) za backend, za frontend koristi jezike: TypeScript (Angular okruženje), AngularJS okruženje, HTML, CSS, jezike koje koristi za baze podataka su: SQL i HQL, i servere: wildfly i tomcat.

&nbsp;

Milijana Vujasinović je rukovodilac Centra za razvoj proizvoda. Ima višegodišnje iskustvo u razvoju i implementaciju softverskih rešenje. U razvoju softverskih rešenja učestvovala je u početku kao programer i biznis analitičar, a kasnije i kao projektant rešenja i menadžer proizvoda. Bogato iskustvo je stekla radeći kao ERP konsultant i menadžer projekata u implementacijama softverskih rešenja u različitim privrednim granama – poljoprivrednoj,veleprodaji i maloprodaji, prehrambenoj industriju, tekstilnoj industriju, metalurgiji, industriji alata i kablova, građevinskoj industriju, uzlužnoj delatnost kao i u javnim preduzećima. Sertifikovani je SAP FI i SAP Project Manager. Više od 3 godine je upravljala PMO (Project Managment Office), odeljenjem koji kontroliše i unapređuje proces upravljanje projektima.

Milica Milovanovic radi kao mlađi saradnik u BioSense Institutu. Diplomirala je 2019. godine Univerzitetu u Novom Sadu na Prirodno-Matematičkom fakultetu, na smeru Informacione tehnologije. Na institutu trenutno radi na razvijanju web aplikacija. Backend implementira u Java i Python okruženjima (Spring, EJB i Django). Za frontend koristi Angular i AngularJS. Takođe radi sa bazama podataka i serverima (Wildfly i Tomcat).

Predrag Lugonja je istraživac na Institutu BioSens. Diplomirao je na Departmanu za Energetiku, elektroniku i telekomunikacije Fakulteta tehničkih nauka Univerziteta u Novom Sadu. Student je završne godine doktorksih studia na Fakulteta tehničkih nauka Univerziteta u Novom Sad. Trenutno se bavi istraživanjem na poljima GIS i podataka koje su dobijeni daljinskom detekcijom.

Dr Oskar Marko je rukovodilac Centra za informacione tehnologije i pomoćnik direktora za inovacije i saradnju sa privredom. Njegovo istraživanje usmereno je ka primeni naprednih metoda mašinskog učenja i evolutivnih algoritama u poljoprivredi. Treću godinu osnovnih studija je pohađao je na “Siti univerzitetu” u Londonu, gde je odbranio diplomski rad u domenu obrade signala. Vodio je tim BioSensa koji je razvio nove algoritme iz oblasti obrade velikih podataka koje su za cilj imale predikciju prinosa, distribuciju semena i optimizaciju strategije setve, koje su Institutu osigurale prvo mesto na Sindžentinom “Izazovu za useve” i CGIAR-ovom “Inspirišućem izazovu”. Aktivno je uključen u mnoge projekte iz poziva Horizont 2020, među kojima su Antares, Cybele, Dragon i Flexirobots, kao i u projekte sa kompanijama poput Krivaje, MK Agri, Delte i drugih poljoprivrednih kompanija i osiguravajućih kuća.

Nastasija Grujić je istraživač pripravnik na Institutu BioSens i student doktorskih studija geoinformatike na Univerzitetu u Novom Sadu, na Fakultetu tehničkih nauka. Završila je master (2018) i osnovne akademske studije (2017) u oblasti geodezije i geomatike. Tokom studija je dobila dve Dositejeve nagrade za najboljih 800 i 400 studenata u državi (školske godine 2016/2017 i 2017/2018 redom). Na kraju 2018. godine je upisala doktorske studije i počela je raditi na Institutu BioSens. Tokom studija je bila dva puta gostujući istraživač na Univerzitetu u Vageningenu, gde se upoznala sa agentskim modelovanjem kompleksnih i stohastičkih sistema. Njena interesovanja uključuju širok spektar analitike podataka, mašinskog učenja i geoinformatike koji se koriste za bolje razumevanje i simulaciju kompleksnih prostornih sistema pomoću agentskih simulacija. Učesnik je na raznim nacionalnim i internacionalnim projektima, uključujući i H2020 projekte ANTARES, DRAGON i BESTMAP.

Mirjana Radulović je istraživač-pripravnik na Institutu Biosens čija interesovanja su okrenuta ka daljinskoj detekciji, geoinformatici, upravljanju vodnim resursima, poljoprivredi i životnoj sredini. Ona je trenutno student doktorskih studija geonauka na Prirodno-matematičkom fakultetu, Univerzitetu u Novom Sadu gde je takođe stekla diplomu osnovnih (2017) i master studija (2018) u oblasti hidrologije i geoinformatike. Tokom master studija pet meseci provela je na Univerzitetu Palacký u Olomoucu (Republika Češka), gde je studirala kao stipendista Erasmus + programa razmene. U martu 2019. godine pridružuje se Institutu Biosens gde radi na primeni geografskih informacionih sistema i tehnologija daljinske detekcije za praćenje navodnjavanih površina, suše, stanja useva, klasifikaciju iskoristivosti zemljišta, praćenje podzemnih voda itd. Učestvuje na nekoliko nacionalnih i internacionalnih projekata vezanih za navedene teme. Bila je autor i koautor na nekoliko radova i prisustvovala je na nekoliko naučnih konferencija.

Miloš Pandžić je istraživač pripravnik čije interesovanje pokriva nekoliko istaživačkih oblasti: osmatranje Zemlje, daljinsku detekciju, obradu slike i analitiku podataka. Trenutno je student doktorskih studija odseka za Geodeziju i geoinformatiku na Građevinskom fakultetu, Univerziteta u Beogradu, gde je takođe završio i osnovne i master akademske studije. U 2015. godini dobio je stipendiju vlade Austrije (OeAD) i proveo 4 meseca na Tehničkom univerzitetu u Beču gde je analizirao geometrijski kvalitet Sentinel-2 satelitskih multispektralnih snimaka. Iz ovog istraživanja je proizašao i Milošev master rad. Nakon završetka studija, radio je u Finskom geoprostornom istraživačkom institutu (Finnish Geospatial Research Institute - FGI) na više projekata finansiranih od strane Finske Akademije i Evropske svemirske agencije. Tu je radio na segmentaciji i detekciji promena na satelitskim slikama za potrebe poljoprivrede, urbanizma i šumarstva. U 2018. godini pridružio se Institutu BioSens gde radi na fuziji podataka optičkih i radarskih slika za procenu prinosa, klasifikaciju useva, praćenje razvoja useva, itd. Učestvuje u realizaciji nekoliko nacionalnih i internacionalnih projekata uključujući Horizon 2020 projekte Antares, Cybele, Dragon, PARSEC i agROBOfood.

