NeuralCrop: Combining physics and machine learning for improved crop modelling
Organizations: Munich Climate Center and Earth System Modelling Group, Department of Aerospace and Geodesy, School of Engineering and Design, Technical University of Munich, Munich, Germany. · Potsdam Institute for Climate Impact Research, Potsdam, Germany. · University of Exeter, Exeter, UK.
Abstract
Global gridded crop models (GGCMs) are crucial for projecting climate impacts on agricultural productivity and assessing associated risks to food security. However, state-of-the-art GGCMs are subject to substantial uncertainties arising from reduced representations of complex processes. Projected increases in the frequency and severity of climate extremes require more reliable agricultural yield simulations. Recent machine learning approaches trained on observational data provide alternatives to GGCMs, but remain under-constrained due to sparse observations and show poor out-of-distribution generalization. Here we introduce NeuralCrop, a differentiable hybrid GGCM that combines the strengths of an advanced process-based GGCM (LPJmL) with data-driven components. NeuralCrop is first trained to reproduce its underlying fully process-based version, before it is fine-tuned on observational flux data of physiological variables. Evaluation against held-out flux-tower observations from European wheat and US maize sites shows 32.6-45.2% reductions in mean normalized root-mean-square error for daily carbon and water fluxes. Although fine-tuned only on physiological variables, NeuralCrop improves temporal correlations with independent yield records across 71.4% of the cultivated area for European wheat and 84.0% for the US Corn Belt during 1981-2019. It performs highly competitively compared to GGCMI Phase~3 models. NeuralCrop reproduces yield anomalies more accurately across a range of soil-moisture conditions and especially for extreme drought conditions. For large-scale, long-term simulations, NeuralCrop runs nearly two orders of magnitude faster than the CPU-based LPJmL baseline model, mainly thanks to GPU acceleration. Our results highlight end-to-end hybrid crop modelling as a promising avenue for improving crop simulations and informing food security assessments under climate change.
Figures & tables
Appendix figures & tables20 assets
Supplementary material from the paper’s appendix.
Appendix
| Variable | Symbol | Dimension | Units | Time |
|---|---|---|---|---|
| Inter-cellular to atmospheric CO 2 ratio | 1 | - | daily | |
| Maximum Rubisco capacity | 1 | daily | ||
| Gross primary productivity | GPP | 1 | daily | |
| Crop carbon pools | 4 | daily | ||
| Crop respiration | 1 | daily | ||
| Crop transpiration | 1 | daily |
| Type | Variable | Units | Time |
|---|---|---|---|
| Climate | Temperature | daily | |
| Climate | Precipitation | daily | |
| Climate | Net longwave radiation | daily | |
| Climate | Downward shortwave radiation | daily | |
| Climate | CO 2 | annual | |
| Soil | Soil texture | - | static |
| Type | Variable | Symbol | Units | Time |
| Feature | Air temperature | daily | ||
| Feature | Precipitation | daily | ||
| Feature | Downward shortwave radiation | daily | ||
| Feature | Downward longwave radiation | daily | ||
| Feature | Upward longwave radiation | daily | ||
| Feature | CO 2 | daily |
| Grid cells | LPJmL | NeuralCrop | Times (speed up) |
|---|---|---|---|
| 1 | 0.50 s | 46.01 s | 0.011x |
| 1573 | 833.99 s | 51.24 s | 16.27x |
| 7865 | 4169.94 s | 70.02 s | 59.55x |
| 14157 | 7505.89 s | 91.16 s | 82.33x |
| Crop | Group | Sites | Grouping basis | Seasons |
|---|---|---|---|---|
| Wheat | W01 | DE-Geb | standalone site | 4 |
| Wheat | W02 | DE-RuM, DE-RuS, DE-Seh | nearby sites | 11 |
| Wheat | W03 | FR-Aur, FR-Lam | nearby sites | 8 |
| Wheat | W04 | FR-EM2 | standalone site | 2 |
| Wheat | W05 | FR-Gri | standalone site | 2 |
| Wheat | W06 | IT-CA2 | standalone site | 2 |
| Crop | Target/metric | Default | Hybrid | Improvement | 95% CI |
|---|---|---|---|---|---|
| Wheat | GPP | 0.716 | 0.896 | +0.180 | [0.102, 0.293] |
| Wheat | RECO | 0.763 | 0.877 | +0.114 | [0.084, 0.143] |
| Wheat | ET | 0.681 | 0.875 | +0.194 | [0.163, 0.226] |
| Wheat | GPP nRMSE | 0.995 | 0.488 | 0.507 | [0.353, 0.648] |
| Wheat | RECO nRMSE | 0.677 | 0.390 | 0.287 | [0.163, 0.410] |
| Wheat | ET nRMSE | 0.778 | 0.528 | 0.249 | [0.181, 0.314] |
| European wheat | US maize | |||||
| Index interval | Leading year (%) | Top three (%) | Leading year (%) | Top three (%) | ||
| 20-point index classes | ||||||
| 35 | 2011 (11.2) | 29.2 | 37 | 1988 (13.7) | 35.7 | |
| 20–40 | 38 | 2015 (8.0) | 23.2 | 39 | 1994 (8.3) | 20.5 |
| 40–60 | 39 | 2008 (8.0) | 20.8 | 39 | 2002 (6.2) | 16.5 |
| 60–80 | 38 | 2001 (10.3) | 22.8 | 39 | 1984 (6.5) | 18.5 |
Crop Yield Prediction
Crop yield prediction estimates harvests from crop, weather, soil, satellite, and management data to support agricultural planning.
See all 21 papers