Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 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

Deterministic Guidance Diffusion Model for Probabilistic Weather Forecasting (2312.02819v1)

Published 5 Dec 2023 in cs.CV

Abstract: Weather forecasting requires not only accuracy but also the ability to perform probabilistic prediction. However, deterministic weather forecasting methods do not support probabilistic predictions, and conversely, probabilistic models tend to be less accurate. To address these challenges, in this paper, we introduce the \textbf{\textit{D}}eterministic \textbf{\textit{G}}uidance \textbf{\textit{D}}iffusion \textbf{\textit{M}}odel (DGDM) for probabilistic weather forecasting, integrating benefits of both deterministic and probabilistic approaches. During the forward process, both the deterministic and probabilistic models are trained end-to-end. In the reverse process, weather forecasting leverages the predicted result from the deterministic model, using as an intermediate starting point for the probabilistic model. By fusing deterministic models with probabilistic models in this manner, DGDM is capable of providing accurate forecasts while also offering probabilistic predictions. To evaluate DGDM, we assess it on the global weather forecasting dataset (WeatherBench) and the common video frame prediction benchmark (Moving MNIST). We also introduce and evaluate the Pacific Northwest Windstorm (PNW)-Typhoon weather satellite dataset to verify the effectiveness of DGDM in high-resolution regional forecasting. As a result of our experiments, DGDM achieves state-of-the-art results not only in global forecasting but also in regional forecasting. The code is available at: \url{https://github.com/DongGeun-Yoon/DGDM}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Rainnetv1.0: a convolutional neural network for radar-based precipitation nowcasting. Geoscientific Model Development, 13(6):2631–2644, 2020.
  2. Stochastic variational video prediction. arXiv preprint arXiv:1710.11252, 2017.
  3. Accurate medium-range global weather forecasting with 3d neural networks. Nature, 619(7970):533–538, 2023.
  4. Parameterization of Subgrid-Scale Processes, page 342–398. Cambridge University Press, 2017.
  5. Unified modeling and prediction of weather and climate: A 25-year journey. Bulletin of the American Meteorological Society, 93(12):1865–1877, 2012.
  6. Forecastnet: a time-variant deep feed-forward neural network architecture for multi-step-ahead time-series forecasting. In NeurIPS, pages 579–591. Springer, 2020.
  7. The era-interim reanalysis: Configuration and performance of the data assimilation system. Quarterly Journal of the royal meteorological society, 137(656):553–597, 2011.
  8. Pedestrian detection: A benchmark. In CVPR, pages 304–311, 2009.
  9. Prediff: Precipitation nowcasting with latent diffusion models. arXiv preprint arXiv:2307.10422, 2023.
  10. Simvp: Simpler yet better video prediction. In CVPR, pages 3170–3180, 2022.
  11. Weather4cast at neurips 2022: Super-resolution rain movie prediction under spatio-temporal shifts. In NeurIPS 2022 Competition Track, pages 292–313. PMLR, 2022.
  12. Disentangling physical dynamics from unknown factors for unsupervised video prediction. In CVPR, pages 11474–11484, 2020.
  13. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415, 2016.
  14. Denoising diffusion probabilistic models. NeurIPS, 33:6840–6851, 2020.
  15. Video diffusion models. arXiv:2204.03458, 2022.
  16. Diffusion models for video prediction and infilling. Transactions on Machine Learning Research, 2022.
  17. A dynamic multi-scale voxel flow network for video prediction. In CVPR, pages 6121–6131, 2023.
  18. Human3.6m: Large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE TPAMI, 36(7):1325–1339, 2013.
  19. Effects of model resolution and subgrid-scale physics on the simulation of precipitation in the continental united states. Climate Dynamics, 23:243–258, 2004.
  20. Graphcast: Learning skillful medium-range global weather forecasting. arXiv preprint arXiv:2212.12794, 2022.
  21. Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification. arXiv preprint arXiv:2304.12891, 2023.
  22. Bbdm: Image-to-image translation with brownian bridge diffusion models. In CVPR, pages 1952–1961, 2023.
  23. Transformation-based adversarial video prediction on large-scale data. arXiv preprint arXiv:2003.04035, 2020.
  24. Mimo is all you need: a strong multi-in-multi-out baseline for video prediction. In AAAI, volume 37, pages 1975–1983, 2023.
  25. Latent video transformer. arXiv preprint arXiv:2006.10704, 2020.
  26. Weatherbench: a benchmark data set for data-driven weather forecasting. Journal of Advances in Modeling Earth Systems, 12(11):e2020MS002203, 2020.
  27. Skilful precipitation nowcasting using deep generative models of radar. Nature, 597(7878):672–677, 2021.
  28. High-resolution image synthesis with latent diffusion models. In CVPR, pages 10684–10695, 2022.
  29. Simple baseline for weather forecasting using spatiotemporal context aggregation network. arXiv preprint arXiv:2212.02952, 2022.
  30. Implicit stacked autoregressive model for video prediction. arXiv preprint arXiv:2303.07849, 2023.
  31. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In CVPR, pages 1874–1883, 2016.
  32. Convolutional lstm network: A machine learning approach for precipitation nowcasting. NeurIPS, 28, 2015.
  33. Unsupervised learning of video representations using lstms. In International conference on machine learning, pages 843–852. PMLR, 2015.
  34. Temporal attention unit: Towards efficient spatiotemporal predictive learning. In CVPR, pages 18770–18782, 2023.
  35. Openstl: A comprehensive benchmark of spatio-temporal predictive learning. In Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2023.
  36. Smaat-unet: Precipitation nowcasting using a small attention-unet architecture. Pattern Recognition Letters, 145:178–186, 2021.
  37. Mcvd-masked conditional video diffusion for prediction, generation, and interpolation. NeurIPS, 35:23371–23385, 2022.
  38. Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In International Conference on Machine Learning, pages 5123–5132. PMLR, 2018.
  39. Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms. NeurIPS, 30, 2017.
  40. Memory in memory: A predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics. In CVPR, pages 9154–9162, 2019.
  41. Image quality assessment: from error visibility to structural similarity. IEEE TIP, 13(4):600–612, 2004.
  42. Deep spatio-temporal residual networks for citywide crowd flows prediction. In AAAI, volume 31, 2017.
  43. Mmvp: Motion-matrix-based video prediction. In ICCV, pages 4273–4283, 2023.
Citations (4)
View on Semantic Scholar

Summary

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

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