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.
Grid‐based soil sampling captures within‐field fertility variability, enabling site‐specific lime and fertilizer management but at a high cost. This study grid‐sampled 20 corn ( Zea mays L.) fields in New York to (1) document spatial variability in soil series, pH, soil test phosphorus (P), and potassium (K); (2) assess the impact of grid size (0.2, 0.4, 1.0 ha/grid) on field‐based lime, P, and K recommendations compared to whole‐field sampling for corn with and without alfalfa ( Medicago sativa L.) in the rotation; and (3) derive guidance for soil sampling beyond the initial grid‐based sampling event. Soil pH was measured using a 1:1 soil‐to‐water mixture, while P and K were extracted or converted to Morgan equivalents. Soil pH ranged from 6.2 to 7.4, while P and K varied from 3 to 177 mg P/kg and 22 to 213 mg K/kg, respectively. Grid‐based management led to higher recommended lime rates, especially for fields in alfalfa rotations. For P, grid‐based decision‐making increased the recommended amount of fertilizer for many fields. For K, several fields showed potential fertilizer savings. In most fields requiring lime applications, the amount recommended increased with grid size, whereas for P and K, smaller grid sizes resulted in higher recommendations. Grid‐based soil measurements were converted to soil test‐based management zones, providing both a transition from regular grid sampling in the initial year to more cost‐effective zone‐based sampling in future years, and a means to homogenize the field with targeted lime and fertilizer management.