Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 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

DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting (2312.06734v2)

Published 11 Dec 2023 in cs.CV

Abstract: Precipitation nowcasting is an important spatio-temporal prediction task to predict the radar echoes sequences based on current observations, which can serve both meteorological science and smart city applications. Due to the chaotic evolution nature of the precipitation systems, it is a very challenging problem. Previous studies address the problem either from the perspectives of deterministic modeling or probabilistic modeling. However, their predictions suffer from the blurry, high-value echoes fading away and position inaccurate issues. The root reason of these issues is that the chaotic evolutionary precipitation systems are not appropriately modeled. Inspired by the nature of the systems, we propose to decompose and model them from the perspective of global deterministic motion and local stochastic variations with residual mechanism. A unified and flexible framework that can equip any type of spatio-temporal models is proposed based on residual diffusion, which effectively tackles the shortcomings of previous methods. Extensive experimental results on four publicly available radar datasets demonstrate the effectiveness and superiority of the proposed framework, compared to state-of-the-art techniques. Our code is publicly available at https://github.com/DeminYu98/DiffCast.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Stochastic variational video prediction. In International Conference on Learning Representations, 2018.
  2. Rainformer: Features extraction balanced network for radar-based precipitation nowcasting. IEEE Geoscience and Remote Sensing Letters, 19:1–5, 2022.
  3. Mau: A motion-aware unit for video prediction and beyond. Advances in Neural Information Processing Systems, 34:26950–26962, 2021.
  4. Strpm: A spatiotemporal residual predictive model for high-resolution video prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13946–13955, 2022.
  5. A deep learning-based methodology for precipitation nowcasting with radar. Earth and Space Science, 7(2):e2019EA000812, 2020.
  6. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34:8780–8794, 2021.
  7. Stochastic latent residual video prediction. In International Conference on Machine Learning, pages 3233–3246. PMLR, 2020.
  8. Earthformer: Exploring space-time transformers for earth system forecasting. Advances in Neural Information Processing Systems, 35:25390–25403, 2022a.
  9. Simvp: Simpler yet better video prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3170–3180, 2022b.
  10. Prediff: Precipitation nowcasting with latent diffusion models. arXiv preprint arXiv:2307.10422, 2023.
  11. Disentangling physical dynamics from unknown factors for unsupervised video prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11474–11484, 2020.
  12. Flexible diffusion modeling of long videos. Advances in Neural Information Processing Systems, 35:27953–27965, 2022.
  13. Diffusion models for high-resolution solar forecasts. arXiv preprint arXiv:2302.00170, 2023.
  14. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020.
  15. Diffusion models for video prediction and infilling. Transactions on Machine Learning Research, 2022.
  16. Motiondiffuser: Controllable multi-agent motion prediction using diffusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9644–9653, 2023.
  17. Meteonet, an open reference weather dataset, 2020.
  18. Stochastic adversarial video prediction. arXiv preprint arXiv:1804.01523, 2018.
  19. Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification. arXiv preprint arXiv:2304.12891, 2023.
  20. Experimental study on generative adversarial network for precipitation nowcasting. IEEE Transactions on Geoscience and Remote Sensing, 60:1–20, 2022a.
  21. The reconstitution predictive network for precipitation nowcasting. Neurocomputing, 507:1–15, 2022b.
  22. Vidm: Video implicit diffusion models. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 9117–9125, 2023.
  23. Mimo is all you need: a strong multi-in-multi-out baseline for video prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1975–1983, 2023.
  24. Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting. In International Conference on Machine Learning, pages 8857–8868. PMLR, 2021.
  25. Skilful precipitation nowcasting using deep generative models of radar. Nature, 597(7878):672–677, 2021.
  26. Convolutional lstm network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems, 28, 2015.
  27. Deep learning for precipitation nowcasting: A benchmark and a new model. Advances in neural information processing systems, 30, 2017.
  28. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, pages 2256–2265. PMLR, 2015.
  29. Denoising diffusion implicit models. In International Conference on Learning Representations, 2020.
  30. Temporal attention unit: Towards efficient spatiotemporal predictive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18770–18782, 2023a.
  31. Openstl: A comprehensive benchmark of spatio-temporal predictive learning. In Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2023b.
  32. Mocogan: Decomposing motion and content for video generation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1526–1535, 2018.
  33. Sevir: A storm event imagery dataset for deep learning applications in radar and satellite meteorology. Advances in Neural Information Processing Systems, 33:22009–22019, 2020.
  34. Mcvd-masked conditional video diffusion for prediction, generation, and interpolation. Advances in Neural Information Processing Systems, 35:23371–23385, 2022.
  35. Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms. Advances in neural information processing systems, 30, 2017.
  36. Motionrnn: A flexible model for video prediction with spacetime-varying motions. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15435–15444, 2021.
  37. Video probabilistic diffusion models in projected latent space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18456–18466, 2023.
  38. Skilful nowcasting of extreme precipitation with nowcastnet. Nature, 619(7970):526–532, 2023.
Citations (14)
View on Semantic Scholar

Summary

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

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