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

Integrating Remote Sensing and Soil Features for Enhanced Machine Learning-Based Corn Yield Prediction in the Southern US

Efficient and reliable corn (Zea mays L.) yield prediction is important for varietal selection by plant breeders and management decision-making by growers. Unlike prior studies that focus mainly on county-level or controlled laboratory-scale areas, this study targets a production-scale area, better representing real-world agricultural conditions and offering more practical relevance for farmers. Therefore, the objective of our study was to determine the best combination of vegetation indices and abiotic factors for predicting corn yield in a rain-fed, production-scale area, identify the most suitable corn growth stage for yield estimation using machine learning, and identify the most effective machine learning model for corn yield estimation. Our study used high-resolution (6 cm) aerial multispectral imagery. Sixty-two different predictors, including soil properties (sand, silt, and clay percentages), slope, spectral bands (red, green, blue, red-edge, NIR), vegetation indices (GNDRE, NDRE, TGI), color-space indices, and wavelengths were derived from the multispectral data collected at the seven (V4, V5, V6, V7, V9, V12, and V14/VT) growth stages of corn. Four regression and machine learning algorithms were evaluated for yield prediction: linear regression, random forest, extreme gradient boosting, and gradient boosting regressor. A total of 6865 yield values were used for model training and 1716 for validation. Results show that, using random forest method, the V14/VT stage had the best yield predictions (RMSE of 0.52 Mg/ha for a mean yield of 10.19 Mg/ha), and yield estimation at V6 stage was still feasible. We concluded that integrating abiotic factors, such as slope and soil properties, significantly improved model accuracy. Among vegetation indices, TGI, HUE, and GNDRE performed better. Results from this study can help farmers or crop consultants plan ahead for future logistics through enhanced early-season yield predictions and support farm profitability and sustainability.

Developing Functional Relationships between Soil Moisture Content and Corn Early-Season Physiology, Growth, and Development

Drought is a severe threat to agriculture production that affects all growth stages of plants, including corn (Zea mays L.). Any factor affecting early seedling growth and development will significantly impact yield. Despite the recurrence of low rainfall during the growing seasons, corn responses to different early-season soil moisture content levels have not been investigated. In this study, we investigated how corn morpho-physiological and biomass traits responded to varied soil moisture content during the early vegetative stage. Two corn hybrids were grown in a pot-culture facility under five different soil moisture treatments (0.15, 0.12, 0.09, 0.06, and 0.03 m³ m^-3 volumetric water content, VWC) to assess the growth and developmental responses to varied soil moisture content during early-season growth (V2 to V7) stage. Sub-optimal soil moisture content limited plant growth and development by reducing physiological and phenotypic expression. Stomatal conductance and transpiration were decreased by an average of 65% and 59% across stress treatments relative to optimum conditions. On average, soil moisture deficit reduced the total leaf area by 71% and 72% compared to the control in 'A6659VT2RIB' and 'P1316YHR', respectively. Shoot and root dry weights were reduced by 74% and 43% under 0.03 m³ m^-3 VWC. An increase in the root-to-shoot ratio was noticed under low VWC conditions compared to the control. Based on the stress tolerance index, the physiology and leaf growth parameters were more sensitive to soil moisture deficit. Our results highlight the impact of sub-optimal soil moisture on physiology and morphological traits during early-season growth. 'P1316YHR' demonstrated better physiological performance under stress conditions, while 'A6659VT2RIB' produced relatively better root growth. The findings suggest that biomass partitioning between shoot and root components is dynamic and depends on stress intensity. The current findings can help to prioritize traits associated with the early-season drought tolerance in corn. The functional relationships developed between soil moisture content and growth and developmental responses can be integrated into corn crop modeling to allow better irrigation management decisions.

Explainable Machine Learning Approach Quantified the Long-Term (1981–2015) Impact of Climate and Soil Properties on Yields of Major Agricultural Crops Across CONUS

A comprehensive understanding of the long-term data on the crop, soils, environment, climate, and production management would facilitate efficient data-driven decision-making in agriculture production under changing climate. We have employed an explainable machine learning algorithm (random forest model coupled with LIME; Local Interpretable Model-Agnostic Explanations framework) using multi-decadal (1981–2015) data on climate variables, soil properties, and yield of major crops across the Coterminous United States (CONUS). This data-driven approach explained the multi-faceted factors of crop production for corn, soybean, cotton, and wheat under field conditions by leveraging agricultural informatics. We attempted to show how crop yields can better be correlated and explained when production input varies along with changing climatic/environmental and edaphic conditions. Our findings suggest Growing Degree Days (GDDs) as important climatic factors, while water holding capacity is one of the dominant soil properties in interpreting crop yield variability. Our findings will facilitate growers, crop production scientists, land management specialists, stakeholders, and policy makers in their future decision-making processes related to sustainable and long-term soil, water, and crop management practices.