Weather conditions regulate the growth and yield of crops, especially in rain-fed agricultural systems. This study evaluated the use and relative importance of readily available weather data to develop yield estimation models for maize and soybean in the US central Corn Belt. Total rainfall (Rain), average air temperature (Tavg), and the difference between maximum and minimum air temperature (Tdiff) at weekly, biweekly, and monthly timescales from May to August were used to estimate county-level maize and soybean grain yields for Iowa, Illinois, Indiana, and Minnesota. Step-wise multiple linear regression (MLR), general additive (GAM), and support vector machine (SVM) models were trained with Rain, Tavg, and with/without Tdiff. For the total study area and at individual state level, SVM outperformed other models at all temporal levels for both maize and soybean. For maize, Tavg and Tdiff during July and August, and Rain during June and July, were relatively more important whereas for soybean, Tavg in June and Tdiff and Rain during August were more important. The SVM model with weekly Rain and Tavg estimated the overall maize yield with a root mean square error (RMSE) of 591 kg ha−1 (4.9% nRMSE) and soybean yield with a RMSE of 205 kg ha−1 (5.5% nRMSE). Inclusion of Tdiff in the model considerably improved yield estimation for both crops; however, the magnitude of improvement varied with the model and temporal level of weather data. This study shows the relative importance of weather variables and reliable yield estimation of maize and soybean from readily available weather data to develop a decision support tool in the US central Corn Belt.
Bibliographical noteFunding Information:
The authors would like to thank the two anonymous reviewers for their insightful suggestions and comments on the manuscript. We appreciate the financial support from the University of Minnesota, Saint Paul, MN.
© 2020, The Author(s).
- Crop modeling
- Statistical modeling
- Weather index
- Yield forecasting