Research map / Probabilistic and scientific modeling / Dynamical systems
RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs
Yeeun Seong, Doyi Kim, Minseok Seo, Changick Kim
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 stochastic source modeling (Brownian Bridge) to Latent ODE (ablation) | RainODE · RAPID-60min | CSI-219: 0.002 -> 0.056 | Improved |
| add SSM to Latent ODE (ablation) | RainODE · RAPID-60min | CSI-M: 0.152 -> 0.220 | Improved |
| add SSM to Latent ODE (ablation) | RainODE · RAPID-60min | LPIPS: 0.376 -> 0.275 | Improved |
| add SSM to Latent ODE (ablation) | RainODE · RAPID-60min | RMSE: 0.101 -> 0.113 | Hurt |
| add SSM to Latent ODE (ablation) | RainODE · RAPID-60min | CSI-16: 0.404 -> 0.400 | Hurt |
| replace SimVP discrete output with Latent ODE (ablation) | SimVP · RAPID-60min | RMSE: 0.107 -> 0.101 | Improved |
| replace SimVP discrete output with Latent ODE (ablation) | SimVP · RAPID-60min | CSI-219: 0.011 -> 0.002 | No clear effect |
| use RainODE instead of discrete baselines | RainODE · RAPID-60min | CSI-M (P4): 0.172 -> 0.270 vs exPreCast | Improved |
| use RainODE instead of baselines | RainODE · SEVIR | CSI-M (P4): 0.452 -> 0.464 vs exPreCast | Improved |
| use RainODE on RAPID-10min | RainODE · RAPID-10min | CSI-16: 0.682 -> 0.618 vs 3D U-Net | Hurt |
| Latent ODE with longer outputs | Latent ODE · Compute | parameters: 9.32 -> 9.32 params, 68.84 -> 104.97 GFLOPs | Improved |
Closest papers by meaning
- Data-driven Precipitation Nowcasting Using Satellite Imagery (AAAI 2025 · similarity 0.87)
- Integrating Multi-Source Data for Long Sequence Precipitation Forecasting (AAAI 2025 · similarity 0.87)
- AlphaPre: Amplitude-Phase Disentanglement Model for Precipitation Nowcasting (CVPR 2025 · similarity 0.87)
- DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting (CVPR 2024 · similarity 0.87)
- Perceptually Constrained Precipitation Nowcasting Model (ICML 2025 · similarity 0.86)
- ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs (ICLR 2024 · similarity 0.86)
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.
