NeuralCrop: Combining physics and machine learning for improved crop yield predictions

We introduce NeuralCrop, a differentiable hybrid global gridded crop model (GGCM) that combines the strengths of an advanced process-based GGCM, resolving important processes explicitly, with data-driven machine learning components. The model is first trained to emulate a competitive GGCM before it is fine-tuned on observational data. We show that NeuralCrop outperforms state-of-the-art GGCMs across site-level and large-scale cropping regions. Across moisture conditions, NeuralCrop reproduces the interannual yield anomalies in European wheat regions and the US Corn Belt more accurately during the period from 2000 to 2019 with particularly strong improvements under drought extremes. When generalizing to conditions unseen during training, NeuralCrop continues to make robust projections, while pure machine learning models exhibit substantial performance degradation. Thanks to optimization to graphical processing units (GPUs), NeuralCrop is more than 80 times faster on a single GPU than a state-of-the-art competitor on 128 CPU cores. Our results show that our hybrid crop modelling approach offers overall improved crop simulations and more reliable yield projections under climate change and intensifying extreme weather conditions.