Gordan Mimić je naučni saradnik na Biosens Institutu. Gordan Mimić je završio osnovne (2011), master (2012) i doktorske (2016) studije fizike-meteorologije na Prirodno-matematičkom fakultetu, Univerziteta u Novom Sadu. Radio je u Republičkom hidrometeorološkom zavodu Srbije tokom perioda 2011-2012, u odeljenju za numeričku prognozu vremena. Gordan Mimić je radio kao asistent na raznim predmetima iz oblasti meteorologije na Univerzitetu u Novom Sadu (Prirodno-matematički fakultet i Poljoprivredni fakultet) u periodu 2012-2017 godina. Trenutno se bavi analitikom podataka u oblasti agrometeorologije i biometeorologije. Predvodio je tim BioSensa koji je razvio novi algoritam za klasifikaciju hibrida kukuruza koji si otporni na sušu i toplotni stress, i za koji su osvojili treću nagradu na Sindžentinom “Izazovu za useve” 2019. godine. Učestvovao je na nekoliko nacionalnih i međunarodnih projekata. Gordan Mimić je koautor 20 naučnih radova, 4 konferencijska rada i 1 poglavlja u knjizi.

Dragana Blagojević je završila osnovne (2017) i master (2018) akademske studije smer geograf-geoinformatičar na Departmanu za geografiju, turizam i hotelijerstvo na Prirodno-matematičkom fakultetu u Novom Sadu. Njena istraživanja za završne radove su obuhvatala upotrebu geografskih informacionih sistema u analizi hidroloških i geomorfoloških procesa u prirodi. Na istom fakultetu, u oktobru 2018. godine upisuje doktorske studije, smer – Geonauke. Letnji semestar master studija provela je u Češkoj na Departmanu za Geoinformatiku na Palacki Univerzitetu u Olomoucu kao stipendista Erasmus+ programa razmene studenata. U januaru 2018. godine počinje da radi na Institutu BioSens gde je zaposlena kao istraživač-pripravnik u okviru Centra za informacione tehnologije. Njeni domeni istraživanja su daljinska detekcija, precizna poljoprivreda, monitoring i mapiranje prinosa, kao i analiza podataka dobijenih na terenu. Cilj njenog istraživanja je integracija ovih tehnika kako bi se dobila kompletna i precizna informacija o stanju poljoprivredne parcele, useva, fizičkih karakteristika terena i zemljišta.

&nbsp;

Dejan Pavlović je istraživač na Institutu Biosens i student doktorskih studija na Elektrotehničkom fakultetu, Univerziteta u Beogradu. Njegovo primarno interesovanje obuhvata obradu signala i primenu mašinskog učenja u poljoprivredi. Dejan je stekao zvanje diplomiranog inženjera biomedicinskog inženjerstva na Fakultetu tehničkih nauka, Univerziteta u Novom Sadu i zvanje master inženjera elektrotehnike i računarstva na Elektrotehničkom fakultetu, Univerziteta u Beogradu. Trenutno radi na razvoju algoritma za klasifikaciju različitih aktivnosti kod krava primenom Konvolucionih neuralnih mreža. Učestvuje u realizaciji nekoliko nacionalnih i internacionalnih projekata uključujući Horizon 2020 projekte, Antares i Dragon.

Branislav Pejak je student doktorskih studija Elektrotehničkog i kompjuterskog inženjerstva na Fakultetu tehničkih nauka, Univerziteta Novi Sad, na kojem je takođe završio osnovne (2017) i master (2018) studije u oblsti Biomedicinskog inženjerstva. Tokom osnovnih i master studija bio je stipendista Ministarstva obrazovanja, nauke i tehnološkog razvoja, Republike Srbije. Od marta 2018. godine zaposlen je u Centru za informacione tehnologije, Instituta BioSens, na poziciji mlađeg istraživača. Tema njegovog istraživanja je analiza podataka sa satelitskih snimaka. Trenutno se bavi razvojem GAN algoritama mašinskog učenja za klasifikaciju i predikciju prinosa na bazi multispektralnih satelitskih snimaka. Aktivno je uključen u mnoge projekte sa poziva Horizont 2020, među kojima su Antares, Cybele, Dragon i AgRoboFood koji imaju za cilj upotrebu informaciono-komunikacionih tehnologija u poljoprivredi poput kreiranja mapa za selektivno uzorkovanje i đubrenje zemljišta, detekciju navodnjavanih površina, procenu prinosa i proteinskog sastava useva.

&nbsp;

Dr Nataša Ljubičić, naučni saradnik, doktorirala je na Poljoprivrednom fakultetu, u Novom Sadu u oblasti Biotehničkih nauka i užoj naučnoj oblasti Genetika i oplemenjivanje biljaka. Magistarsku tezu pod nazivom: ”Multivarijaciona analiza genotipova pšenice gajenih na meliorisanom solonjecu”, kao i diplomski rad iz predmeta Pedologija, odbranila je na Poljoprivrednom fakultetu, u Novom Sadu. Dr Nataša Ljubičić je angažovana u svojstvu naučnog saradnika u okviru Centra za biosisteme, Instituta BioSens u Novom Sadu. Oblast istraživanja obuhvata primenu inovativne i pametne tehnologije u službi povećanja prinosa glavnih poljoprivrenih kultura i pre svega unapređenja poljoprivredne proizvodnje. Istraživanja obuhvataju praćenje fenotipske stabilnosti osobina različitih genotipova pšenice, kukuruza i drugih poljoprivrednih kultura u različitim agroekološkim uslovima, kao i procenu interakcije genotip/spoljna sredina kao različit odgovor biljke na različite uslove sredine. U istraživanjima, fenotipska varijabilnost je praćena merenjem spektralnog odziva biljaka, gde se primenom aktivnih i pasivnih senzora izračunava više od 40 različitih vegetacionih, tj. spektralnih indeksa. Ovakvo udruživanje podataka doprinosi razvoju metoda za procenu stanja biljaka pre vidljivih simptoma i daje smernicu za unapređenje tehnologije proizvodnje, a pre svega maksimalnom iskorišćavanju rodnosti ispitivanih genotipova za područja istih ili sličnih agroekoloških uslova. Pored odabira adekvatnih vegetacionih indeksa, definišu se mere koje pogoduju ili eventualno štete proizvodnji useva za određene lokalitete. Dr Nataša Ljubičić je u dosadašnjem radu bila angažovana u okviru nekoliko projekata Ministarstvo prosvete, nauke i tehnološkog razvoja Republike Srbije, učesnik u međunarodnim recenzijama, kao i član udruženja EUCARPIA (European Association for Research on Plant Breeding). Dr Nataša Ljubičić je u dosadašnjem naučnoistraživačkom radu, kao autor ili koautor, objavila preko 50 naučnih radova u međunarodnim i nacionalnim časopisima koje prema bazi Google Scholar, imaju preko 80 citata u međunarodnim čaopisima i vrednost 6 za Hiršov indeks.

