From extreme weather to agricultural consequences with agentic AI
Abstract
Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffer or how much is at risk, and the records that could tell span many sources. We present WxCrop, the first agent that judges agricultural hazards from physically interpretable weather indices examined by causal analysis, and the first that combines weather and agricultural information to predict crop loss reliably for past and forecast dates. We demonstrate it in Florida on hurricanes, freezes and dry heat, with a loss model calibrated on insurance records for each, and the same procedure extends to other hazards and areas. Three checks show reliability: the hurricane index detects recorded cyclone days with an AUC of 0.98, recorded losses in held-out years are reproduced to within 2%, and independent production records confirm the county rankings (rank correlation 0.63). Users ask the agent for each crop group's loss as a fraction of expected season value, every number sourced, so that governments, growers and scientists respond to agricultural disasters quickly.
Related
- Global warming and the Pacific Decadal Oscillation drive seasonally varying increases in extreme fire weather over the southwestern US
- AI-Boosted Rare Event Sampling to Characterize Extreme Weather
- Building adaptive capacity of US Gulf Coast city practitioners to extreme weather events.
- A neural network-based Universal Thermal Climate Index for reliable global thermal-stress classification across extreme weather
- RHITA: a web tool for real-time detection of extreme weather events
BibTeX
@misc{yu2026from,
title = {{From extreme weather to agricultural consequences with agentic AI}},
author = {Minghan Yu and Mengyu Dai and Yixin Wen and Haizhao Yang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40641},
eprint = {2610.40641},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40641},
}
RIS
TY - UNPB
TI - From extreme weather to agricultural consequences with agentic AI
AU - Minghan Yu
AU - Mengyu Dai
AU - Yixin Wen
AU - Haizhao Yang
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.40641
UR - https://arxiv.org/abs/2610.40641
AB - Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffer or how much is at risk, and the records that could tell span many sources. We present WxCrop, the first agent that judges agricultural hazards from physically interpretable weather indices examined by causal analysis, and the first that combines weather and agricultural information to predict crop loss reliably for past and forecast dates. We demonstrate it in Florida on hurricanes, freezes and dry heat, with a loss model calibrated on insurance records for each, and the same procedure extends to other hazards and areas. Three checks show reliability: the hurricane index detects recorded cyclone days with an AUC of 0.98, recorded losses in held-out years are reproduced to within 2%, and independent production records confirm the county rankings (rank correlation 0.63). Users ask the agent for each crop group's loss as a fraction of expected season value, every number sourced, so that governments, growers and scientists respond to agricultural disasters quickly.
ER -