Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.07893 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915851080302592 |
|---|---|
| author | Aitken, Colin Masiwal, Rajat Marchakitus, Adam Kowal, Katherine Gupta, Mayank Yang, Tyler Jina, Amir Hassanzadeh, Pedram Boos, William R. Kremer, Michael |
| author_facet | Aitken, Colin Masiwal, Rajat Marchakitus, Adam Kowal, Katherine Gupta, Mayank Yang, Tyler Jina, Amir Hassanzadeh, Pedram Boos, William R. Kremer, Michael |
| contents | Hundreds of millions of farmers make high-stakes decisions under uncertainty about future weather. Forecasts can inform these decisions, but available choices and their risks and benefits vary between farmers. We introduce a decision-theory framework for designing useful forecasts in settings where the forecaster cannot prescribe optimal actions because farmers' circumstances are heterogeneous. We apply this framework to the case of seasonal onset of monsoon rains, a key date for planting decisions and agricultural investments in many tropical countries. We develop a system for tailoring forecasts to the requirements of this framework by blending systematically benchmarked artificial intelligence (AI) weather prediction models with a new "evolving farmer expectations" statistical model. This statistical model applies Bayesian inference to historical observations to predict time-varying probabilities of first-occurrence events throughout a season. The blended system yields more skillful Indian monsoon forecasts at longer lead times than its components or any multi-model average. In 2025, this system was deployed operationally in a government-led program that delivered subseasonal monsoon onset forecasts to 38 million Indian farmers, skillfully predicting that year's early-summer anomalous dry period. This decision-theory framework and blending system offer a pathway for developing climate adaptation tools for large vulnerable populations around the world. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07893 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Designing probabilistic AI monsoon forecasts to inform agricultural decision-making Aitken, Colin Masiwal, Rajat Marchakitus, Adam Kowal, Katherine Gupta, Mayank Yang, Tyler Jina, Amir Hassanzadeh, Pedram Boos, William R. Kremer, Michael Machine Learning Artificial Intelligence General Economics Economics Atmospheric and Oceanic Physics Hundreds of millions of farmers make high-stakes decisions under uncertainty about future weather. Forecasts can inform these decisions, but available choices and their risks and benefits vary between farmers. We introduce a decision-theory framework for designing useful forecasts in settings where the forecaster cannot prescribe optimal actions because farmers' circumstances are heterogeneous. We apply this framework to the case of seasonal onset of monsoon rains, a key date for planting decisions and agricultural investments in many tropical countries. We develop a system for tailoring forecasts to the requirements of this framework by blending systematically benchmarked artificial intelligence (AI) weather prediction models with a new "evolving farmer expectations" statistical model. This statistical model applies Bayesian inference to historical observations to predict time-varying probabilities of first-occurrence events throughout a season. The blended system yields more skillful Indian monsoon forecasts at longer lead times than its components or any multi-model average. In 2025, this system was deployed operationally in a government-led program that delivered subseasonal monsoon onset forecasts to 38 million Indian farmers, skillfully predicting that year's early-summer anomalous dry period. This decision-theory framework and blending system offer a pathway for developing climate adaptation tools for large vulnerable populations around the world. |
| title | Designing probabilistic AI monsoon forecasts to inform agricultural decision-making |
| topic | Machine Learning Artificial Intelligence General Economics Economics Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2603.07893 |