Research map / Probabilistic and scientific modeling / Dynamical systems
Learning to Assimilate in Chaotic Dynamical Systems
Michael McCabe, Jed Brown
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 MC Dropout to the ensemble analysis network (vs deterministic network) (ablation) | AmEnF · Lorenz 96, sigma=1, m=10 | ensemble variance / collapse | Improved |
| train with self-supervised analysis loss instead of supervised analysis loss (ablation) | AmEnF · Lorenz 96 fully observed, sigma=1 | analysis RMSE | Hurt |
| train with self-supervised forecast loss instead of supervised analysis loss (ablation) | AmEnF · Lorenz 96 fully observed, sigma=1 | analysis RMSE | No clear effect |
| AmEnF vs 4D-Var, LETKF, iEnKS at small ensemble sizes and high noise | AmEnF · Lorenz 96 and VL20, partial observation | time-averaged RMSE | Improved |
| AmEnF vs standard assimilation methods on Kuramoto-Shivashinsky | AmEnF · Kuramoto-Shivashinsky | time-averaged RMSE | No clear effect |
| include an ensemble-based prior term in the amortized objective (ablation) | AmEnF · earlier iteration (unspecified) | performance | Hurt |
Closest papers by meaning
- Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos (ICML 2025 · similarity 0.85)
- Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series (ICLR 2025 · similarity 0.85)
- The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling (NeurIPS 2026 · similarity 0.85)
- Compositional simulation-based inference for time series (ICLR 2025 · similarity 0.84)
- Chaos Meets Attention: Transformers for Large-Scale Dynamical Prediction (ICML 2025 · similarity 0.84)
- Learning semilinear neural operators: A unified recursive framework for prediction and data assimilation. (ICLR 2024 · 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.
