Research map / Time series / Causal and generative time series
Adaptable Regression Method for Ensemble Consensus Forecasting
John Williams, Peter Neilley, Joseph Koval, Jeff McDonald
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 bias modulation (AR000 to AR100) (ablation) | adaptable regression · temperature consensus, total RMSE | relative RMSE (% of EW): 96.7 -> 96.4 | Improved |
| add regularization (AR000 to AR010) (ablation) | adaptable regression · temperature consensus, total RMSE | relative RMSE (% of EW): 96.7 -> 96.1 | Improved |
| add covariance aggregation (AR000 to AR001) (ablation) | adaptable regression · temperature consensus, total RMSE | relative RMSE (% of EW): 96.7 -> 94.7 | Improved |
| add all three (AR000 to AR111) (ablation) | adaptable regression · temperature consensus, total RMSE | relative RMSE (% of EW): 96.7 -> 94.3 | Improved |
| add regularization when covariance aggregation is already used (ablation) | AR111 · 4 lead times, RMSE sensitivity | RMSE: about 1% reduction without aggregation; 0.1% with aggregation | Mixed |
| AR111 vs DICast SGD | consensus method · temperature consensus, total RMSE | relative RMSE (% of EW): 97.3 -> 94.3 | Improved |
| bias-correct best input forecast (BF to BFB) | best input forecast · temperature, total RMSE | relative RMSE (% of EW): 128.6 -> 110.8 | Improved |
| average bias-corrected forecasts (BFB to EW) | input forecasts · temperature, total RMSE | relative RMSE (% of EW): 110.8 -> 100.0 | Improved |
| decrease bias modulation factor from 1.0 to 0.8 (ablation) | AR000 and AR111 · 4 lead times | RMSE: about 0.04% reduction | Improved |
Closest papers by meaning
- Continuous Ensemble Weather Forecasting with Diffusion models (ICLR 2025 · similarity 0.84)
- Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting (NeurIPS 2026 · similarity 0.82)
- Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks (NeurIPS 2024 · similarity 0.82)
- ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction (NeurIPS 2024 · similarity 0.81)
- Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective (NeurIPS 2024 · similarity 0.81)
- Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function (ICML 2025 · similarity 0.81)
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.
