Data Driven Explanation of Temporal and Spatial Variability of Maize Yield in the United States

Maize yield has demonstrated significant variability both temporally and spatially. Numerous models have been presented to explain such variability in crop yield using data from multiple sources with varying temporal and spatial resolutions. Some of these models are data driven, which focus on approximating the complex relationship between explanatory variables and crop yield from massive data sets. Others are knowledge driven, which focus on integrating scientific understanding of crop growth mechanism in the modeling structure. We propose a new model that leverages the computational efficiency and prediction accuracy of data driven models and incorporates agronomic insights from knowledge driven models. Referred to as the GEM model, this model estimates three independent components of (G)enetics, (E)nvironment, and (M)anagement, the product of which is used as the predicted crop yield. The aim of this study is to produce not only accurate crop yield predictions but also insightful explanations of temporal and spatial variability with respect to weather, soil, and management variables. Computational experiments were conducted on a data set that includes maize yield, weather, soil, and management data covering 2,649 counties in the U.S. from 1980 to 2019. Results suggested that the GEM model is able to achieve a comparable prediction performance with state-of-the-art machine learning models and produce meaningful insights such as the estimated growth potential, effectiveness of management practices, and genetic progress.