Bojana Ivošević se bavi upotrebom bespilotnih letelica za efikasno nadgledanje ratarskih kultura, slatkih voda i životne sredine. Ona je po struci biolog i ekolog. Doktorske studije je upisala na Kyungpook Nacionalnom Univerzitetu u Južnoj Koreji, gde je stekla dve godine iskustva rada na bespilotnim letelicama. Nastavila je studije na Prirodno-matematičkom fakultetu, Univerzitetu u Novom Sadu. Njen trenutni fokus istraživanja je primena bespilotnih letelica u preciznoj poljoprivredi za izračunavanje vegetacijskih indeksa važnih za procenu prinosa, detekciju bolesti i upravljanje usevima. Takođe je zainteresovana za primenu dronova u detekciji i prebrojavanju životinjskih vrsta, praćenju cvetanja algi, klasifikaciju zemljišnog pokrivača i sezonskih efekata na ekosisteme.

Nacionalni

Na Institutu BioSens koristimo slike kvadkoptera DJI Inspire 1 kako bismo dobili bolji uvid u stanje useva i preciznije planirali i upravljali agroekološkim aktivnostima. Ova tehnologija omogućava prikupljanje podataka visoke rezolucije ispod nivoa oblaka sa mnogo više detalja nego što se može videti u satelitskim snimcima. Skup podataka uključuje slike iz vidljivog dela spektra kao i slike dobijene modifikovanom NDVI kamerom. Takođe koristimo i Flir termalnu kameru za merenje temperature na velikim površinama u hetoregenim staništima. Bespilotne letelice su jednostavne za upotrebu, jer se većina mapiranja terena i prikupljanja podataka sada sprovodi autonomno, prema zadatim granicama terena uz pomoć aplikacija za planiranje leta.

&nbsp;

Za preklapanje slika koristimo softvere Pix4D i AgisoftPhotoscan kako bismo generisali ortomozaike, mape vegetacionih indeksa i digitalne modele površine. Ove orto-mape su važni slojevi informacija i mogu se integrisati u GIS sisteme zajedno sa slojevima podataka dobijenih iz drugih izvora. Ovakvi skupovi podataka se zatim obrađuju i koriste za obuku naprednih algoritama mašinskog učenja.

&nbsp;

BioSens koristi bespilotne vazdušne sisteme za otkrivanje nedostatka hranljivih materija u biljkama, napada štetočina, prekomerne suše ili vlage kao i drugih faktora koji utiču na razvoj useva, kao i za povećanje efikasnosti pri donošenju odluka. Posebno su korisni za površine od nekoliko desetina hektara, poput voćnjaka i vinograda, jer skeniranje velikih ratarskih parcela zahteva mnogo vremena. Bespilotne letelice su se pokazale i kao efikasni alati za praćenje stanja ekosistema. Pokrivajući veća prostranstva, omogućavaju pristup informacijama o tipu staništa u kojem rastu i razvijaju se živi organizmi od insekata do sisara. Njihova upotreba dovela je do revolucionarnih otkrića na poljima prostorne ekologije i poljoprivrede, i omogućila nam dobijanje podataka visoke rezolucije za donošenje optimalnih odluka sa visokom preciznošću.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1853 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/slika5.png" alt="" width="775" height="444" />

NDVI map of sugar beet crop

Obrada slika sa dronova

BioSens je dom habu za Sentinel podatke i kao takav je korisnik proizvoda Kopernikus programa Evropske svemirske agencije (ESA). Pre lansiranja Sentinel satelita, naša istraživanja su se zasnivala na snimcima sa satelita Landsat 7 i 8, kao i RapidView-a, ali su danas primarno usmerena na podatke koji potiču sa Sentinel 1 i 2 misija. Slike sa Sentinela 2 sadrže 13 spektralnih kanala i dostupne su na svakih 5 dana u zavisnosti od oblačnosti, dok Sentinel 1 koji snima radarske slike omogućava praćenje čak i u slučaju oblačnosti. Na ovaj način omogućeno je kontinualno osmatranje površine Zemlje u visokoj rezoluciji uključujući praćenje poljoprivrednje proizvodnje kroz sve faze rasta biljaka.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1495 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/52.png" alt="" width="960" height="600" />

&nbsp;

Od 2012. godine proizvodimo mape upotrebe zemljišta za Autonomnu Pokrajinu Vojvodinu, gde klasifikujemo zemljište u šume, vodene mase, urbane površine i različite tipove useva. Ovakve mape su nam omogućile da mapiramo životinjska staništa, posmatramo kako se menjaju tokom godina i ispratimo plodored na proizvodnim parcelama. Oslanjajući se na principe fuzije podataka, uspeli smo da dođemo do sub-pikselske rezolucije korišćenjem višestrukih izvora podataka sa heterogenim mrežama piksela. Druga grana našeg istraživanja se bavi prognozom prinosa useva. Na osnovu podataka sa terena dobijenih pomoću digitalnih knjiga polja, kraudsorsinga ili mapa prinosa, obučavamo napredne modele mašinskog učenja u cilju što bolje procene prinosa. Ovakvi modeli koriste više od 30 satelitskih vegetacionih indeksa koji uključuju domensko znanje o usevima, a njihova tačnost se povećava kako napredujemo kroz faze razvoja biljaka. Vegetacioni indeksi su takođe odlični pokazatelji procene štete jer neki od njih veoma dobro reaguju na pojavu prirodnih nepogoda poput suše, požara i izmrzavanja. Na ovaj način se osiguravajuća društva uključuju u partnerstvo sa Institutom, zajedno sa državnim oragnima, istraživačkim institucijama i poljoprivrednim proizvođačima koji naše rezultate koriste za optimalno donošenje odluka o navodnjavanu i distribuciji đubriva i pesticida.

Obrada satelitskih slika

Evropska svemirska agencija je kroz Kopernikus program lansirala plejadu Sentinel satelita. Sa svojih 7 milijardi evra ulaganja, Kopernikus je najambiciozniji poduhvat satelitskog snimanja Zemlje u istoriji svemirskih istraživanja, a podaci sa satelita su našli široku primenu u praćenju klimatskih promena, građevinarstvu, saobraćaju i reagovanju u kriznim situacijama poput zemljotresa i vremenskih nepogoda. Podaci generisani kroz ovaj projekat su besplatni i potpuno otvoreni za svakoga. Veruje se da će evropska privreda do 2030. generisati čak 30 milijardi evra kroz preduzeća čija delatnost se zasniva na obradi satelitskih slika. Zbog ovako velikog zamajca koji Kopernikus daje visokotehnološkim startapovima i velikim kompanijama, često se koristi izraz „Kopernikus ekonomija“.

&nbsp;

Godine 2017. Srbija je postala jedina zemlja koja kao pridruženi član EU ima širokopojasni pristup ESA-inim slikama. Hab za Sentinel podake koji je otvoren na Institutu BioSens dobija podatke sa satelita, a nakon toga se podaci obrađuju na serverima visokih performansi. Za samu diseminaciju satelitskih slika zadužen je softver zasnovan na Javi - DHuS (Dejta Hab Softver). DHuS je softver otvorenog koda koji obezbeđuje jednostavno veb okruženje za interaktivno otkrivanje i preuzimanje podataka, kao i odličan interfejs za programiranje aplikacija (API) koji korisnicima omogućava pristup podacima preko sopstvenih računarskih programa, skripti ili klijentskih aplikacija. Time se automatizuje preuzimanje u okviru njihovog radnog procesa, a sami snimci postaju dostupni zainteresovanim stranama iz svih krajeva sveta.

