Evaluation of machine learning models to assess relationships between climate and corn suitability in the U.S.

Given the impact that climate change is projected to have on agriculture, it is essential to understand the mechanisms and conditions that drive agricultural land suitability. The Maximum Entropy model (Maxent) is a correlative machine learning model often used to model cropland suitability. In this study, we used Maxent to model land suitability for corn production in the contiguous United States under current bioclimatic conditions. We evaluated Maxent's predictive ability though three comparisons: (i) classification of suitable land units and comparison of results with another similar species distribution model (Random Forest Classification), (ii) with real-world corn location suitability and yield data, and (iii) existing literature on corn suitability thresholds associated with the Maxent formulation. In this presentation we will review the results of Maxent vs RF, compare the Maxent results with observed crop yield statistics, and discuss broader issues of agriculture-climate relationships.