2022, issue 1, p. 19-27
Received 13.01.2022; Revised 03.02.2022; Accepted 28.06.2022
Published 30.06.2022; First Online 03.08.2022
https://doi.org/10.34229/2707-451X.22.1.3
Application of Artificial Neural Network Technology for Prediction of Sunflower Harvest Losses
Oleksandr Zozulya 1, Volodymyr
Domrachev 2 
, Violeta Tretynyk 3
*
1 «Syngenta» LLC
2 Taras Shevchenko National University of Kyiv
3 The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"
* Correspondence: This email address is being protected from spambots. You need JavaScript enabled to view it.
Introduction The current stage of economic development is characterized by digitalization. Digital technologies in crop production occupy leading positions in agrocybernetics.
The digitalization of society has brought to the fore new methods of studying development processes, among which a significant role is played by deep learning and its most successful methods such as artificial neural networks.
“Artificial neural networks (ANNs) have gained popularity an effective tool for offering solutions to a wide variety of different case studies of biological and agricultural background. Their effectiveness emanates from their ability to model complex relationships between observation data from sensors and predicted variables without relying on assumptions about the model structure hence they can predict the real nature of the nonlinear relation between input and output data.” Yield prediction is a major challenge in precision agriculture, closely associated to the adoption of best management practices, crop pricing and security. Various techniques and methodologies have been developed to predict crop yield in agriculture.
Yield forecasting requires control of many parameters, including Moisture Content pH, Soil Organic Matter, Total Nitrogen and Organic Carbon, which complicates the forecasting process .
The purpose of the paper. The purpose of this paper is to find out and substantiate the possibility of predicting the probable loss of the sunflower crop by the farmer based on the analysis of the distribution of the vegetation index in the field. Our hypothesis is that the distribution of the vegetation index significantly affects the percentage of losses, of course, with additional parameters.
Results. The influence of parameters that characterize the harvest on its losses is, but a clear regression relationship can not be built. Therefore, the technology of artificial neural networks is used to build the model. The model is formed in the form of an algorithm at the input of which input parameters are given (value of vegetation index at the beginning of the study, change of index value during the study period, seed moisture in the accounting area, percentage of study area from field area), at the output we get the percentage of possible crop losses. The algorithm is automatically translated into a program in the C ++ programming language (or another programming language), which allows in practice to model the farmer's possible crop losses depending on his actions in relation to growing crops.
Keywords: sunflower, machine learning, artificial neural networks, forecast model.
Cite as: Zozulya O., Domrachev V., Tretynyk V. Application of Artificial Neural Network Technology for Prediction of Sunflower Harvest Losses. Cybernetics and Computer Technologies. 2022. 1. P. 19–27. https://doi.org/10.34229/2707-451X.22.1.3
References
1. Zozulya O.L., Mykhalska L.M., Kovel O.L., Schwartau V.V. Digital technologies in crop production. Кyiv, 2020. 72 p. (in Ukrainian)
2. Snityuk V.E., Miroshnik O.N. Modeling and forecasting of processes in the real estate market. Cherkasy, 2014. 332 p. (in Russian)
3. Pantazi X., Moshou D., Bochtis D. Intelligent Data Mining and Fusion Systems in Agriculture. Academic Press Elsevier Inc., London, 2020. 319 p. https://doi.org/10.1016/B978-0-12-814391-9.00001-7
4. Haikin S. Neural networks Dialectics, 2020. 1104 p. (in Russian)
5. Tadeusiewicz R., Chaki R., Chaki N. Exploring Neural Networks with C #. New York CRC Press, 2015. 296 р. https://doi.org/10.1201/b17332
6. Sugomori Y., Kaluza B., Soares F.M., Souza A.M.F. Deep Learning: Practical Neural Networks with Java. Packt Publishing, 2017. 721 р.
7. Livshin I. Artificial Neural Networks with Java: Tools for Building Neural Network Applications. APress. 2019. 575 р. https://doi.org/10.1007/978-1-4842-4421-0
8. Virender S. C ++ Neural Networks and Fuzzy Logic. Amazon Digital Services, Inc., 2015. 447 p.
ISSN 2707-451X (Online)
ISSN 2707-4501 (Print)