Digitalization of crop yield forecasting methods

   The article describes the development and application of agricultural crop yield forecasting methods in the Irkutsk region based on digital analysis. The study involved the representatives from three organizations, demonstrating successful integration of research and innovation work of the scientists. The use of complex statistical analysis and data visualization allows not only carrying out calculations, but also visually presenting the results in the form of graphs, making it possible to assess the accuracy of forecasts through the indicators of their justifiability, absolute and relative error. When creating the
calculation models, a multi-year series of potato yields for all categories of farms and agricultural enterprises in the Irkutsk region (the data provided by the Irkutskstat, the state statistics authority for the Irkutsk region) was used. The proposed desktop application is developed using the C# programming language, has a modular structure and includes three main components: data interaction module, data presentation module, and modeling module. The program integrates both traditional physical-statistical models based on ground meteorological station network data and experimental models using the Leaf Area Index (LAI) obtained through remote sensing methods. The developed models demonstrate high forecasting accuracy with determination coefficients ranging from 0.59 to 0.85. The software product has successfully passed testing and has been implemented in the practical activities of the Irkutsk Department of Hydrometeorology and Environmental Monitoring according to the decision of the Central Methodological Commission on Hydrometeorological and Heliogeophysical Forecasts. Special attention is paid to the system's development prospects, including functionality expansion through the implementation of machine learning methods and development of the models for other agricultural crops.

   The practical significance of the development lies in the ability to obtain operational yield forecasts, which contributes to making informed decisions in agricultural production planning and ensuring regional food security.

1. Cesco S., Sambo P., Borin M., Basso B., Orzes G., Mazzetto F. Smart agriculture and digital twins: Applications and challenges in a vision of sustainability. European Journal of Agronomy, 2023, vol. 146, р. 126809. DOI: 10.3390/agronomy13081964.

2. Becker-Reshef I., Justice C., Barker B., Humber M., Rembold F., Bonifacio R., Zappacosta M., Budde M., Magadzire T., Shitote C., Pound J., Constantino A., Nakalembe C., Mwangi K., Sobue S., Newby T., Whitcraft A., Jarvis I., Verdin J. Strengthening agricultural decisions in countries at risk of food insecurity: the GEOGLAM crop monitor for early warning Remote Sens. Environ, 2020, vol. 237, p. 111553. DOI: 10.1016/j.rse.2019.111553.

3. Liu K., Harrison M.T., Yan H., Liu D.L., Meinke H., Hoogenboom G., Wang B., Peng B., Guan K., Jaegermeyr J., Wang E., Zhang F., Yin X., Archontoulis S., Nie L., Badea A., Man J., Wallach D., Zhao J., Benjumea A.B., Fahad S., Tian X., Wang W., Tao F., Zhang Z., Rötter R., Yuan Y., Zhu M., Dai P., Nie J., Yang Y., Zhang Y. Silver lining to a climate crisis in multiple prospects for alleviating crop waterlogging under future climates. Nature Communications, 2023, vol. 14, no. 1, р. 765. DOI: 10.1038/s41467-023-36129-4.

4. Archontoulis S.V., Castellano M.J., Licht M.A., Nichols V., Baum M., Huber I., Martinez-Feria R., Puntel L., Ordóñez R.A., Iqbal J., Wright E.E., Dietzel R.N., Helmers M., Vanloocke A., Liebman M., Hatfield J.L., Herzmann D., Córdova S.C., Edmonds P., Togliatti K., Kessler A., Danalatos G., Pasley H., Pederson C., Kendall R., Lamkey K.R. Predicting crop yields and soil plant nitrogen dynamics in the US Corn Belt. Crop Science, 2020, vol. 60, no. 2, pр. 721–738. DOI: 10.1002/csc2.20039.

5. Ji Z., Pan Y., Zhu X., Wang J., Li Q. Prediction of crop yield using phenological information extracted from remote sensing vegetation index. Sensors, 2021, vol. 21, no. 4, р. 1406. DOI: 10.3390/s21041406.

6. Wolanin A., Mateo-Garciá G., Camps-Valls G., Gómez-Chova L., Meroni M., Duveiller G., Liangzhi Y., Guanter L. Estimating and understanding crop yields with explainable deep learning in the Indian Wheat Belt. Environmental research letters, 2020, vol. 15, no. 2, р. 024019. DOI: 10.1088/1748-9326/ab68ac.

7. Seffrin R., Araújo E.C., Bazzi C.L. Regression models for prediction of corn yield in the state of Paraná (Brazil) from 2012 to 2014. Acta Scientiarum. Agronomy, 2018, vol. 40, p. e36494. DOI: 10.4025/actasciagron.v40i1.36494.

8. Mathieu J.A., Aires F. Assessment of the agro-climatic indices to improve crop yield forecasting. Agricultural and Forest Meteorology, 2018, vol. 253, рр. 15–30. DOI: 10.1016/j.agrformet.2018.01.031.

9. Holzman M.E., Carmona F., Rivas R., Niclos R. Early assessment of crop yield from remotely sensed water stress and solar radiation data. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, vol. 145, pр. 297–308. DOI: 10.1016/j.isprsjprs.2018.03.014.

10. Adisa O., Botai J., Adeola A., Hassen A., Botai C., Darkey D., Tesfamariam E. Application of Artificial Neural Network for Predicting Maize Production in South Africa. Sustainability, 2019, vol. 11, p. 1145. DOI: 10.3390/su11041145.

11. Abbas F., Afzaal H., Farooque A.A., Tang S. Crop Yield Prediction through Proximal Sensing and Machine Learning Algorithms. Agronomy, 2020, vol. 10, p. 1046. DOI: 10.3390/agronomy10071046.

12. Gómez D., Salvador P., Sanz J., Luis J. Casanova Potato yield prediction using machine learning techniques and sentinel 2 data. Remote Sensing, 2019, vol. 11, no. 15, р. 1745. DOI: 10.3390/rs11151745.

13. Pishimko O.I., Garafutdinova L.V. Forecasting potato yield. Vestnik Buryatskoy gosudarstvennoy sel’skokhozyaistvennoy akademii im. V.R. Filippovа = Vestnik of Buryat State Academy of Agriculture named after V.R. Philippov, 2022, no. 4 (69), рр. 15–22. (In Russian). DOI: 10.34655/bgsha.2022.69.4.002.