Research map / Probabilistic and scientific modeling / Molecules and proteins
ENS-10: A Dataset For Post-Processing Ensemble Weather Forecasts
Saleh Ashkboos, Langwen Huang, Nikoli Dryden, Tal Ben-Nun, Peter Dominik Dueben, Lukas Gianinazzi, Luca Nicola Kummer, Torsten Hoefler
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 ten instead of five ensemble members for Transformer | Transformer · ENS-10 test | Z500 CRPS: 77.30 -> 74.79 | Improved |
| Use ten instead of five ensemble members for LeNet | LeNet · ENS-10 test | Z500 CRPS: 75.56 -> 74.41 | Improved |
| Use ten instead of five ensemble members for EMOS | EMOS · ENS-10 test | Z500 CRPS: 79.08 -> 81.74 | Hurt |
| Use ten instead of five ensemble members for Transformer | Transformer · ENS-10 test | T2m CRPS: 0.649 -> 0.626 | Improved |
| Use ten instead of five ensemble members for EMOS | EMOS · ENS-10 test | T2m CRPS: 0.718 -> 0.749 | Hurt |
| Learned post-processing (Transformer) vs raw ensemble | Transformer · ENS-10 test | T2m CRPS, 10-ENS: 0.733 -> 0.626 | Improved |
| LeNet-style model vs Transformer on Z500 | LeNet · ENS-10 test | Z500 CRPS, 10-ENS: 74.79 -> 74.41 | Improved |
| Transformer vs LeNet on T850 | Transformer · ENS-10 test | T850 CRPS, 10-ENS: 0.674 -> 0.665 | Improved |
| Learned MLP vs raw ensemble | MLP · ENS-10 test | T850 CRPS, 10-ENS: 0.719 -> 0.684 | Improved |
| EECRPS: Transformer vs raw on T2m, 10-ENS | Transformer · ENS-10 test | T2m EECRPS: 0.25 -> 0.214 | Improved |
Closest papers by meaning
- EWMoE: An Effective Model for Global Weather Forecasting with Mixture-of-Experts (AAAI 2025 · similarity 0.86)
- ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction (NeurIPS 2024 · similarity 0.85)
- DiffDA: a Diffusion model for weather-scale Data Assimilation (ICML 2024 · similarity 0.85)
- Continuous Ensemble Weather Forecasting with Diffusion models (ICLR 2025 · similarity 0.85)
- Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks (NeurIPS 2024 · similarity 0.85)
- Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting (NeurIPS 2026 · 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.
