Sunflower crop yield prediction by advanced statistical modeling using satellite-derived vegetation indices and crop phenology

Timely crop yield information is needed for agricultural land management and food security. We investigated using remote sensing data from the Earth observation mission Sentinel-2 to monitor the crop phenology and predict the crop yield of sunflowers at the field scale. Ten sunflower fields in Mezohegyes, southeastern Hungary, were monitored in 2021, and the crop yield was measured by a combine harvester. Images from Sentinel-2 were collected throughout the monitoring period, and vegetation indices (VIs) were extracted to monitor the crop growth. Multiple linear regression and two different machine learning approaches were applied to predicting the crop yield, and the best-performing one was selected for further analysis. The results were as follows. The VIs showed the highest correlation with the crop yield (R > 0.6) during the inflorescence emergence stage. The most suitable time for predicting the crop yield was 86-116 days after sowing. Random forest regression (RFR) was the best machine learning approach for predicting field-scale variability of the crop yield (R-2 similar to 0.6 and RMSE 0.284-0.473 t/ha). Our results can be used to develop a timely and robust prediction method for sunflower crop yields at the field scale to support decision-making by policymakers regarding food security.

Automated summary

In order to manage agricultural land and ensure food security, timely crop yield information is essential. This study explored the use of remote sensing data from Sentinel-2 to monitor sunflower crop phenology and predict crop yield at the field scale. Ten sunflower fields in Mezohegyes, southeastern Hungary, were studied in 2021, and Sentinel-2 images were collected throughout the monitoring period. Vegetation indices (VIs) were extracted to monitor crop growth. Multiple linear regression and two different machine learning approaches were used to predict crop yield, with random forest regression (RFR) showing the best performance. The study provides valuable insights for developing a robust and timely prediction method for sunflower crop yields to support decision-making regarding food security.