ML Anthology

Generating Observation Guided Ensembles for Data Assimilation with Denoising Diffusion Probabilistic Model

Yuuichi Asahi, Yuta Hasegawa, Naoyuki Onodera, Takashi Shimokawabe, Hayato Shiba, Yasuhiro Idomura
ICMLW 2023
/icmlw/2023/asahi2023icmlw-generating/

Abstract

This paper presents an ensemble data assimilation method using the pseudo ensembles generated by denoising diffusion probabilistic model. Since the model is trained against noisy and sparse observation data, this model can produce divergent ensembles consistent with observations. Thanks to the variance in generated ensembles, our proposed method displays better performance than the well-established ensemble data assimilation method when the simulation model is imperfect.

PDF ICMLW OpenReview Semantic Scholar

Cite

Text

Asahi et al. "Generating Observation Guided Ensembles for Data Assimilation with Denoising Diffusion Probabilistic Model." ICML 2023 Workshops: SynS_and_ML, 2023.

Markdown

[Asahi et al. "Generating Observation Guided Ensembles for Data Assimilation with Denoising Diffusion Probabilistic Model." ICML 2023 Workshops: SynS_and_ML, 2023.](https://mlanthology.org/icmlw/2023/asahi2023icmlw-generating/)

BibTeX

@inproceedings{asahi2023icmlw-generating,
  title     = {{Generating Observation Guided Ensembles for Data Assimilation with Denoising Diffusion Probabilistic Model}},
  author    = {Asahi, Yuuichi and Hasegawa, Yuta and Onodera, Naoyuki and Shimokawabe, Takashi and Shiba, Hayato and Idomura, Yasuhiro},
  booktitle = {ICML 2023 Workshops: SynS_and_ML},
  year      = {2023},
  url       = {https://mlanthology.org/icmlw/2023/asahi2023icmlw-generating/}
}