&nbsp;

ESA-ine satelitske slike se već uveliko koriste na Institutu, za dobijanje mapa setvene strukture, procenu prinosa i praćenje rasta i razvoja useva u čiju svrhu se koriste brojni vegetacioni indeksi od kojih su najpoznatiji „normalizovani diferencijalni vegetacioni indeks“ (NDVI), „unapređeni vegetacioni indeks“ (EVI), „indeks vegetacije prilagođen zemljištu“ (SAVI) i mnogi drugi. Očekujemo i da će srpska preduzeća iskoristiti ovu priliku, razviti industrijska rešenja na bazi Sentinel slika i sa svojim inovacijama izađi na svetsko tržište.

Hab za Sentinel podatke

Analitika velikih podataka se zasniva na obradi heterogenih izvora podataka, različitih rezolucija, koji se prikupljaju u nejednakim vremenskim intervalima. Osim satelitskih podataka, Grupa za veštačku inteligenciju Instituta BioSens prikuplja i koristi podatke dobijene pomoću elektromagnetne sonde koja meri električnu provodnost zemljišta, kao i brojne druge instrumente koji se montiraju na poljoprivredne mašine ili koriste iz ruke. Električna provodnost zemljišta je odličan indikator teksture zemljišta, njene kompaktnosti i hemijskog sastava. Ovi parametri mogu se odrediti na različitim dubinama u zavisnosti od potreba i interesovanja korisnika prema tipu biljaka. Mape elevacije terena nisu ništa manje važne s obziorm na to da određuju pravac i smer oticanja nutrijenata koji je u tesnoj sprezi sa prinosom, dok se ručni uređaji, poput Plant-O-Meter-a razvijenog od strane istraživača Instituta BioSens, uspešno koriste pri monitoringu rasta useva.

&nbsp;

<img class="alignnone wp-image-1486 " src="https://api.biosens.rs/wp-content/uploads/2021/06/46.jpg" alt="" width="220" height="312" /><img class="alignnone wp-image-2435" src="https://api.biosens.rs/wp-content/uploads/2021/06/prostorna-212x300.jpg" alt="" width="220" height="311" />

<img class="alignnone wp-image-1487" src="https://api.biosens.rs/wp-content/uploads/2021/06/47-212x300.jpg" alt="" width="220" height="311" /><img class="alignnone wp-image-1490" src="https://api.biosens.rs/wp-content/uploads/2021/06/9-212x300.jpg" alt="" width="220" height="311" />

&nbsp;

Korišćenjem tehnika fuzije podataka, heterogeni podaci se agregiraju u jedinstven skup koji se koristi za iscrtavanje, odnosno određivanje menadžment zona. Određivanje zona vrši se algoritmima klasterizacije bilo u normalnoj ili težinskoj formi, što zavisi od relativne važnosti ulaznih podataka. Ove menadžment zone međusobno imaju različite osobine, ali se u okviru jedne zone zemljište može posmatrati homogenim. To dalje omogućava davanje preporuka o poljoprivrednoj proizvodnji za svaku zonu ponaosob, u skladu sa njenim specifičnostima. Ovakav pristup donošenju odluka u okviru jedne parcele osnova je za preciznu poljoprivredu, a ujedno je i prvi korak pri određivanju optimalne lokacije za postavljanje senzora jer se na taj način maksimizuje njihova efikasnost.

Analitika prostornih podataka

Sa pojavom neparametaskih modela mašinskog učenja i rastućom popularnošću dubokih neuronskih mreža, većina klasifikatora i regresora koji se danas koriste su “crne kutije”. Tačnost ovih modela često je neuporedivo bolja nego kod konvencionalih modela, a iako znamo matematiku koja se krije iza njih, ipak ne možemo direktno da zaključimo kompleksnu vezu izmeću ulaznih i izlaznih podataka. Velika tačnost modela je od izuzetnog praktičkog značaja, ali kako bismo imali bolje razumevanje problema i kako bismo pomerili granice nauke moramo da zagrebemo dublje u način njihovog funkcionisanja.

&nbsp;

<img class="alignnone wp-image-1474 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/39-1.jpg" alt="" width="1187" height="1028" />

&nbsp;

&nbsp;

Oslanjamo se na nekoliko tehnika otkrivanja znanja, koje se baziraju na indirektnim posmatranjima modela mašinskog učenja. Jedan od njih je test slučajne permutacije. Pomoću njega procenjujemo važnost obeležja na osnovu smanjenja tačnosti modela nakon slučajne permutacije obeležja u skupu podataka. Morisonova i Soboljeova analiza neizvesnosti i osetljivosti nam sa druge strane govore o mogućim izlazima sistema i interakcijama između ulaznih parametara. Analiza objašnjivosti modela ide korak dalje. Za svako obeležje koje se koristi u prediktivnom modelu, kroz aproksimaciju zasnovanu na uzorkovanju , možemo da procenimo pozitivan ili negativan uticaj na izlaznu promenljivu, što nam omogućava da domensko istraživanje usmerimo tamo gde je najefikasnije. Ovi i drugi modeli nam omogućavaju da odredimo uticaj različitih parametara zemljišta i vremena na prinos useva i da utvrdimo koji hibridi kukuruza su otporni na sušu, a koje sorte soje imaju stabilan prinos.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1471 " src="https://api.biosens.rs/wp-content/uploads/2021/06/38-1024x768.jpg" alt="" width="351" height="263" /><img class="alignnone wp-image-1473 " src="https://api.biosens.rs/wp-content/uploads/2021/06/39-1024x768.jpg" alt="" width="351" height="263" />

Otkrivanje znanja

Značajan deo BioSensovih istraživanja u oblasti Velikih Podataka je fokusiran na dva tipa podataka koji zahtevaju velik memorijski kapacitet za skladištenje i ekstremno efikasne algoritme za obradu podataka koji mogu da se izvrše u zahtevanom vremenskom roku.

&nbsp;

Prvi od njih su satelitske slike. Sentinel 2 sateliti isporučuju nove slike u 13 pojasa za bilo koju tačku na Zemlji, približno svakih 5 dana. Ove slike dolaze u isečcima dimenzija 100x100 km2, sa prostornom rezolucijom od 10m. U okviru Cybele Projekta, na primer, analiziramo satelitske slike cele Evrope da bismo klasifikovali polja soje, što znači da treba da prođemo kroz stotine isečaka i primenimo nad njima algoritam za klasifikaciju. U takvim situacijama, radimo paralelizaciju koda radi bolje i efikasnije eksploatacije multicore server arhitekture, ubrzavajući procese korišćenjem biblioteke Cython, dok u isto vreme prilagođavamo implementaciju da umanjimo računarsku kompleksnost algoritama.

