Interpretability of deep learning models for crop yield forecasting

Dilli R. Paudel, Allard de Wit, Hendrik Boogaard, Diego Marcos, Sjoukje A. Osinga, Ioannis N. Athanasiadis

Abstract: Highlights•Deep learning models learn plausible relationships between features and crop yield.•Neural networks learn features that perform similar to expert-designed features.•Feature influence on yield matches expert knowledge when model accuracy is high.