CoChat
Sign Up
Cited by 465Meteorological Phenomena and SimulationsPrecipitation Measurement and AnalysisHydrological Forecasting Using AI

Skilful nowcasting of extreme precipitation with NowcastNet

Open access
Zhang, Yuchen, Long, Mingsheng, Chen, Kaiyuan, Xing, Lanxiang, Jin, Ronghua, Jordan, Michael I., Wang, Jianmin·2023·Nature
DOI 10.1038/s41586-023-06184-4PMC PMC10356617
Open this paper in CoChat — free accountOpen PDF

Abstract

Abstract Extreme precipitation is a considerable contributor to meteorological disasters and there is a great need to mitigate its socioeconomic effects through skilful nowcasting that has high resolution, long lead times and local details 1–3 . Current methods are subject to blur, dissipation, intensity or location errors, with physics-based numerical methods struggling to capture pivotal chaotic dynamics such as convective initiation 4 and data-driven learning methods failing to obey intrinsic physical laws such as advective conservation 5 . We present NowcastNet, a nonlinear nowcasting model for extreme precipitation that unifies physical-evolution schemes and conditional-learning methods into a neural-network framework with end-to-end forecast error optimization. On the basis of radar observations from the USA and China, our model produces physically plausible precipitation nowcasts with sharp multiscale patterns over regions of 2,048 km × 2,048 km and with lead times of up to 3 h. In a systematic evaluation by 62 professional meteorologists from across China, our model ranks first in 71% of cases against the leading methods. NowcastNet provides skilful forecasts at light-to-heavy rain rates, particularly for extreme-precipitation events accompanied by advective or convective processes that were previously considered intractable.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41586-023-06184-4

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Current implementations of advection schemes fail to incorporate nonlinear evolution processes, leading to reduced accuracy in precipitation nowcasts.

    “However, current implementations of advection schemes fail to incorporate nonlinear evolution processes, leading to reduced accuracy in precipitation nowcasts, such as heavy rain reported in [16] and hailstorms analyzed in our study.”

    From MiMo: Unlocking the Reasoning Potential of Language Model - From Pretraining to Posttraining (2025) · cites this paper as [16]

  • NowcastNet aggregates spatial-temporal features by integrating a deep generative model with physical knowledge of precipitation processes.

    “Long etal. [16] propose NowcastNet, a reliable nowcasting framework that aggregates spatial-temporal features by integrating DGM with physical knowledge of precipitation processes, including the conservation law of cloud transport [9] and the rain rate distribution [3].”

    From MiMo: Unlocking the Reasoning Potential of Language Model - From Pretraining to Posttraining (2025) · cites this paper as [16]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 33