&nbsp;

Drugi tip podataka su liste poziva korisnika mobilne telefonije i oni zadovoljavaju sve “V”-ove analitike velikih podataka. Ovi podaci se sastoje iz liste uspostavljenih poziva, razmenjenih poruka i registrovanog internet saobraćaja i ogromne su veličine. Važno pitanje u obradi je vezano za privatnost i izdvajanje korisnih informacija iz anonimizovanih i agregiranih skupova podataka predstavlja veliki izazov. Takođe, iako su podaci semi-struktuirani, tradicionalna RDBMS tehnologija za analitiku podataka nije primenljiva na skupove ove veličine. U tu svrhu razvijamo tokove rada za obradu korišćenjem Apache porodice tehnologija - Spark, Hadoop i Hive. One nam daju mogućnost da dobijemo dodatni uvid u ljudsko ponašanje, šablone kretanja i saznamo više o interakciji između ruralnih i urbanih oblasti.

&nbsp;

<img class="alignnone wp-image-1465 size-large" src="https://api.biosens.rs/wp-content/uploads/2021/06/35-1024x578.jpg" alt="" width="1024" height="578" />

Analitika Velikih Podataka

Duboko učenje je novi metod mašinskog učenja. Zbog svoje specifičnosti i odličnih performansi u obradi slike često se posmatra kao zasebna oblast u okviru veštačke inteligencije. Najbolje radi na velikim skupovima podataka koji imaju multi-dimenzionalne karakteristike, sa kakvim se često susrećemo na BioSensu.

&nbsp;

U prvu grupu podataka koje posedujemo spadaju hiperspektralne, multispektralne i termalne slike, napravljene u laboratoriji ili na terenu. Cilj njihove obrade je segmentacija slike i prepoznavanje karakterističnih obrazaca, kao što su počeci truljenja i fizička oštećenja na jabukama, infekcija peteljke paradajza ili detektovanje klasova pšenice. Brojne arhitekture su testirane sa različitim parametrima, poput broja konvolucionih i potpuno povezanih slojeva, vrsta aktivacionih funkcija i slučajne eliminacije dela mreže da bi se izbeglo preučenje. Svaka arhitektura je optimizovana za specifičan problem, uzimajući u obzir veličinu slika i broj uzoraka u bazi podataka.

&nbsp;

<img class="alignnone wp-image-1469 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/337.jpg" alt="" width="640" height="480" />

&nbsp;

Druga grupa skupa podataka se sastoji od merenja čestica u vazduhu pomoću uređaja Rapid-E, prvog automatskog detektora čestica zasnovanog na tzv. LIF (eng. laser-induced ﬂuorescence) tehnologiji. LIF tehnologija beleži raspršene fluroscentne obrasce svetlosti i lasera, koji predstavljaju oblik i hemijski otisak čestica. U ovom slučaju se koristi jedan od primera dubokih neuronskih mreža (DNN) koje se najviše oslanjaju na konvolucione slojeve, zbog njihove sposobnosti da obrade skupove podataka koji potiču iz različitih izvora.

&nbsp;

U oba slučaja, predobrada je jedan od najvažnijih koraka, jer su zašumljeni i nestandardni uzorci veoma teški za analizu. Takođe, važno je istaći da svaki problem zahteva drugačije, prilagođeno rešenje, čija složenost odgovara veličini i složenosti skupova podataka i čija tačnost mora opravdati vreme učenja i izvršavanja algoritma.

&nbsp;

Duboko učenje

Cilj BioSensove Grupe za veštačku inteligenciju je da obezbedi sveobuhvatan i precizan uvid u stanje biosistema, poveća efikasnost fenotipizacije i oplemenjivanja biljaka, ponudi bolje razumevanje molekularne biologije i pomogne poljoprivrednicima kroz optimalno i automatsko donešenje odluka. Naše istraživanje počinje od problema i zahteva inovativnu primenu i razvoj algoritama koji su poslednja reč nauke. Algoritmi mašinskog učenja koji se najčešće koriste za probleme kojima se BioSens bavi su stabla odluke, vektori nosači, ridž regresija, spektralno klasterovanje i mnogi drugi, uključujući i posebnu porodicu algoritama mašinskog učenja – duboko učenje, a tamo gde složenost problema prevazilazi postojeće algoritme, istraživači sa Instituta razvijaju nove.

&nbsp;

Primer algoritma koji je razvijen na BioSens Institutu je algoritam regresije težinskim histogramima. Dati algoritam je zasnovan na mehanizmu glasanja, gde uzorci za obuku glasaju za izlaznu vrednost test uzorka. Svaki glas dobija određenu težinu u zavisnosti od sličnosti uzorka koji glasa i uzorka iz test skupa. Pomoću dobijenih glasova, formira se histogram koji de fakto predstavlja funkciju gustine verovatnoće (PDF) izlaza test uzorka, dok matematičko očekivanje PDF-a predstavlja predikovanu vrednost datog uzorka. Ovaj algoritam se pokazao veoma korisnim za problem predikcije prinosa, gde je nadmašio algoritme stabla odluke, vektora nosača i veštačkih neuronskih mreža.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1478 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/42.png" alt="" width="503" height="504" />

&nbsp;

&nbsp;

Još jedan inovativni algoritam koji je razvijen na Institutu BioSens je algoritam integrisane klasterizacije zasnovan na nenegativnoj faktorizaciji matrica. Kombinovanjem individualnih rezultata klasterovanja u ansambl, dokazi se akumuliraju u cilju poboljšanja rezultata klasterizacije.

Individualni rezultati klasteriziacije spojeni su u zajedničku matricu koja se zatim faktorizuje u matrice kodovanja i bazne vektore. Algoritam ima mogućnost da integriše klastere koji potiču iz različitih baza podataka, različitih nivoa predprocesiranja ili poseduju različite podskupove obeležja.
Ovaj algoritam se pokazao kao izuzetno koristan za funkcionalnu genomiku. Dati pristup, zanosvan na nenegativnoj faktorizaciji matrica poseduje mogućnost fuzije različitih izvora podataka i rezultuje klasterima gena sa povećanom funkcionalnošću i pokrivenošću gena.

&nbsp;

&nbsp;

<img class="alignnone wp-image-1480 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/06/43.png" alt="" width="1691" height="692" />

Mašinsko učenje

BioSens ima odličnu saradnju sa Ministarstvom poljoprivrede Republike Srbije i Pokrajinskim sekretarijatom za poljoprivredu, vodoprivredu i šumarstvo Vojvodine. Za njih smo razvili brojna rešenja koja pomažu javnoj upravi da stekne bolji uvid u poljoprivrednu proizvodnju, postigne efikasniju kontrolu subvencija i otkrije neodgovorno korišćenje poljoprivrednog zemljišta.

&nbsp;

Naša rešenja se uglavnom baziraju na daljinskom istraživanju i GIS-u i uključuju velike baze podataka o poljima, poljoprivrednicima i prikupljenim podacima. Usluge poput mapiranja useva u regionu od interesa razvijaju se pomoću satelitskih snimaka Sentinel 2 i imaju rezoluciju od 10m. Mapiranje useva ima različite svrhe, od verifikacije subvencija do identifikovanja paljenja polja ili ilegalnog zauzimanja državnog poljoprivrednog zemljišta.

