Random Forests for Global and Regional Crop Yield Predictions

TLDR

Accurate predictions of crop yield are critical for developing effective agricultural and food policies at the regional and global scales. The study evaluated Random Forests for predicting crop yield responses to climate and biophysical variables in wheat, maize, and potato at global and regional scales, benchmarking against multiple linear regressions. The authors trained and tested Random Forest models on gridded global wheat yield, thirty‑year US county maize yield, and northeastern seaboard potato and maize silage yield data, comparing them to multiple linear regression benchmarks. Random Forests outperformed multiple linear regressions, achieving RMSEs of 6–14% versus 14–49% for MLR, demonstrating high accuracy, precision, and versatility for crop yield predictions, though accuracy may decline at extreme values beyond training data.

Abstract

Accurate predictions of crop yield are critical for developing effective agricultural and food policies at the regional and global scales. We evaluated a machine-learning method, Random Forests (RF), for its ability to predict crop yield responses to climate and biophysical variables at global and regional scales in wheat, maize, and potato in comparison with multiple linear regressions (MLR) serving as a benchmark. We used crop yield data from various sources and regions for model training and testing: 1) gridded global wheat grain yield, 2) maize grain yield from US counties over thirty years, and 3) potato tuber and maize silage yield from the northeastern seaboard region. RF was found highly capable of predicting crop yields and outperformed MLR benchmarks in all performance statistics that were compared. For example, the root mean square errors (RMSE) ranged between 6 and 14% of the average observed yield with RF models in all test cases whereas these values ranged from 14% to 49% for MLR models. Our results show that RF is an effective and versatile machine-learning method for crop yield predictions at regional and global scales for its high accuracy and precision, ease of use, and utility in data analysis. RF may result in a loss of accuracy when predicting the extreme ends or responses beyond the boundaries of the training data.