Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Extreme Precipitation Nowcasting using Transformer-based Generative Models (2403.03929v1)

Published 6 Mar 2024 in cs.LG and cs.AI

Abstract: This paper presents an innovative approach to extreme precipitation nowcasting by employing Transformer-based generative models, namely NowcastingGPT with Extreme Value Loss (EVL) regularization. Leveraging a comprehensive dataset from the Royal Netherlands Meteorological Institute (KNMI), our study focuses on predicting short-term precipitation with high accuracy. We introduce a novel method for computing EVL without assuming fixed extreme representations, addressing the limitations of current models in capturing extreme weather events. We present both qualitative and quantitative analyses, demonstrating the superior performance of the proposed NowcastingGPT-EVL in generating accurate precipitation forecasts, especially when dealing with extreme precipitation events. The code is available at \url{https://github.com/Cmeo97/NowcastingGPT}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Global projections of river flood risk in a warmer world. Earth’s Future, 5, 2017. URL https://api.semanticscholar.org/CorpusID:42772267.
  2. Rainformer: Features extraction balanced network for radar-based precipitation nowcasting. IEEE Geoscience and Remote Sensing Letters, 19:1–5, 2022. URL https://api.semanticscholar.org/CorpusID:248132089.
  3. Nowcasting of extreme precipitation using deep generative models. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.  1–5, 2023. doi: 10.1109/ICASSP49357.2023.10094988.
  4. Maskgit: Masked generative image transformer. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2022.
  5. Meta-transfer-learning for time series data with extreme events: An application to water temperature prediction. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, New York, NY, USA, October 2023. ACM.
  6. Stuart Coles. An introduction to statistical modeling of extreme values. Springer Series in Statistics. Springer-Verlag, 2001. ISBN 1-85233-459-2.
  7. Autonowp: An approach using deep autoencoders for precipitation nowcasting based on weather radar reflectivity prediction. Mathematics, 2021. URL https://api.semanticscholar.org/CorpusID:238018677.
  8. Extreme Value Theory. Springer Series in Operations Research and Financial Engineering. Springer Science+Business Media, January 2006.
  9. Modeling extreme events in time series prediction. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’19, pp.  1114–1122, New York, NY, USA, 2019. Association for Computing Machinery. ISBN 9781450362016. doi: 10.1145/3292500.3330896. URL https://doi.org/10.1145/3292500.3330896.
  10. Taming transformers for high-resolution image synthesis. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.  12873–12883, 2021.
  11. Extreme value theory and Value-at-Risk: Relative performance in emerging markets. Int. J. Forecast., 20(2):287–303, April 2004.
  12. Generative adversarial nets. Advances in neural information processing systems, 27, 2014.
  13. Spatial and temporal evaluation of radar rainfall nowcasting techniques on 1,533 events. Water Resources Research, 56(8):e2019WR026723, 2020.
  14. Preformer: Simple and efficient design for precipitation nowcasting with transformers. IEEE Geoscience and Remote Sensing Letters, 21:1–5, 2024. doi: 10.1109/LGRS.2023.3325628.
  15. Ms-nowcasting: Operational precipitation nowcasting with convolutional lstms at microsoft weather. ArXiv, abs/2111.09954, 2021. URL https://api.semanticscholar.org/CorpusID:244463010.
  16. A spatiotemporal deep learning model st-lstm-sa for hourly rainfall forecasting using radar echo images. Journal of Hydrology, 2022. URL https://api.semanticscholar.org/CorpusID:247602986.
  17. Predrann: The spatiotemporal attention convolution recurrent neural network for precipitation nowcasting. Knowl. Based Syst., 239:107900, 2021. URL https://api.semanticscholar.org/CorpusID:245591327.
  18. A concept of nowcasting of convective precipitation using an x-band radar for the territory of the zlín region (czech republic). In Computer Science On-line Conference, pp.  499–514. Springer, 2022.
  19. Overview of observed clausius-clapeyron scaling of extreme precipitation in midlatitudes. Atmosphere, 11(8):786, 2020.
  20. A review of radar-based nowcasting of precipitation and applicable machine learning techniques. arXiv preprint arXiv:2005.04988, 2020.
  21. Pysteps: An open-source python library for probabilistic precipitation nowcasting (v1. 0). Geoscientific Model Development, 12(10):4185–4219, 2019.
  22. Skilful precipitation nowcasting using deep generative models of radar. Nature, 597(7878):672–677, 2021.
  23. Convolutional lstm network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems, 28, 2015.
  24. R Sluiter. Interpolation methods for the climate atlas. KNMI De Bilt, The Netherlands, 2012. URL https://cdn.knmi.nl/knmi/pdf/bibliotheek/knmipubTR/TR335.pdf.
  25. Smaat-unet: Precipitation nowcasting using a small attention-unet architecture. Pattern Recognition Letters, 145:178–186, 2021.
  26. Neural discrete representation learning. Advances in neural information processing systems, 30, 2017.
  27. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  28. Sevir : A storm event imagery dataset for deep learning applications in radar and satellite meteorology. In Neural Information Processing Systems, 2020a. URL https://api.semanticscholar.org/CorpusID:227222587.
  29. Sevir : A storm event imagery dataset for deep learning applications in radar and satellite meteorology. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (eds.), Advances in Neural Information Processing Systems, volume 33, pp.  22009–22019. Curran Associates, Inc., 2020b. URL https://proceedings.neurips.cc/paper_files/paper/2020/file/fa78a16157fed00d7a80515818432169-Paper.pdf.
  30. Nüwa: Visual synthesis pre-training for neural visual world creation. In European conference on computer vision, pp.  720–736. Springer, 2022.
  31. Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157, 2021.
  32. Temporally consistent transformers for video generation. arXiv preprint arXiv:2210.02396, 2022.
  33. Aa-transunet: Attention augmented transunet for nowcasting tasks. 2022 International Joint Conference on Neural Networks (IJCNN), pp.  01–08, 2022. URL https://api.semanticscholar.org/CorpusID:246705912.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets