masf / README.md
eunbii1's picture
update
bb9b5c1 verified
|
Raw History Blame Contribute Delete
2.18 kB
metadata
tags:
  - data-assimilation
  - score-based-model
  - diffusion
  - pytorch

MASF checkpoints

Pretrained score models for MASF: Measurement-Aware Score-based Filter, from Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions.

Code: https://github.com/tcnllab-oss/masf · Data: eunbii1/masf

Files

file system measurement config
checkpoints/kolmogorov_128/grid_mask.pt Kolmogorov flow 128×128 grid mask (stride 10) configs/kolmogorov_128/grid_mask.yaml
checkpoints/kolmogorov_128/center_mask.pt Kolmogorov flow 128×128 center mask (hole ratio 0.5) configs/kolmogorov_128/center_mask.yaml
checkpoints/kolmogorov_128/speed.pt Kolmogorov flow 128×128 speed configs/kolmogorov_128/speed.yaml
checkpoints/kolmogorov_256/grid_mask.pt Kolmogorov flow 256×256 grid mask (stride 15) configs/kolmogorov_256/grid_mask.yaml
checkpoints/kolmogorov_512/grid_mask.pt Kolmogorov flow 512×512 grid mask (stride 20) configs/kolmogorov_512/grid_mask.yaml
checkpoints/lorenz96/cubic.pt Lorenz96 (dim 40, F=8) cubic configs/lorenz96/cubic.yaml

Each checkpoint is pretrained on the 1000 prior states in the dataset repo. The model architecture is defined by the matching config in the code repo. During filtering, the model is fine-tuned online at every measurement step.

Usage

git clone https://github.com/tcnllab-oss/masf && cd masf
hf download eunbii1/masf --include "checkpoints/*" --local-dir .
hf download eunbii1/masf --repo-type dataset --include "datasets/*" --local-dir .
python main.py -d kolmogorov_128 --measurement_type grid_mask --seed 42

Files land in checkpoints/ and datasets/, where the configs expect them. See notebooks/ for examples.

Citation

@article{yoon2026masf,
  title={Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions},
  author={Yoon, Eunbi and Chang, Won and Kim, Donghan and Kim, Dae Wook},
  journal={arXiv preprint},
  year={2026}
}