Advancing global crop simulations with differentiable modelling
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.
Related
- DiffSWE2d: a differentiable Shallow Water Equations solver for end-to-end flood and tsunami modelling
- Drought vulnerability assessment and its severe impact on crop production and livelihood of people: An empirical modelling of northern Ghana
- Differentiable land model reveals global environmental controls on latent ecological functions
- Advancing Spatial Pattern Integration in Species Distribution Modelling With Computer Vision: How Grain Size and Extent Concepts Shape Predictions of Emerging Aquatic Insects
- Global sensitivity analysis of a complex marine ecosystem model: Advancing the understanding of ecosystem functioning
BibTeX
@misc{lin2026advancing,
title = {{Advancing global crop simulations with differentiable modelling}},
author = {Yunan Lin and Sebastian Bathiany and Maximilian Gelbrecht and Jens Heinke and Christoph Müller and Niklas Boers},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.36827},
eprint = {2610.36827},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.36827},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Advancing global crop simulations with differentiable modelling
AU - Yunan Lin
AU - Sebastian Bathiany
AU - Maximilian Gelbrecht
AU - Jens Heinke
AU - Christoph Müller
AU - Niklas Boers
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.36827
UR - https://arxiv.org/abs/2610.36827
AB - 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.
ER -