Machine Learning-Based Modeling of Spatio-Temporally Varying Responses of Rainfed Corn Yield to Climate, Soil, and Management in the U.S. Corn Belt

Better understanding the variabilities in crop yield and production is critical to assessing the vulnerability and resilience of food production systems. Both environmental (climatic and edaphic) conditions and management factors affect the variabilities of crop yield. In this study, we conducted a comprehensive data-driven analysis in the U.S. Corn Belt to understand and model how rainfed corn yield is affected by climate variability and extremes, soil properties (soil available water capacity, soil organic matter), and management practices (planting date and fertilizer applications). Exploratory data analyses revealed that corn yield responds non-linearly to temperature, while the negative vapor pressure deficit (VPD) effect on corn yield is monotonic and more prominent. Higher mean yield and inter-annual yield variability are found associated with high soil available water capacity, while lower inter-annual yield variability is associated with high soil organic matter (SOM). We also identified region-dependent relationships between planting date and yield and a strong correlation between planting date and the April weather condition (temperature and rainfall). Next, we built machine learning models using the random forest and LASSO algorithms, respectively, to predict corn yield with all climatic, soil properties, and management factors. The random forest model achieved a high prediction accuracy for annual yield at county level as early as in July (R(2) = 0.781) and outperformed LASSO. The gained insights from this study lead to improved understanding of how corn yield responds to climate variability and projected change in the U.S. Corn Belt and globally.