Research map / Probabilistic and scientific modeling / Differential equations and PDEs
FuXi-RTM: A Physics-Guided Prediction Framework with Radiative Transfer Modeling
Qiusheng Huang, Xiaohui Zhong, Xu Fan, Hao Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add DLRTM radiative flux regularization | FuXi-base · ERA5 3320 var-lead combos | fraction of combos improved: 88.51% of combinations improved | Improved |
| add DLRTM radiative flux regularization | FuXi-base · ERA5, CC | fraction of leads improved: 95.38% | Improved |
| add DLRTM radiative flux regularization | FuXi-base · ERA5, FAL | nRMSE: exceeding 7% | Improved |
| add DLRTM regularization | FuXi-base · ERA5, Q50 | RMSE: 0.1735 -> 0.1546 | Improved |
| add DLRTM regularization | FuXi-base · ERA5, TP | RMSE: 2.4127 -> 2.4092 | Improved |
| add DLRTM regularization | FuXi-base · ERA5, Q at 1000 hPa | RMSE: trails for up to 1.25 days | Mixed |
| add sunlit region-centered sampling instead of global random sampling (ablation) | FuXi-RTM · ERA5, Q50 | RMSE: 0.1857 -> 0.1546 | Improved |
| add sunlit region-centered sampling instead of global random sampling (ablation) | FuXi-RTM · ERA5, FAL | RMSE: 0.02515 -> 0.02300 | Improved |
| supervise only surface SW fluxes instead of all 13 levels SW+LW (ablation) | FuXi-RTM · ERA5, Q50 | RMSE: 0.1697 -> 0.1546 | Improved |
| supervise only surface SW fluxes instead of all 13 levels SW (ablation) | FuXi-RTM · ERA5, TTR | RMSE: 158.4191 -> 158.1290 | Improved |
| supervise raw SW fluxes instead of net surface SW (GSW) (ablation) | FuXi-RTM · ERA5, Q500 | RMSE: 0.7567 -> 0.7388 | Improved |
| supervise raw SW fluxes instead of ISSRD (ablation) | FuXi-RTM · ERA5, Q50 | RMSE: 0.1741 -> 0.1546 | Improved |
Closest papers by meaning
- HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting (ICLR 2025 · similarity 0.83)
- Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling (NeurIPS 2024 · similarity 0.83)
- ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction (NeurIPS 2024 · similarity 0.83)
- Probablistic Emulation of a Global Climate Model with Spherical DYffusion (NeurIPS 2024 · similarity 0.82)
- PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows (ICLR 2025 · similarity 0.82)
- Data-driven Precipitation Nowcasting Using Satellite Imagery (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
