IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2603.07893.html

Designing probabilistic AI monsoon forecasts to inform agricultural decision-making

Author

Listed:
  • Colin Aitken
  • Rajat Masiwal
  • Adam Marchakitus
  • Katherine Kowal
  • Mayank Gupta
  • Tyler Yang
  • Amir Jina
  • Pedram Hassanzadeh
  • William R. Boos
  • Michael Kremer

Abstract

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.

Suggested Citation

  • Colin Aitken & Rajat Masiwal & Adam Marchakitus & Katherine Kowal & Mayank Gupta & Tyler Yang & Amir Jina & Pedram Hassanzadeh & William R. Boos & Michael Kremer, 2026. "Designing probabilistic AI monsoon forecasts to inform agricultural decision-making," Papers 2603.07893, arXiv.org, revised Mar 2026.
    • Handle: RePEc:arx:papers:2603.07893
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2603.07893
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Xiaosheng Mu & Luciano Pomatto & Philipp Strack & Omer Tamuz, 2021. "From Blackwell Dominance in Large Samples to Rényi Divergences and Back Again," Econometrica, Econometric Society, vol. 89(1), pages 475-506, January.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Kailin Chen, 2025. "Communication as Voting," Papers 2505.14639, arXiv.org, revised May 2026.
    2. Mira Frick & Ryota Iijima & Yuhta Ishii, 2021. "Learning Efficiency of Multi-Agent Information Structures," Cowles Foundation Discussion Papers 2299R, Cowles Foundation for Research in Economics, Yale University, revised Dec 2021.
    3. Mira Frick & Ryota Iijima & Yuhta Ishii, 2021. "Welfare Comparisons for Biased Learning," Cowles Foundation Discussion Papers 2274, Cowles Foundation for Research in Economics, Yale University.
    4. Xiaosheng Mu & Luciano Pomatto & Philipp Strack & Omer Tamuz, 2021. "Monotone additive statistics," Papers 2102.00618, arXiv.org, revised Apr 2024.
    5. Kosenko, Andrew, 2024. "Beyond the Blackwell order in dichotomies," Economics Letters, Elsevier, vol. 245(C).
    6. Nidhish Shah & Shaurjya Mandal & Asfandyar Azhar, 2026. "All Substitution Is Local," Papers 2604.01443, arXiv.org.
    7. Zizhe Xia, 2025. "Comparisons of Experiments in Moral Hazard Problems," Papers 2507.12476, arXiv.org, revised May 2026.
    8. Alexander W. Bloedel & Weijie Zhong, 2025. "The Cost of Optimally Acquired Information," Papers 2511.05466, arXiv.org.
    9. Davide Bordoli & Ryota Iijima, 2025. "Convex Cost of Information via Statistical Divergence," Papers 2509.00229, arXiv.org.
    10. Xiaosheng Mu & Luciano Pomatto & Philipp Strack & Omer Tamuz, 2021. "Monotone Additive Statistics," Working Papers 2021-36, Princeton University. Economics Department..
    11. Xiaosheng Mu & Luciano Pomatto & Philipp Strack & Omer Tamuz, 2021. "From Blackwell Dominance in Large Samples to Rényi Divergences and Back Again," Econometrica, Econometric Society, vol. 89(1), pages 475-506, January.
    12. Mira Frick & Ryota Iijima & Yuhta Ishii, 2021. "Learning Efficiency of Multi-Agent Information Structures," Cowles Foundation Discussion Papers 2299R2, Cowles Foundation for Research in Economics, Yale University, revised Jul 2022.
    13. Andrew Kosenko, 2021. "Algebraic Properties of Blackwell's Order and A Cardinal Measure of Informativeness," Papers 2110.11399, arXiv.org.
    14. Alex Bloedel & Tommaso Denti & Luciano Pomatto, 2025. "Modeling information acquisition via f-divergence and duality," Papers 2510.03482, arXiv.org.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2603.07893. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.