Tag
The paper presents an input-frugal deep learning framework using only routine weather data plus two static context inputs for national crop-yield forecasting, benchmarking MLP, CNN, LSTM, Transformer, and Mamba models on 20 seasons of Brazilian soybean data. The Transformer achieves the best accuracy (RMSE 149 kg ha⁻¹, rRMSE 5.3%), reducing error by 47.6% relative to a farmer baseline, with SHAP diagnostics showing crop year drives long-run trends while weather variables drive interannual deviations.
This paper presents the first machine learning study for crop yield forecasting in Sierra Leone, finding that combining freely available satellite climate data (CHIRPS, NASA POWER) with national crop statistics reduces forecast error by a third compared to persistence, though crop statistics alone are insufficient.