&nbsp;

Subvencije se daju za uzgoj određenih useva, izgradnju staklenika ili instaliranje sistema za navodnjavanje. One su brojne, a za inspekciju i proveru pravilnog korišćenja svake ponaosob, potrebni su veliki timovi državnih službenika. Takođe, provera celog polja koje može biti veliko desetine ili stotine hektara zahteva mnogo vremena. Zahvaljujući sistemu koji smo razvili, verifikacije se vrše na daljinu, uz satelitsku obradu slika zajedno sa naprednim algoritmima mašinskog učenja.

&nbsp;

Slična tehnologija se koristi za otkrivanje ilegalnih aktivnosti. Tradicionalno, poljoprivrednici su često spaljivali ostatke useva na svojim poljima kako bi uštedeli vreme i gorivo potrebno za oranje. Ova praksa se ne primenjuje proteklih decenija i proglašena je ilegalnom, jer predstavlja opasnost za ljude i životnu sredinu. Takođe, bilo je slučajeva zauzimanja poljoprivrednog zemljišta u državnom vlasništvu bez nadmetanja i plaćanja zakupnine. Ovi i drugi prekršaji otkriveni su satelitskom tehnologijom i njihov obim je smanjen, čime se osigurava sigurnija i ekološki prihvatljivija poljoprivreda, kao i veći prihodi vlade.

&nbsp;

Ostale usluge uključuju sisteme postavljene za razne druge javne aktere, a posebno za savetodavne usluge. Savetodavne usluge pružaju savetodavnu podršku poljoprivrednicima i prikupljaju velike količine podataka na terenu. Postavljena je namenska platforma zasnovana na AgroSense-u gde se svi podaci čuvaju i vizualizuju pomoću GIS mehanizma. Na taj način su hiljade novih zapisa, kao i istorijska baza podataka posmatranja na terenu digitalizovane i prikupljene pod jednim krovom.

&nbsp;

<img class="alignnone wp-image-1871 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/07/xyz.png" alt="" width="680" height="283" />

<img class="alignnone wp-image-1872 size-full" src="https://api.biosens.rs/wp-content/uploads/2021/07/xy.png" alt="" width="844" height="346" />

Saradnja sa Državnom upravom

Mašinsko učenje i domenska ekspertiza se često posmatraju kao dva rivalska pristupa u rešavanju problema u raznim oblastima, uključujući poljoprivredu. Međutim, naša strategija je da se koristi najbolje iz oba pristupa. Algoritmi mašinskog učenja daju odlične rezultate pri otkrivanju zavisnosti među podacima, ali uveliko postoje i dobro poznate teorije koje objašnjavaju prirodne procese i koje su već dokazane u praksi. Mi u potpunosti iskorištavamo ovu činjenicu ugrađujući domensko znanje u naše modele. To se obično radi tokom procesa izbora i inženjeringa obeležja. Dobro osmišljena obeležja uvode novi nivo informacija u sistem i usmeravaju algoritme mašinskog učenja ka optimalnim konfiguracijama.

&nbsp;

Jedan primer inženjeringa obeležja, zasnovan na domenskoj ekspertizi, je korišćen pri izboru hibrida kukuruza otpornih na stres u Syngenta izazovu za useve u 2019. godini. Suša je pojava povezana sa dužim periodom vremena bez padavina, praćenog visokim temperaturama i niskom vlažnošću vazduha. Međutim, ne postoji stroga matematička definicija suše i u praksi se koriste razni pokazatelji. Na osnovu dnevnih vrednosti maksimalne i minimalne temperature vazduha, količine padavina i pritiska vodene pare u nekoliko faza tokom vegetacione sezone, dizajnirali smo obeležja koja ukazuju na pojavu suše ili toplotnog stresa na određenoj lokaciji. Među njima su bili maksimalan broj uzastopnih suvih dana, mala količina padavina u određenoj fazi razvoja i deficit vodene pare. U ovom problemu su nam dizajnirana obeležja pomogla da pronađemo hibride otporne na sušu koje treba posejati kako bi se maksimizovao prinos i minimizovao rizik loše žetve, ali se ovaj pristup može primeniti i na druge probleme. Ostali primeri sadrže dizajn meteoroloških obeležja za predikciju koncentracije polena u vazduhu, dizajn elevacionih obeležja za bolju predikciju slivanja nutrijenata na njivama i dizajn obeležja koja opisuju kretanje životinja u predikciji bolesti i inflamacije mlečnih žlezda.

&nbsp;

<img class="alignnone wp-image-1471 size-large" src="https://api.biosens.rs/wp-content/uploads/2021/06/38-1024x768.jpg" alt="" width="1024" height="768" />

<img class="alignnone wp-image-1473 size-large" src="https://api.biosens.rs/wp-content/uploads/2021/06/39-1024x768.jpg" alt="" width="1024" height="768" />

Dizajn obeležja

Jedna od oblasti koje prolaze kroz najdinamičnije promene na krilima Četvrte industrijske revolucije je poljoprivreda. Danas, više nego ikad, na proizvođačima je imperativ da povećaju prinose, smanje troškove i uzgajaju kvalitetnije proizvode. Ovo nije nimalo lak zadatak i zahteva posvećenost, trud i ulaganje, a jedini način da uspeju je da odluke koje donose učine maksimalno efikasnim i pravovremenim. U eri satelita, interneta i moćnih računara konačno imamo priliku da odluke donosimo na osnovu činjenica, a ključ uspeha leži upravo u podacima.

&nbsp;

Senzori, monitori prinosa, dronovi i sonde za uzorkovanje zemljišta se sve češće mogu videti na našim njivama, a svi oni su samo različite platforme za dobijanje podataka. Njihovom upotrebom dolazimo do informacija o tipu zemljišta, elevaciji terena, prinosima i rastu useva i na optimalan način biramo sorte i hibride za određenu njivu, određujemo vreme setve, količinu i tip đubriva, kao i pravi trenutak za navodnjavanje. Na ovaj način obezbeđujemo sve potrebne uslove za dobar rast biljaka i sprečavamo prekomerno korišćenje agrohemije. Ipak, ogroman problem sa podacima je taj što su sve do sada oni bili veoma teško dostupni poljoprivrednicima. Nalazili su se na različitim stranama, u različitim formatima, a neki čak nisu bili dostupni u digitalnom obliku. Danas su ovi problemi prošlost. AgroSens, elekronska platforma Digitalne poljoprivrede Srbije, svim domaćim poljoprivrednicima stavlja na raspolaganje satelitske, meteorološke i druge podatke i pruža mogućnost da elektronski, profesionalno i efikasno vode svoje gazdinstvo – i to potpuno besplatno.

