State-observation augmented diffusion model for nonlinear assimilation with unknown dynamics
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912491359961088 |
|---|---|
| author | Li, Zhuoyuan Dong, Bin Zhang, Pingwen |
| author_facet | Li, Zhuoyuan Dong, Bin Zhang, Pingwen |
| contents | Data assimilation has become a key technique for combining physical models with observational data to estimate state variables. However, classical assimilation algorithms often struggle with the high nonlinearity present in both physical and observational models. To address this challenge, a novel generative model, termed the State-Observation Augmented Diffusion (SOAD) model is proposed for data-driven assimilation. The marginal posterior associated with SOAD has been derived and then proved to match the true posterior distribution under mild assumptions, suggesting its theoretical advantages over previous score-based approaches. Experimental results also indicate that SOAD may offer improved performance compared to existing data-driven methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21314 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | State-observation augmented diffusion model for nonlinear assimilation with unknown dynamics Li, Zhuoyuan Dong, Bin Zhang, Pingwen Machine Learning 49N45, 60J60, 62F15, 68T20 Data assimilation has become a key technique for combining physical models with observational data to estimate state variables. However, classical assimilation algorithms often struggle with the high nonlinearity present in both physical and observational models. To address this challenge, a novel generative model, termed the State-Observation Augmented Diffusion (SOAD) model is proposed for data-driven assimilation. The marginal posterior associated with SOAD has been derived and then proved to match the true posterior distribution under mild assumptions, suggesting its theoretical advantages over previous score-based approaches. Experimental results also indicate that SOAD may offer improved performance compared to existing data-driven methods. |
| title | State-observation augmented diffusion model for nonlinear assimilation with unknown dynamics |
| topic | Machine Learning 49N45, 60J60, 62F15, 68T20 |
| url | https://arxiv.org/abs/2407.21314 |