A collection of research papers on Diffusion Models for Weather Forecasting.
| Model | Paper | Topic | Publication | Date (↓) | Links |
|---|---|---|---|---|---|
| - | Diffusion Models for High-Resolution Solar Forecasts | Cloud Cover Forecasting | - | 2023.02 | [paper] |
| LDCast | Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification | Precipitation Nowcasting | - | 2023.04 | [paper] [code] |
| DiffESM | Conditional Emulation of Earth System Models with Diffusion Models | Emulation | ICLR 2023 Workshop | 2023.04 | [paper] [code] |
| SEEDS | Emulation of Weather Forecast Ensembles with Diffusion Models | Ensemble Forecast Emulation | Science Advances | 2023.06 | [paper] |
| DYffusion | A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting | Spatiotemporal Forecasting | NeurIPS 2024 | 2023.06 | [paper] [code] |
| SwinRDM | Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting | Global Weather Forecasting | AAAI 2023 | 2023.06 | [paper] |
| PreDiff | Precipitation Nowcasting with Latent Diffusion Models | Precipitation Nowcasting | NeurIPS 2023 | 2023.07 | [paper] [code] |
| GDE | Precipitation nowcasting with generative diffusion models | Precipitation Nowcasting | - | 2023.08 | [paper] [code] |
| CorrDiff | Residual Diffusion Modeling for Km-scale Atmospheric Downscaling | Downscaling | - | 2023.10 | [paper] |
| FuXi-Extreme | Improving extreme rainfall and wind forecasts with diffusion model | Global (Extreme) Weather Forecasting | - | 2023.10 | [paper] |
| OF-Diff | Probabilistic Precipitation Downscaling with Optical Flow-Guided Diffusion | Downscaling | - | 2023.11 | [paper] |
| GenCast | GenCast: Diffusion-based ensemble forecasting for medium-range weather | Global Weather Forecasting | - | 2023.12 | [paper] |
| DiffCast | A Unified Framework via Residual Diffusion for Precipitation Nowcasting | Precipitation Nowcasting | CVPR 2024 | 2023.12 | [paper] [code] |
| DGDM | Deterministic Guidance Diffusion Model for Probabilistic Weather Forecasting | Weather Forecasting using Satellite | - | 2023.12 | [paper] [code] |
| - | Advancing Realistic Precipitation Nowcasting With a Spatiotemporal Transformer-Based Denoising Diffusion Model | Precipitation Nowcasting | IEEE TGRS | 2024.01 | [paper] |
| DiffDA | A diffusion model for weather-scale data assimilation | Data Assimilation | - | 2024.01 | [paper] |
| LT3P | Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data | Tropical Cyclone Trajectory Forecasting | ICLR 2024 | 2024.01 | [paper] [code] |
| - | Wind speed super-resolution and validation: from ERA5 to CERRA via diffusion models | Super resolution | - | 2024.01 | [paper] [code] |
| ExtremeCast | Boosting Extreme Value Prediction for Global Weather Forecast | Global (Extreme) Weather Forecasting | - | 2024.02 | [paper] |
| CasCast | Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling | Precipitation Nowcasting | - | 2024.02 | [paper] |
| SDEdit-Weather | Weather Prediction with Diffusion Guided by Realistic Forecast Processes | Global Weather Forecasting | - | 2024.02 | [paper] |
| - | Physics-Informed Diffusion Model and Sampling for Global Weather Forecasting | Global Weather Forecasting | - | 2024.03 | [paper] |
| DiffObs | Generative Diffusion for Global Forecasting of Satellite Observations | Global Preciptation Forecasting | ICLR 2024 Workshop | 2024.04 | [paper] |
| - | Diffusion-Based Joint Temperature and Precipitation Emulation of Earth System Models | Emulation | ICLR 2024 Workshop | 2024.04 | [paper] |
| SLAMS | Deep Generative Data Assimilation in Multimodal Setting | Data Assimilation | - | 2024.04 | [paper] [code] |
| ClimateDiffuse | Generative Diffusion-based Downscaling for Climate | Downscaling | - | 2024.04 | [paper] [code] |
| CloudDiff | Super-resolution ensemble retrieval of cloud properties for all day using the generative diffusion model | Super-resolution | - | 2024.05 | [paper] |
| - | - | - | - | 2024.00 | [paper] [code] |