&nbsp;

AgroSens je platforma razvijena sa ciljem da poljoprivredniku omogući brz i jednostavan pristup podacima, ali i da vrhunske naučne rezultate koje je Institut BioSens postigao u domenu veštačke inteligencije, obrade satelitskih slika i razvoja senzorskih mreža, pruži zajednici na korišćenje. Od lansiranja AgroSensa u oktobru 2017. godine, pa do danas, stekli smo više od 10.000 zadovoljnih korisnika, što je samo potvrda da su naši poljoprivrednici prepoznali značaj digitalne transformacije u svojoj delatnosti. Platforma se sastoji iz mnoštva modula, a njihov broj se iz meseca u mesec povećava u skladu sa novim potrebama koje se javljaju u proizvodnji. Platforma je dostupna na adresi <a href="https://www.agrosens.rs/#/app-h/welcome">www.agrosens.rs</a>.

&nbsp;

&nbsp;

Korišćenje servisa

&nbsp;

Svi zainteresovani za korišćenje AgroSensa se mogu potpuno besplatno registrovati na adresi <a href="https://www.agrosens.rs/#/app-h/welcome">www.agrosens.rs</a>, za šta im je potrebna isključivo imejl adresa. Prvi korak nakon registracije je svakako kreiranje proizvodne parcele. Ovo je moguće uraditi preko katastra, ukoliko korisnik poseduje podatke o katastarskoj opštini i broju parcele, a kako proizvodna parcela često obuhvata više katastarskih, moguće je obeležiti i susedne katastarske parcele, čime se one udružuju u jednu proizvodnu. Sa druge strane, čest je i slučaj deljenja jedne katastarske u više proizvodnih parcela, zbog čega je korisniku ostavljena mogućnost da korišćenjem jednostavnog alata iscrta parcelu na mapi. Korisnik može imati neograničen broj proizvodnih parcela na svom profilu, a istog trenutka, nakon kreiranja svake od njih, postaju mu dostupni mnogobrojni moduli koji se nalaze na platformi. Ovi moduli su detaljnije opisani u poglavljima koje slede.

&nbsp;

&nbsp;

Meteorološki podaci

&nbsp;

Meteorološki podaci spadaju u kategoriju ključnih pokazatelja stanja na njivi i na osnovu njih se planiraju brojne aktivnosti. Temperatura tla je presudan parametar kod sejanja, prognoza padavina definiše optimalan trenutak primene veštačkog đubriva i pesticida, a sunčevo zračenje i temperatura vazduha utiču na stepen razvoja biljaka. AgroSens sadrži dva modula koja se bave meteorologijom. Prvi se tiče istorijskih meteo podataka. Podaci sa mernih stanica Republičkog hidrometeorološkog zavoda se pohranjuju u sistem, a korisnik ima mogućnost da izabere do 3 meteo stanice od interesa. Platforma mu pruža mogućnost da posmatra meteorološke parametre tla i vazduha u prethodnih 7 dana i na taj način dođe do zaključka o trenutnom stanju na njivi. Drugi modul se tiče vremenske prognoze. Prema dugogodišnjem iskustvu stručnjaka sa Instituta BioSens, najtačniju vremensku prognozu isporučuje norveški meteorološki institut i to na rezoluciji od 2 km. Ovako visoka rezolucija nam omogućava da korisniku damo na uvid vremensku prognozu izuzetne tačnosti i to za lokaciju na kojoj se njegova njiva nalazi.

&nbsp;

&nbsp;

Sateliti

&nbsp;

Zahvaljujući istraživačkim uspesima BioSensa i aktivnosti Instituta u evropskim naučnim projektima, Srbija je postala jedina država van Evropske Unije koja ima slobodan širokopojasni pristup snimcima sa Sentinel satelita Evropske svemirske agencije, a AgroSens u potpunosti koristi ovu mogućnost. Sentinel sateliti snimaju useve svakih pet dana na rezoluciji od 10 m i omogućuju korisniku da posmatra svoje njive iz sasvim nove perspektive. Kao što ljudsko oko razlikuje 3 komponente svetlosti (crvenu, zelenu i plavu), Sentineli razlikuju čak 13 komponenti. To znači da vide i ono što mi ne vidimo, a ponekad su upravo infracrveni i termalni delovi spektra ti koji nam najviše govore o „zdravstvenom stanju“ biljaka. Obradom 13 spektralnih kanala se dalje izračunavaju vegetacioni indeksi koji nam ukazuju na rast biljaka, intenzitet suše, rasprostranjenost biljnih bolesti i potrebu biljaka za navodnjavanjem i đubrenjem. Na ovaj način proizvođači mogu da vide koji delovi njive im rastu bolje, a koji lošije i da pravilno rasporede đubrivo u skladu sa stvarnim potrebama useva u različitim delovima parcele.

&nbsp;

&nbsp;

Digitalna knjiga polja

&nbsp;

Svaka ozbiljna proizvodnja treba da bude propraćena ozbiljnom dokumentacijom. U poljoprivredi je praksa da se vode knjige polja, a kako se Srbija približava Evropskoj Uniji, to će uskoro biti i obaveza poljoprivrednika. Sa stanovišta obrade podataka, knjige polja u papirnom obliku su jedna velika propuštena prilika. Skupovi podataka vezanih za setvu, primenu agrotehničkih mera i prinose su „rudnik zlata“ za BioSens, a oni po pravilu ostaju na policama, upisani u sveske i rokovnike. Sa digitalnim podacima, primenom naprednih metoda veštačke inteligencije, mašinskog učenja i „big dejta“ analitike, u mogućnosti smo da obradimo velike skupove podataka, pronađemo skrivene zavisnosti među njima, damo automatske preporuke poljoprivredniku i učinimo njegove odluke efikasnijim. Stara kineska poslovica kaže: „najbolji trenutak za sađenje drveta bio pre dvadeset godina. Drugi najbolji je sada.“ Trenutno nemamo velike skupove podataka o poljoprivrednoj proizvodnji, ali je vođenje digitalne knjige polja idealna prilika da počnemo da sakupljamo informacije na osnovu kojih će BioSens razviti nove module u službi poljoprivrednika. Digitalna knjiga polja koja se nalazi u okviru AgroSensa pruža mogućnost korisniku da unese informacije o datumu sprovedenih aktivnosti na njivi i specificira detalje vezane za tip obrade zemljišta, primenjeno đubrivo, prinose i cene operacija, a sve ove aktivnosti se mogu dodatno dokumentovati fotografijama upotrebom AgroSens mobilne aplikacije. Osim modula sa aktivnostima postoji i poseban modul za analizu zemljišta koji omogućava praćenje unetih podataka kroz godine, dok modul nazvan „Fotografije“ sadrži fotografije koje je korisnik napravio pametnim telefonom i daje njihovu mapu na osnovu GPS lokacije.

