IDEAS home Printed from https://ideas.repec.org/a/nat/nature/v597y2021i7878d10.1038_s41586-021-03854-z.html
   My bibliography  Save this article

Skilful precipitation nowcasting using deep generative models of radar

Author

Listed:
  • Suman Ravuri

    (DeepMind)

  • Karel Lenc

    (DeepMind)

  • Matthew Willson

    (DeepMind)

  • Dmitry Kangin

    (Met Office
    University of Exeter)

  • Remi Lam

    (DeepMind)

  • Piotr Mirowski

    (DeepMind)

  • Megan Fitzsimons

    (Met Office)

  • Maria Athanassiadou

    (Met Office)

  • Sheleem Kashem

    (DeepMind)

  • Sam Madge

    (Met Office)

  • Rachel Prudden

    (Met Office
    University of Exeter)

  • Amol Mandhane

    (DeepMind)

  • Aidan Clark

    (DeepMind)

  • Andrew Brock

    (DeepMind)

  • Karen Simonyan

    (DeepMind)

  • Raia Hadsell

    (DeepMind)

  • Niall Robinson

    (Met Office
    University of Exeter)

  • Ellen Clancy

    (DeepMind)

  • Alberto Arribas

    (Met Office
    University of Reading)

  • Shakir Mohamed

    (DeepMind)

Abstract

Precipitation nowcasting, the high-resolution forecasting of precipitation up to two hours ahead, supports the real-world socioeconomic needs of many sectors reliant on weather-dependent decision-making1,2. State-of-the-art operational nowcasting methods typically advect precipitation fields with radar-based wind estimates, and struggle to capture important non-linear events such as convective initiations3,4. Recently introduced deep learning methods use radar to directly predict future rain rates, free of physical constraints5,6. While they accurately predict low-intensity rainfall, their operational utility is limited because their lack of constraints produces blurry nowcasts at longer lead times, yielding poor performance on rarer medium-to-heavy rain events. Here we present a deep generative model for the probabilistic nowcasting of precipitation from radar that addresses these challenges. Using statistical, economic and cognitive measures, we show that our method provides improved forecast quality, forecast consistency and forecast value. Our model produces realistic and spatiotemporally consistent predictions over regions up to 1,536 km × 1,280 km and with lead times from 5–90 min ahead. Using a systematic evaluation by more than 50 expert meteorologists, we show that our generative model ranked first for its accuracy and usefulness in 89% of cases against two competitive methods. When verified quantitatively, these nowcasts are skillful without resorting to blurring. We show that generative nowcasting can provide probabilistic predictions that improve forecast value and support operational utility, and at resolutions and lead times where alternative methods struggle.

Suggested Citation

  • Suman Ravuri & Karel Lenc & Matthew Willson & Dmitry Kangin & Remi Lam & Piotr Mirowski & Megan Fitzsimons & Maria Athanassiadou & Sheleem Kashem & Sam Madge & Rachel Prudden & Amol Mandhane & Aidan C, 2021. "Skilful precipitation nowcasting using deep generative models of radar," Nature, Nature, vol. 597(7878), pages 672-677, September.
  • Handle: RePEc:nat:nature:v:597:y:2021:i:7878:d:10.1038_s41586-021-03854-z
    DOI: 10.1038/s41586-021-03854-z
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41586-021-03854-z
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.

    File URL: https://libkey.io/10.1038/s41586-021-03854-z?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Fenghua Ling & Jing-Jia Luo & Yue Li & Tao Tang & Lei Bai & Wanli Ouyang & Toshio Yamagata, 2022. "Multi-task machine learning improves multi-seasonal prediction of the Indian Ocean Dipole," Nature Communications, Nature, vol. 13(1), pages 1-9, December.
    2. Xueliang Zhao & Qilong Sun & Xiaoguang Lin, 2023. "Physical Attention-Gated Spatial-Temporal Predictive Network for Weather Forecasting," Mathematics, MDPI, vol. 11(6), pages 1-10, March.
    3. Olivares, Kin G. & Meetei, O. Nganba & Ma, Ruijun & Reddy, Rohan & Cao, Mengfei & Dicker, Lee, 2024. "Probabilistic hierarchical forecasting with deep Poisson mixtures," International Journal of Forecasting, Elsevier, vol. 40(2), pages 470-489.
    4. Pan Xia & Lu Zhang & Min Min & Jun Li & Yun Wang & Yu Yu & Shengjie Jia, 2024. "Accurate nowcasting of cloud cover at solar photovoltaic plants using geostationary satellite images," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    5. Aurélie Bouchard & Magalie Buguet & Adrien Chan-Hon-Tong & Jean Dezert & Philippe Lalande, 2023. "Comparison of different forecasting tools for short-range lightning strike risk assessment," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, Springer;International Society for the Prevention and Mitigation of Natural Hazards, vol. 115(2), pages 1011-1047, January.
    6. Fuping Liu & Ying Liu & Chen Yang & Ruixun Lai, 2022. "A New Precipitation Prediction Method Based on CEEMDAN-IWOA-BP Coupling," Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), Springer;European Water Resources Association (EWRA), vol. 36(12), pages 4785-4797, September.
    7. Xiao-Yang Liu & Jingyang Rui & Jiechao Gao & Liuqing Yang & Hongyang Yang & Zhaoran Wang & Christina Dan Wang & Jian Guo, 2021. "FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative Finance," Papers 2112.06753, arXiv.org, revised Mar 2022.
    8. Chu, Yinghao & Wang, Yiling & Yang, Dazhi & Chen, Shanlin & Li, Mengying, 2024. "A review of distributed solar forecasting with remote sensing and deep learning," Renewable and Sustainable Energy Reviews, Elsevier, vol. 198(C).
    9. Marino Marrocu & Luca Massidda, 2022. "Coupling a Neural Network with a Spatial Downscaling Procedure to Improve Probabilistic Nowcast for Urban Rain Radars," Forecasting, MDPI, vol. 4(4), pages 1-21, October.
    10. Bai, Mingliang & Yao, Peng & Dong, Haiyu & Fang, Zuliang & Jin, Weixin & Xusheng Yang, & Liu, Jinfu & Yu, Daren, 2024. "Spatial-temporal characteristics analysis of solar irradiance forecast errors in Europe and North America," Energy, Elsevier, vol. 297(C).

    More about this item

    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:nat:nature:v:597:y:2021:i:7878:d:10.1038_s41586-021-03854-z. 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.

    We have no bibliographic references for this item. You can help adding them by using 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: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    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.