Research map / Probabilistic and scientific modeling / Dynamical systems
LoPhyDA: Low-Rank Tensor and Physics Gradient Guided Diffusion for Atmospheric Data Assimilation
Danyang Peng, Yang Chen, Yunlong Zhou, Xiaotong Yuan
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 low-rank tensor completion prior and physics gradient guidance (ablation) | latent diffusion assimilation (LDA) · ERA5, 1% observations | MSE: 0.0415 -> 0.0336 | Improved |
| add geostrophic-balance physics gradient guidance only (ablation) | LDA · ERA5, 1% observations | MSE: 0.0415 -> 0.0388 | Improved |
| add low-rank tensor prior only (ablation) | LDA · ERA5, 1% observations | MSE: 0.0415 -> 0.0365 | Improved |
| add physics guidance on top of low-rank prior (ablation) | LDA-LoR · ERA5, 1% observations | WRMSE z500: 65.3315 -> 58.8376 | Improved |
| add physics guidance alone (ablation) | LDA · ERA5, 1% observations | WRMSE (second WRMSE column, t850): 1.4726 -> 1.4964 | No clear effect |
| use low-rank tensor completion instead of Kriging interpolation (ablation) | LoPhyDA · ERA5, 1% observations | MSE: 0.0391 -> 0.0336 | Improved |
| use low-rank tensor completion instead of learnable encoder (ablation) | LoPhyDA · ERA5, 1% observations | MSE: 0.0352 -> 0.0336 | Improved |
| LoPhyDA over best baseline AlignDA on real GDAS observations | LoPhyDA · GDAS real observations | MSE: 0.0413 -> 0.0385 | Improved |
| LoPhyDA over best baseline PhyDA on simulated 1% observations | LoPhyDA · ERA5, 1% observations | MAE: 0.1225 -> 0.1183 | Improved |
| LoPhyDA vs AlignDA on 15-day cyclic assimilation | LoPhyDA · ERA5 15-day cycling, fixed observation locations | RMSE | Improved |
Closest papers by meaning
- DiffDA: a Diffusion model for weather-scale Data Assimilation (ICML 2024 · similarity 0.91)
- FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation (NeurIPS 2025 · similarity 0.89)
- Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation (ICML 2025 · similarity 0.87)
- Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences (NeurIPS 2025 · similarity 0.86)
- Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution (CVPR 2025 · similarity 0.86)
- Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge (NeurIPS 2026 · similarity 0.86)
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.
