Learning from Precipitation Events in the Wider Domain to Improve the Performance of a Deep Learning–Based Precipitation Nowcasting Model

Tsuyoshi Inoue aUniversity of Tsukuba, Tsukuba City, Ibaraki Prefecture, Japan

Search for other papers by Tsuyoshi Inoue in
Current site
Google Scholar
PubMed
Close
and
Ryohei Misumi bNational Research Institute for Earth Science and Disaster Resilience (NIED), Tsukuba City, Ibaraki Prefecture, Japan

Search for other papers by Ryohei Misumi in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

Deep learning models have been shown to perform well in terms of the radar-based precipitation nowcasting problem when compared with advection-based models. Yet, most of the existing literature has used locally trained models, and relatively little is known about how to construct deep learning–based nowcasting models applicable in wider domains. We conduct experiments for precipitation nowcasting using deep learning models spanning the region around Japan with the Japan Meteorological Agency radar precipitation dataset with 1-km spatial resolution and 5-min temporal resolution. We trained the model with radar data sampled from all over Japan, then applied transfer learning with regional data. Through this experiment, it is found that combining data from all over Japan is effective in improving the forecast performance of heavy precipitation with deep learning models.

Significance Statement

This paper proposes a methodological improvement for the problem of short-term rainfall forecasting (nowcasting) using deep learning. We trained deep learning models with data sampled from all over Japan, then applied transfer learning with regional data. We compared the performance metrics of several modeling approaches and demonstrated that learning from heavy precipitation examples collected from wider domains improves the performance significantly. This finding suggests that there are a lot of commonalities in the time evolution of rainfall patterns at different geographical locations, which could be exploited to improve the model’s performance. A future research topic could be to learn from a larger dataset, including precipitation datasets from other countries.

© 2022 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Tsuyoshi Inoue, s1930237@s.tsukuba.ac.jp

Abstract

Deep learning models have been shown to perform well in terms of the radar-based precipitation nowcasting problem when compared with advection-based models. Yet, most of the existing literature has used locally trained models, and relatively little is known about how to construct deep learning–based nowcasting models applicable in wider domains. We conduct experiments for precipitation nowcasting using deep learning models spanning the region around Japan with the Japan Meteorological Agency radar precipitation dataset with 1-km spatial resolution and 5-min temporal resolution. We trained the model with radar data sampled from all over Japan, then applied transfer learning with regional data. Through this experiment, it is found that combining data from all over Japan is effective in improving the forecast performance of heavy precipitation with deep learning models.

Significance Statement

This paper proposes a methodological improvement for the problem of short-term rainfall forecasting (nowcasting) using deep learning. We trained deep learning models with data sampled from all over Japan, then applied transfer learning with regional data. We compared the performance metrics of several modeling approaches and demonstrated that learning from heavy precipitation examples collected from wider domains improves the performance significantly. This finding suggests that there are a lot of commonalities in the time evolution of rainfall patterns at different geographical locations, which could be exploited to improve the model’s performance. A future research topic could be to learn from a larger dataset, including precipitation datasets from other countries.

© 2022 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Tsuyoshi Inoue, s1930237@s.tsukuba.ac.jp
Save
  • Agrawal, S., L. Barrington, C. Bromberg, J. Burge, C. Gazen, and J. Hickey, 2019: Machine learning for precipitation nowcasting from radar images. arXiv, 1912.12132, http://arxiv.org/abs/1912.12132.

  • Ayzel, G., M. Heistermann, A. Sorokin, O. Nikitin, and O. Lukyanova, 2019a: All convolutional neural networks for radar-based precipitation nowcasting. Procedia Comput. Sci., 150, 186192, https://doi.org/10.1016/j.procs.2019.02.036.

    • Search Google Scholar
    • Export Citation
  • Ayzel, G., M. Heistermann, and T. Winterrath, 2019b: Optical flow models as an open benchmark for radar-based precipitation nowcasting (rainymotion v0.1). Geosci. Model Dev., 12, 13871402, https://doi.org/10.5194/gmd-12-1387-2019.

    • Search Google Scholar
    • Export Citation
  • Babaeizadeh, M., C. Finn, D. Erhan, R. H. Campbell, and S. Levine, 2018: Stochastic variational video prediction. Sixth Int. Conf. on Learning Representations (ICLR), Vancouver, BC, Canada, ICLR Board, https://openreview.net/forum?id=rk49Mg-CW.

  • Brown, T., and Coauthors, 2020: Language models are few-shot learners. Advances in Neural Information Processing Systems 33 (NeurIPS 2020), H. Larochelle et al., Eds., Vol. 33, NeurIPS Proceedings, 1877–1901.

  • Cao, Y., Q. Li, H. Shan, Z. Huang, L. Chen, L. Ma, and J. Zhang, 2019: Precipitation nowcasting with star-bridge networks. arXiv, 1907.08069, https://doi.org/10.48550/arXiv.1907.08069.

    • Search Google Scholar
    • Export Citation
  • Denton, E., and R. Fergus, 2018: Stochastic video generation with a learned prior. Sixth Int. Conf. on Learning Representations (ICLR), Vancouver, BC, Canada, ICLR Board, https://openreview.net/forum?id=SJWzUiZd-r.

