Research map / Bandits and online learning / Online convex optimization and games
ClimSim-Online: A Large Multi-Scale Dataset and Framework for Hybrid Physics-ML Climate Emulation
Sungduk Yu, Zeyuan Hu, Akshay Subramaniam, Walter Hannah, Liran Peng, Jerry Lin, Mohamed Aziz Bhouri, Ritwik Gupta, Björn Lütjens, Justus C. Will, Gunnar Behrens, Julius J. M. Busecke and 35 more
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 |
|---|---|---|---|
| use MLP instead of CNN | offline emulator · ClimSim offline, NETSW | RMSE (W/m^2): 36.91 -> 26.71 | Improved |
| use CNN instead of MLP | offline emulator · ClimSim offline, dT/dt | RMSE (W/m^2): 4.421 -> 4.369 | Improved |
| use RPN instead of cVAE for probabilistic prediction | stochastic baseline · ClimSim offline, dT/dt | CRPS (W/m^2): 2.708 -> 2.305 | Improved |
| use HSR instead of cVAE for probabilistic prediction | stochastic baseline · ClimSim offline, dq/dt | CRPS (W/m^2): 4.565 -> 3.645 | Improved |
| use U-Net with expanded inputs (large-scale forcing, convection memory) and cloud physics constraints instead of baseline MLP | hybrid E3SM-MMF online simulation · 1-year hybrid simulation stability | stability / online error: MLP runs crashed within 2 months; U-Net ran stably for years | Improved |
| add cloud physics constraints (liquid-ice partition, tropopause cloud cap) | U-Net emulator · hybrid E3SM-MMF online simulation | online stability | Improved |
| improve offline skill | hybrid climate emulator · online error | online error | Mixed |
Closest papers by meaning
- ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction (NeurIPS 2024 · similarity 0.83)
- AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science (NeurIPS 2025 · similarity 0.82)
- ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs (ICLR 2024 · similarity 0.81)
- Probablistic Emulation of a Global Climate Model with Spherical DYffusion (NeurIPS 2024 · similarity 0.81)
- Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models (NeurIPS 2024 · similarity 0.81)
- OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting (NeurIPS 2026 · similarity 0.80)
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.