&nbsp;

&nbsp;

Mape parametara

&nbsp;

Osim satelita koji su obuhvaćeni posebnim modulom, postoji još mnogo različitih izvora podataka o parceli, poput mapa prinosa, elevacije, elektroprovodljivosti zemljišta i slika sa bespilotnih letelica. Ove mape su dodatni slojevi informacija koji mogu biti od izuzetne važnosti u planiranju i praćenju rasta i razvoja useva. AgroSens pruža mogućnost da se u sistem uvezu ove mape i da se vrši njihova komparativna analiza. Slika u prilogu je primer kako mape elektroprovodljivosti zemljišta odgovaraju prinosu, a pokazuje i jasan uticaj centar-pivot zalivnog sistema. Sa druge strane, dronovi nam omogućuju da posmatramo useve na rezoluciji od svega nekoliko centimetara i primetimo najfinije promene u njihovom rastu. Dodatne mape parametara nam daju novi uvid u poljoprivrednu proizvodnju, a AgroSens nam pruža priliku da ih jednostavno i adekvatno prikažemo i analiziramo.

&nbsp;

&nbsp;

Senzori i meteo stanice

&nbsp;

Naučni rezultati nam govore da su za 70 % varijabilnosti prinosa odgovorne vremenske prilike. Usled klimatskih promena, ekstremni vremenski događaji poput suša i poplava su postali veoma česti i imaju izrazito lokalan karakter. Mreža Republičkog hidrometeorološkog zavoda pokriva tridesetak geografskih lokacija, ali je ovaj broj daleko od dovoljnog. Često se dešava da se vremenski događaji odigraju između dve meteo stanice i ostanu neregistrovani, što je ozbiljan problem za poljoprivrednike, koji odluke u proizvodnji donose na osnovu vlažnosti zemljišta, temperature ispod i iznad zemlje i drugih parametara. Iz ovog razloga, BioSens će na teritoriji republike Srbije rasporediti čak 500 meteo stanica koje će omogućiti merenje meteoroloških parametra na visokoj prostornoj rezoluciji. Poslednja reč tehnike bežične integracije senzora i meteo stanice su LORA sistemi, a ovakve mreže se još i nazivaju „IoT“-em, odnosno „internetom stvari“. Kao što je mobilna mreža optimizovana za slanje velikih količina podataka, poput slika visoke rezolucije i video klipova, tako je LORA optimizovana za slanje malih količina podataka (očitavanja sa senzora), ali sa velike udaljenosti i sa malom potrošnjom energije. Na ovaj način baterija senzora može da izdrži čitavu sezonu, a slanje podataka je moguće sa njive koja je udaljena i do 30 km od bazne stanice. Na osnovu senzora i meteo stanica, poljoprivrednici kroz AgroSens dobijaju precizan uvid u stanje na terenu i mogu da donesu optimalne odluke u proizvodnji.

&nbsp;

&nbsp;

Presek troškova

&nbsp;

Jedna od direktnih koristi revnosnog vođenja digitalne knjige polja je što se jednim klikom miša dolazi do detaljne analize troškova. Ovaj modul koristi unete informacije o aktivnostima i njihovim cenama i izlistava troškove po parcelama, po vrsti useva ili ukupne troškove za celo gazdinstvo. Analiza troškova je propraćena graficima koji na pregledan način vizualizuju brojke i pomažu korisniku da dobije jasan uvid u finansijski aspekt proizvodnje.

&nbsp;

&nbsp;

Usluge

&nbsp;

Savetodavstvo je jedna od oblasti koja će usled digitalne transformacije poljoprivrede doživeti najveće promene, jer će na osnovu preciznih podataka sa terena savetodavne službe i eksperti biti u prilici da daju tačnije i efektivnije savete za poljoprivrednika. Na osnovu ovog modula savetodavci i poljoprivrednici će moći izuzetno efikasno da se povežu, a nakon sklapanja dogovora, savetodavac će dobiti čitav niz informacija o usevima: od satelitskih slika i mapa parametara, preko fotografija sa terena, pa sve do digitalne knjige polja. Ovako detaljan skup podataka daje mogućnost ekspertu da sagleda problem iz više uglova i odredi optimalne korake u daljem toku proizvodnje, često i bez izlaska na teren. Osim modula za savetodavce i piloti dronova imaju svoj odeljak u okviru Usluga. Poslovanje preko AgroSensa čak eliminiše potrebu za ličnim susretom između pružaoca i primaoca usluga snimanja bespilotnom letelicom. Nakon uspostavljanja kontakta, pilot automatski dobija GPS koordinate i granice parcele, a slike koje načini može elektronskim putem pohraniti na platformu. Na ovaj način se povećava efikasnost i brzina poslovanja i podstiče korišćenje visokih tehnologija u poljoprivredi. Pružaoci usluga imaju priliku da ograniče prostor delovanja na okruge od interesa unutar Republike Srbije, kako bi izbegli poslove koji su neisplativi zbog visokih troškova prevoza. Još jedan kriterijum za odabir pružaoca usluge je i njegova ocena. Naime, postavljen je sistem ocenjivanja pružalaca usluga koji dozvoljava poljoprivredniku da savetodavcu, odnosno pilotu, da ocenu za obavljeni posao. Ovaj sistem favorizuje kvalitetne pružaoce usluga i omogućava im da formiraju cene u skladu sa potražnjom i svojim kvalitetom. Osim savetodavaca i pilota dronova u planu je izrada novih odeljaka za laboratorije za analizu zemljišta, kompanije za skeniranje elektroprovodljivosti terena i druge delatnosti. Ovako postavljena mreža okuplja različite aktere u poljoprivrednoj proizvodnji i integriše ih pod jednim krovom – platformom AgroSens.

&nbsp;

&nbsp;

Alarmi za biljne bolesti i štetočine

&nbsp;

Biljne bolesti i štetočine u okolini parcele su velika pretnja za proizvodnju i stoga se na informacije o njihovoj pojavi mora reagovati hitno i bez oklevanja. Ovaj modul preuzima vesti koje izdaje Prognozno-izveštajna služba i stavlja ih na raspolaganje poljoprivredniku. Vesti se filtriraju, a korisniku se prikazuju informacije o pojavi isključivo onih bolesti koje pogađaju useve koje je on sejao. Ovim putem se poljoprivrednik alarmira i upozorava da treba da deluje u skladu sa preporučenim procedurama.

&nbsp;

&nbsp;

Alati

&nbsp;

Tokom pripreme za svaku operaciju na njivi, poljoprivrednici moraju da sračunaju potrebne količine repromaterijala i kalibrišu prskalice i rasipače. Ovaj modul im omogućava da to urade precizno i brzo.

&nbsp;

&nbsp;

Tehnologije

&nbsp;

BioSens sebe vidi kao lidera u digitalnoj transformaciji poljoprivrede Srbije. AgroSens sadrži velik broj praktičnih funkcionalnosti, ali ni edukacija poljoprivrednika nije ništa manje bitna. Modul pod nazivom „Tehnologiju“ ima ulogu da poljoprivrednika uputi u najnovije trendove koji su prisutni u proizvodnji. U okviru njega se prikazuju članci o najsavremenijim rasipačima đubriva, traktorima, sistemima za navodnjavanje i drugim proizvodima koji su upravo dospeli na tržište i predstavljaju poslednju reč tehnike.

&nbsp;

AgroSense APV

Themes:

People:

Centers:

CST

CIT

CRP