Exploring the Use of High-Resolution Satellite Images to Estimate Corn Silage Yield Within Field

Corn (Zea mays L.) silage yield monitor data offer crucial insights into spatial and temporal yield variability. However, equipment’s sensor malfunctioning can result in data loss, and yield sensor systems are expensive to purchase and maintain. In this study, we analyzed corn silage yield data from two fields and three years each for two dairy farms (Farm A and B). We aimed to explore the potential of integrating high-resolution satellite data, topography, and climate data with machine learning models to estimate missing yield data for a field or a year. Our objectives were to identify key yield-explaining features and assess the accuracy of different machine learning models in estimating silage yield. Results showed that the features differed among farms with a Two-Band Enhanced Vegetation Index, EVI2 (Farm A), and elevation (Farm B) emerging as the most prominent predictors. Ensemble-based models like XGBoost, Random Forest, and Extra Tree regressors exhibited superior predictive performance. However, XGBoost performed poorly when applied to unseen fields or years, whereas Extra Tree regressor, followed closely by Random Forest, emerged as a more reliable model for predicting missing data. Despite achieving reasonable accuracy, the best performance for estimating data for a missing field (6.46 Mg/ha) and year (5.51 Mg/ha) fell short of the acceptable error threshold of 4.9 Mg/ha currently used in state policy to evaluate if a management change resulted in a yield increase. These findings emphasize the need for higher-resolution data and extended years of yield records to better capture the trends in farm-scale yield applications.