From extreme weather to agricultural consequences with agentic AI
arXiv cs.AI · 30 Oct 2026, 03:58 AEST
WxCrop is an innovative agent that predicts agricultural hazards by analyzing weather indices through causal analysis. It has been tested in Florida for various extreme weather events and shows high reliability in predicting crop losses.
Key facts
- 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.
Read aloud
WxCrop is an innovative agent that predicts agricultural hazards by analyzing weather indices through causal analysis. It has been tested in Florida for various extreme weather events and shows high reliability in predicting crop losses. 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 zero point nine eight, recorded losses in held-out years are reproduced to within two percent, and independent production records confirm the county rankings rank correlation zero point six three. 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.
Sources in this cluster
- From extreme weather to agricultural consequences with agentic AI
arXiv cs.AI · 30 Oct 2026, 03:58 AEST