TU Munich's NeuralCrop Beats Traditional Crop Models by 80% on Yield Accuracy
NeuralCrop is a differentiable hybrid of LPJmL and neural networks for crop yield projection. Trained first to emulate LPJmL, then fine-tuned on flux-tower and yield data end-to-end. Improves yield correlation by 80.6% for European wheat and 25.6% for US maize versus baseline.
Takeaways
- NeuralCrop is a differentiable hybrid of LPJmL and neural networks for crop yield projection.
- Trained first to emulate LPJmL, then fine-tuned on flux-tower and yield data end-to-end.
- Improves yield correlation by 80.6% for European wheat and 25.6% for US maize versus baseline.
- Beats the AgMIP multi-model ensemble median on drought-year yield anomalies.
- Runs orders of magnitude faster on one H100 than LPJmL on a 128-core CPU node.
- Paper on arXiv ; no public code release yet.
A team from the Technical University of Munich, the Potsdam Institute for Climate Impact Research, and partner institutions describes NeuralCrop , a differentiable hybrid of the LPJmL crop model and several small neural networks. In historical evaluations of European wheat and US maize, the authors report stronger yield estimates than the original process-based model and competitive results against data-only baselines and a multi-model ensemble. The preprint focuses on climate-impact analysis and crop-risk simulation; it does not validate an operational next-season forecasting system.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
Read original report
