Unsupervised learning for anticipating critical transitions
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915089225875456 |
|---|---|
| author | Panahi, Shirin Kong, Ling-Wei Glaz, Bryan Haile, Mulugeta Lai, Ying-Cheng |
| author_facet | Panahi, Shirin Kong, Ling-Wei Glaz, Bryan Haile, Mulugeta Lai, Ying-Cheng |
| contents | For anticipating critical transitions in complex dynamical systems, the recent approach of parameter-driven reservoir computing requires explicit knowledge of the bifurcation parameter. We articulate a framework combining a variational autoencoder (VAE) and reservoir computing to address this challenge. In particular, the driving factor is detected from time series using the VAE in an unsupervised-learning fashion and the extracted information is then used as the parameter input to the reservoir computer for anticipating the critical transition. We demonstrate the power of the unsupervised learning scheme using prototypical dynamical systems including the spatiotemporal Kuramoto-Sivashinsky system. The scheme can also be extended to scenarios where the target system is driven by several independent parameters or with partial state observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01579 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unsupervised learning for anticipating critical transitions Panahi, Shirin Kong, Ling-Wei Glaz, Bryan Haile, Mulugeta Lai, Ying-Cheng Chaotic Dynamics Machine Learning For anticipating critical transitions in complex dynamical systems, the recent approach of parameter-driven reservoir computing requires explicit knowledge of the bifurcation parameter. We articulate a framework combining a variational autoencoder (VAE) and reservoir computing to address this challenge. In particular, the driving factor is detected from time series using the VAE in an unsupervised-learning fashion and the extracted information is then used as the parameter input to the reservoir computer for anticipating the critical transition. We demonstrate the power of the unsupervised learning scheme using prototypical dynamical systems including the spatiotemporal Kuramoto-Sivashinsky system. The scheme can also be extended to scenarios where the target system is driven by several independent parameters or with partial state observations. |
| title | Unsupervised learning for anticipating critical transitions |
| topic | Chaotic Dynamics Machine Learning |
| url | https://arxiv.org/abs/2501.01579 |