  1. [2]Pendergrass AG What precipitation is extreme? Science 2018 360 1072 1073 10.1126/science.aat1871 29880673 · DOI
  2. [4]Ravuri S Skilful precipitation nowcasting using deep generative models of radar Nature 2021 597 672 677 10.1038/s41586-021-03854-z 34588668 PMC8481123 · DOI · Paper page
  3. [5]Karniadakis GE Physics-informed machine learning Nat. Rev. Phys. 2021 3 422 440 10.1038/s42254-021-00314-5 · DOI · Paper page
  4. [6]Berne A Delrieu G Creutin J-D Obled C Temporal and spatial resolution of rainfall measurements required for urban hydrology J. Hydrol. 2004 299 166 179 10.1016/S0022-1694(04)00363-4 · DOI
  5. [7]Sun J Use of NWP for nowcasting convective precipitation: recent progress and challenges Bull. Am. Meteorol. Soc. 2014 95 409 426 10.1175/BAMS-D-11-00263.1 · DOI
  6. [9]Pulkkinen S Pysteps: an open-source Python library for probabilistic precipitation nowcasting (v1.0) Geosci. Model Dev. 2019 12 4185 4219 10.5194/gmd-12-4185-2019 · DOI · Paper page
  7. [10]Ruzanski E Chandrasekar V Wang Y The CASA nowcasting system J. Atmos. Ocean. Technol. 2011 28 640 655 10.1175/2011JTECHA1496.1 · DOI · Paper page
  8. [11]Roca-Sancho, J., Berenguer, M., Zawadzki, I. & Sempere-Torres, D. in Proc. Conference on Radar Meteorology P7.2 (2009).
  9. [12]Shi, X. et al. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Advances in Neural Information Processing Systems Vol. 28 (eds Cortes, C. et al.) (NIPS, 2015).
  10. [13]Wang Y PredRNN: a recurrent neural network for spatiotemporal predictive learning IEEE Trans. Pattern Anal. Mach. Intell. 2022 45 2208 2225 10.1109/TPAMI.2022.3165153 35380958 · DOI · Paper page
  11. [14]Ayzel G Scheffer T Heistermann M RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting Geosci. Model Dev. 2020 13 2631 2644 10.5194/gmd-13-2631-2020 · DOI
  12. [15]Espeholt, L. et al. Deep learning for twelve hour precipitation forecasts. Nat. Commun.13, 5145 (2022). PMC9436943 36050311
  13. [16]Franch G Precipitation nowcasting with orographic enhanced stacked generalization: improving deep learning predictions on extreme events Atmosphere 2020 11 267 10.3390/atmos11030267 · DOI
  14. [17]Crane RK Space-time structure of rain rate fields J. Geophys. Res. Atmos. 1990 95 2011 2020 10.1029/JD095iD03p02011 · DOI · Paper page
  15. [18]Seed A A dynamic and spatial scaling approach to advection forecasting J. Appl. Meteorol. 2003 42 381 388 10.1175/1520-0450(2003)042<0381:ADASSA>2.0.CO;2 · DOI
  16. [19]Weyn JA Durran DR The scale dependence of initial-condition sensitivities in simulations of convective systems over the southeastern United States Q. J. R. Meteorol. Soc. 2019 145 57 74 10.1002/qj.3367 · DOI
  17. [20]Park, T., Liu, M.-Y., Wang, T.-C. & Zhu, J.-Y. in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2337–2346 (IEEE, 2019).
  18. [21]Goodfellow, I. et al. Generative adversarial nets. In Advances in Neural Information Processing Systems Vol. 27 (eds Ghahramani, Z. et al.) (NIPS, 2014).
  19. [22]Germann U Zawadzki I Scale-dependence of the predictability of precipitation from continental radar images. Part I: description of the methodology Mon. Weather Rev. 2002 130 2859 2873 10.1175/1520-0493(2002)130<2859:SDOTPO>2.0.CO;2 · DOI
  20. [23]He, K., Zhang, X., Ren, S. & Sun, J. in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778 (IEEE, 2016).
  21. [25]Imhoff R Brauer C Overeem A Weerts A Uijlenhoet R Spatial and temporal evaluation of radar rainfall nowcasting techniques on 1,533 events Water Resour. Res. 2020 56 e2019WR026723 10.1029/2019WR026723 · DOI
  22. [26]Zhang J Multi-radar multi-sensor (MRMS) quantitative precipitation estimation: initial operating capabilities Bull. Am. Meteorol. Soc. 2016 97 621 638 10.1175/BAMS-D-14-00174.1 · DOI
  23. [27]Jiang, J., Shu, Y., Wang, J. & Long, M. Transferability in deep learning: a survey. Preprint at https://arxiv.org/abs/2201.05867 (2022). · arXiv
  24. [28]Jolliffe, I. T. & Stephenson, D. B. Forecast Verification: A Practitioner’s Guide in Atmospheric Science (Wiley, 2012).
  25. [29]Sinclair S Pegram G Empirical Mode Decomposition in 2-D space and time: a tool for space-time rainfall analysis and nowcasting Hydrol. Earth Syst. Sci. 2005 9 127 137 10.5194/hess-9-127-2005 · DOI
  26. [30]Ronneberger, O., Fischer, P. & Brox, T. in Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention 234–241 (MICCAI, 2015).
  27. [31]Xu, G. & Chandrasekar, V. Radar storm motion estimation and beyond: A spectral algorithm and radar observation based dynamic model. In Proc. International Symposium on Nowcasting and Very Short Range Forecasting (World Meteorological Organization, 2005).
  28. [32]Miyato, T., Kataoka, T., Koyama, M. & Yoshida, Y. Spectral normalization for generative adversarial networks. In Proc. International Conference on Learning Representations (ICLR, 2018).
  29. [33]Hofinger, M. et al. In Proc. European Conference on Computer Vision 770–786 (Springer, 2020).
  30. [34]Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. In Proc. International Conference on Learning Representations (ICLR, 2015).
  31. [35]Ulyanov, D., Vedaldi, A. & Lempitsky, V. Instance normalization: the missing ingredient for fast stylization. Preprint at https://arxiv.org/abs/1607.08022 (2016). · arXiv
  32. [37]Wang, Y., Long, M., Wang, J., Gao, Z. & Yu, P. S. In Advances in Neural Information Processing Systems Vol. 30 (eds Guyon, I. et al.) 879–888 (NIPS, 2017).
  33. [38]Zhang J National Mosaic and Multi-sensor QPE (NMQ) system: description, results, and future plans Bull. Am. Meteorol. Soc. 2011 92 1321 1338 10.1175/2011BAMS-D-11-00047.1 · DOI

Cited by

Sorted by citations

Authors
Zhang, Y., Long, M., Chen, K., Xing, L., Jin, R., Jordan, M. I., & Wang, J.
Affiliations
  • Tsinghua University (CN)
  • China Meteorological Administration (CN)
  • University of California, Berkeley (US)
Corresponding author
  • Long, Mingsheng
  • Jordan, Michael I.
  • Wang, Jianmin
ORCID
Venue
Nature
Publisher
Springer Science and Business Media LLC
Published
2023-07-05
Volume
619
Issue
7970
Pages
526-532
ISSN
  • 0028-0836 (ISSN-L)
  • 1476-4687
DOI
10.1038/s41586-023-06184-4
PMC
PMC10356617
OpenAlex
W4383197616
Cited by
465
References
2
Citations by year
2026: 151 · 2025: 165 · 2024: 134 · 2023: 15
FWCI
51.34
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
Funders
  • National Natural Science Foundation of China (62022050, 62021002)
  • China Meteorological Administration
  • Science Fund for Creative Research Groups
Topics
  • Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations
  • Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Precipitation Measurement and Analysis
  • Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
Keywords
heavy rainfall, nowcasting, radar observations, convective initiation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review