Uncertainty-aware neural emulation reveals climate-resilient maize traits at scale

Abstract

Global food security depends on predicting crop responses to climate variability, yet process based crop models remain too computationally expensive for large scale exploration of genotype and environment interactions. Here we develop a probabilistic neural emulator of APSIM that reproduces key maize growth processes across 13 outputs with high fidelity (with R^2 of 0.93) while reducing simulation time by several orders of magnitude. Trained on two million simulations spanning diverse genetic, soil, and management conditions, and augmented with a convolutional synthetic weather generator that produces physically consistent climate sequences, the framework enables scalable exploration of crop responses under realistic and diverse environmental inputs while providing calibrated predictive uncertainty without costly Bayesian inference. Applying this framework across 100,000 trait configurations, six soil environments in Iowa and Illinois, and climate projections through the year 2100 under two emissions scenarios, we identify 181 maize trait combinations that consistently maintain high yield across all tested conditionsan analysis infeasible with the mechanistic model alone. We further show that radiation use efficiency and temperature driven root dynamics are dominant drivers of yield resilience. Notably, projected yield distributions vary substantially across locations, with some lower productivity sites exhibiting yield increases under future climate scenarios, indicating that climate change may reshape regional yield potential in nonintuitive ways. These results demonstrate how uncertainty aware emulation transforms mechanistic crop simulation from a computational bottleneck into an on demand discovery engine, one capable of interrogating the full genotype, environment and management space at a scale no process-based model can match.

From Seedling Architecture to Grain: Linking Root and Shoot Traits with Yield Potential for Climate-Resilient Wheat Breeding
Amal Gamal Mohamed, Amira M. I. Mourad, Atif Aboelwafa +2
Plants (Basel, Switzerland)22 Sep 2026Peer-reviewedCC BYFull textPlant biologyEurope PMC
Tylosema esculentum (Marama Bean) as a Climate-Resilient Opportunity Crop: A Review of Nutritional, Medicinal, andGenomics Insights and Drought Adaptation
Pfunzo Gavhi, Mulisa Nkuna, Gumani Luidney Nemauluma +3
Plants (Basel, Switzerland)1 Oct 2026Peer-reviewedCC BYFull textPlant biologyEurope PMC
Innovations and policies for climate-resilient food and water systems in sub-Saharan Africa: a systematic review
Lindiwe Maphalala, Unathi Kolanisi, Denver Naidoo +1
Frontiers in Sustainable Food Systems26 May 2026Peer-reviewedCC BYFull text5 citedEcologyOpenAlex
Genomic forecasting for climate‐resilient fruit trees
Maxime Criado, Mathieu Brisson, Karine Alix +4
New Phytologist30 Jun 2026Peer-reviewedCC BY-NC-ND 4.0Full textGenetics & genomicsHAL
Deciphering plant stress resilience in different millet crops: from multi-omics discoveries to predictive breeding for climate-resilient crop enhancement
Mahalakshmi Mani, Poonguzhali Subramanian, Sourav Paramanik +1
Frontiers in plant science1 Oct 2026Peer-reviewedCC BYFull textPlant biologyEurope PMCCrossref

Cite

BibTeX RIS

BibTeX

@misc{saadati2026uncertaintyaware,
  title = {{Uncertainty-aware neural emulation reveals climate-resilient maize traits at scale}},
  author = {Mojdeh Saadati and Juan Panelo and Gustavo Visentini and Soumik Sarkar and Carlos Messina and Baskar Ganapathysubramanian},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2605.22848},
  eprint = {2605.22848},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.22848},
}

RIS

TY  - UNPB
TI  - Uncertainty-aware neural emulation reveals climate-resilient maize traits at scale
AU  - Mojdeh Saadati
AU  - Juan Panelo
AU  - Gustavo Visentini
AU  - Soumik Sarkar
AU  - Carlos Messina
AU  - Baskar Ganapathysubramanian
PY  - 2026
DA  - 2026/09/26
PB  - arXiv
DO  - 10.48550/arxiv.2605.22848
UR  - https://arxiv.org/abs/2605.22848
AB  - Global food security depends on predicting crop responses to climate variability, yet process based crop models remain too computationally expensive for large scale exploration of genotype and environment interactions. Here we develop a probabilistic neural emulator of APSIM that reproduces key maize growth processes across 13 outputs with high fidelity (with R^2 of 0.93) while reducing simulation time by several orders of magnitude. Trained on two million simulations spanning diverse genetic, soil, and management conditions, and augmented with a convolutional synthetic weather generator that produces physically consistent climate sequences, the framework enables scalable exploration of crop responses under realistic and diverse environmental inputs while providing calibrated predictive uncertainty without costly Bayesian inference. Applying this framework across 100,000 trait configurations, six soil environments in Iowa and Illinois, and climate projections through the year 2100 under two emissions scenarios, we identify 181 maize trait combinations that consistently maintain high yield across all tested conditionsan analysis infeasible with the mechanistic model alone. We further show that radiation use efficiency and temperature driven root dynamics are dominant drivers of yield resilience. Notably, projected yield distributions vary substantially across locations, with some lower productivity sites exhibiting yield increases under future climate scenarios, indicating that climate change may reshape regional yield potential in nonintuitive ways. These results demonstrate how uncertainty aware emulation transforms mechanistic crop simulation from a computational bottleneck into an on demand discovery engine, one capable of interrogating the full genotype, environment and management space at a scale no process-based model can match.
ER  -

Abstract

Related

Cite