Crop yield modeling at the regional level is one of the most important methods to ensure the profitability of the agro-industrial economy and the solving of the food security problem. Due to a lack of information about crop distribution over large agricultural areas, as well as the crop separation problem (based on remote sensing data) caused by the similarity of phenological cycles, a question arises regarding the relevance of using data obtained from the arable land mask of the region to predict the yield of individual crops. This study aimed to develop a regression model for soybean crop yield monitoring in municipalities and was conducted in the Khabarovsk Territory, located in the Russian Far East. Moderate Resolution Imaging Spectroradiometer (MODIS) data, an arable land mask, the meteorological characteristics obtained using the VEGA-Science web service, and crop yield data for 2010–2019 were used. The structure of crop distribution in the Khabarovsk District was reproduced in experimental fields, and Normalized Difference Vegetation Index (NDVI) seasonal variation approximating functions were constructed (both for total district sown area and different crops). It was found that the approximating function graph for the experimental fields corresponds to a similar graph for arable land. The maximum NDVI forecast error on the 30th week in 2019 using the approximation parameters according to 2014–2018 did not exceed 0.5%. The root-mean-square error (RMSE) was 0.054. The maximum value of the NDVI, as well as the indicators characterizing the temperature regime, soil moisture, and photosynthetically active radiation in the region during the period from the 1st to the 30th calendar weeks of the year, were previously considered as parameters of the regression model for predicting soybean yield. As a result of the experiments, the NDVI and the duration of the growing season were included in the regression model as independent variables. According to 2010–2018, the mean absolute percentage error (MAPE) of the regression model was 6.2%, and the soybean yield prediction absolute percentage error (APE) for 2019 was 6.3%, while RMSE was 0.13 t/ha. This approach was evaluated with a leave-one-year-out cross-validation procedure. When the calculated maximum NDVI value was used in the regression equation for early forecasting, MAPE in the 28th–30th weeks was less than 10%.

No abstract

The paper presents an assessment of the model for predicting soybean yield at the level of municipalities in the Far East for the Oktyabrskiy and Leninskiy districts of the Jewish Autonomous Region, as well as the Khabarovsk and Vyazemskiy districts of Khabarovsk Territory. The share of soybean in the total arable land structure of these municipalities in 2018 ranged from 58% to 97%. According to 2010–2018 data, regression models were constructed for each region. The model used statistical data on district soybean yield, as well as data from remote sensing of the Earth. The values of the maximum NDVI (Normalized Difference Vegetation Index) of arable land and the growing duration at the week that reached maximum NDVI were used as independent variables in the regression model. We used weekly NDVI composites obtained for delineated arable lands through the Vega-Science system. According to long-term observations, it was found that in the study area the maximum NDVI was reached in weeks 30–33 (end of July to mid-August). The RMSE for different regions ranged from 0.06 to 0.15 t/ha, and the MAPE did not exceed 10%. The developed model can be used for predicting soybean yield and planning export operations by farms and territorial authorities.