Differentiable crop models improve yield predictions and management strategies
Advancing global crop simulations with differentiable modelling
Computational Engineering, Finance, and Science
Summary
Crop models help predict food production under changing conditions but are hard to tune accurately. The authors made a new type of crop model that can automatically adjust its settings by learning from real-world data on plant growth and water use. This makes the model better at predicting crop yields and understanding why crops fail during bad weather. It also helps farmers and planners design better ways to grow crops and reduce losses during droughts. Overall, the improved model offers more reliable food supply forecasts under future climates.
What this means in practice
- •For agricultural modelers: Calibrate crop model parameters automatically using observed environmental data to improve yield predictions worldwide.
- •For farm management teams: Design irrigation and other adaptive strategies to reduce yield losses during extreme weather events like droughts.
Authors
Yunan Lin, Sebastian Bathiany, Maximilian Gelbrecht, Jens Heinke, Christoph Müller, Niklas Boers
Abstract
Global gridded crop models (GGCMs) are crucial for assessing the performance of food producing systems, for example under climate change or their contribution to environmental challenges. However, systematic calibration of their parameters remains a long-standing challenge. Persisting uncertainties in these parameters propagate into future crop projections, thereby affecting and potentially biasing food security assessments. Here we present a fully process-based differentiable GGCM implementation that offers a fundamentally new approach to parameter calibration, uncertainty quantification, yield loss attribution, and management optimization. Using automatic differentiation, we optimize selected model parameters against site-scale carbon and water flux observations, reducing normalized root-mean-square errors at held-out sites by 24.8-36.2% compared to the default state-of-the-art model. Without calibration against yield data, the optimized model better captures detrended yield anomalies across 61.2-64.3% of global crop area and reduces low-yield errors by 3.4-43.5% for wheat, rice, maize and soybean. It also ranks among the best performers in comparison with GGCMI Phase 3 models. Future simulations show that calibration reduces the projected end-of-century rice production increase from 55.1% to 22.1% under SSP5-8.5. Parameter ensembles further reveal that parameterizations with comparable historical skill can produce markedly different future production responses. Beyond calibration, differentiability enables the attribution of crop losses under extreme events and supports the design of adaptive crop management strategies. For the 2018 European drought, we identify spring heat and water limitation as major contributors to wheat yield losses and develop more effective irrigation strategies for mitigating simulated regional yield losses.