Research map / Probabilistic and scientific modeling / Molecules and proteins
ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models
Salva Rühling Cachay, Venkatesh Ramesh, Jason N. S. Cole, Howard Barker, David Rolnick
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 1D CNN instead of MLP | MLP · ClimART pristine-sky, vertical avg. | RMSE: 0.701 -> 0.303 | Improved |
| use GraphNet instead of MLP | MLP · ClimART pristine-sky, vertical avg. | RMSE: 0.701 -> 0.648 | Improved |
| use GraphNet instead of MLP for bias | MLP · ClimART pristine-sky, vertical avg. | MBE: -0.160 -> -0.001 | Improved |
| use GCN with line-graph instead of MLP | MLP · ClimART pristine-sky, vertical avg. | RMSE: 0.701 -> 1.209 | Hurt |
| learn the adjacency matrix (L-GCN) instead of fixed line graph | GCN · ClimART pristine-sky, vertical avg. | RMSE: 1.209 -> 0.878 | Improved |
| learn the adjacency matrix (L-GCN) instead of fixed line graph | GCN · ClimART pristine-sky, TOA | RMSE: 0.815 -> 0.440 | Improved |
| run models on GPU instead of 4 CPUs | MLP · ClimART speed | inference time (s): 0.1643 -> 0.0016 | Improved |
| run models on GPU instead of 4 CPUs | GraphNet · ClimART speed | inference time (s): 28.1253 -> 0.1659 | Improved |
| use MLP on GPU instead of physics-based RT (64 CPUs) | Physics-RT · ClimART speed | inference time (s): 1.9817 -> 0.0016 | Improved |
| increase number of CPUs for physics RT from 2 to 64 | Physics-RT · ClimART speed | inference time (s): 3.3919 -> 1.9817 | Improved |
| increase batch size from 512 to 8192 | ML models · ClimART speed | inference throughput: 3.5x | Improved |
| test on future climate conditions instead of present-day | MLP · ClimART OOD | RMSE: 1 -> 100 | Hurt |
Closest papers by meaning
- ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs (ICLR 2024 · similarity 0.88)
- ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction (NeurIPS 2024 · similarity 0.87)
- Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet (NeurIPS 2026 · similarity 0.86)
- Probablistic Emulation of a Global Climate Model with Spherical DYffusion (NeurIPS 2024 · similarity 0.86)
- AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science (NeurIPS 2025 · similarity 0.85)
- Causal Climate Emulation with Bayesian Filtering (NeurIPS 2025 · similarity 0.84)
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.