  • Franch, G., D. Nerini, M. Pendesini, L. Coviello, G. Jurman, C. Furlanello, and A. Wang, 2020: Precipitation nowcasting with orographic enhanced stacked generalization: Improving deep learning predictions on extreme events. Atmosphere, 11, 267, https://doi.org/10.3390/atmos11030267.

    • Search Google Scholar
    • Export Citation
  • Guen, V. L., and N. Thome, 2020: Disentangling physical dynamics from unknown factors for unsupervised video prediction. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Seattler, WA, CVPR, 11 pp., https://openaccess.thecvf.com/content_CVPR_2020/papers/Le_Guen_Disentangling_Physical_Dynamics_From_Unknown_Factors_for_Unsupervised_Video_Prediction_CVPR_2020_paper.pdf.

  • Han, L., Y. Zhao, and H. Chen, 2021: Advancing radar nowcasting through deep transfer learning. IEEE Trans. Geosci. Remote Sens., 60, 19, https://doi.org/10.1109/TGRS.2021.3056470.

    • Search Google Scholar
    • Export Citation
  • Japan Meteorological Agency, 2014: Precipitation analysis and prediction technology in the high resolution precipitation nowcast (in Japanese). Sokko-Jihou, 81, 5576.

    • Search Google Scholar
    • Export Citation
  • Japan Meteorological Agency, 2021: General information on climate of Japan—Overview of Japan’s climate. Accessed 2 October 2021, https://www.data.jma.go.jp/gmd/cpd/longfcst/en/tourist_japan.html.

  • Kato, R., S. Shimizu, K. Shimose, T. Maesaka, K. Iwanami, and H. Nakagaki, 2017: Predictability of meso-gamma-scale, localized, extreme heavy rainfall during the warm season in Japan using high-resolution precipitation nowcasts. Quart. J. Roy. Meteor. Soc., 143, 14061420, https://doi.org/10.1002/qj.3013.

    • Search Google Scholar
    • Export Citation
  • Nagata, K., 2011: Quantitative precipitation estimation and quantitative precipitation forecasting by the Japan meteorological agency. Japan Meteorological Agency Tech. Rev. 13, RSMC Tokyo–Typhoon Center, 14 pp., https://www.jma.go.jp/jma/jma-eng/jma-center/rsmc-hp-pub-eg/techrev/text13-2.pdf.

  • Ravuri, S., and Coauthors, 2021: Skilful precipitation nowcasting using deep generative models of radar. Nature, 597, 672677, https://doi.org/10.1038/s41586-021-03854-z.

    • Search Google Scholar
    • Export Citation
  • Roberts, N. M., and H. W. Lean, 2008: Scale-selective verification of rainfall accumulations from high-resolution forecasts of convective events. Mon. Wea. Rev., 136, 7897, https://doi.org/10.1175/2007MWR2123.1.

    • Search Google Scholar
    • Export Citation
  • Shakti, P. C., R. Misumi, T. Nakatani, K. Iwanami, M. Maki, T. Maesaka, and K. Hirano, 2016: Accuracy of quantitative precipitation estimation using operational weather radars: A case study of heavy rainfall on 9–10 September 2015 in the East Kanto region, Japan. J. Disaster Res., 11, 10031016, https://doi.org/10.20965/jdr.2016.p1003.

    • Search Google Scholar
    • Export Citation
  • Shi, X., Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W.-C. Woo, 2015: Convolutional LSTM network: A machine learning approach for precipitation nowcasting. NIPS’15: Proc. 28th Int. Conf. on Neural Information Processing Systems, Vol. 1, Montreal, QC, Canada, ACM, 802–810.

  • Shi, X., Z. Gao, L. Lausen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W.-C. Woo, 2017: Deep learning for precipitation nowcasting: A benchmark and a new model. Adv. Neural Inf. Process. Syst., 30, 56175627.

    • Search Google Scholar
    • Export Citation
  • Sutskever, I., O. Vinyals, and Q. V. Le, 2014: Sequence to sequence learning with neural networks. 28th Conf. on Neural Information Processing Systems (NIPS), Montréal, QC, Canada, NIPS Organizing Committee, https://proceedings.neurips.cc/paper/2014/hash/a14ac55a4f27472c5d894ec1c3c743d2-Abstract.html.

  • Tan, C., F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, 2018: A survey on deep transfer learning. Artificial Neural Networks and Machine Learning—ICANN 2018: Lecture Notes in Computer Science, Vol. 11141, Springer, https://doi.org/10.1007/978-3-030-01424-7_27.

  • Yao, Z., Y. Wang, M. Long, and J. Wang, 2020: Unsupervised transfer learning for spatiotemporal predictive networks. Int. Conf. on Machine Learning (ICML), online, PMLR, https://icml.cc/virtual/2020/poster/6100.

All Time Past Year Past 30 Days
Abstract Views 425 0 0
Full Text Views 650 480 63
PDF Downloads 465 245 60