Predicting rare events using neural networks and short-trajectory data
Estimating the likelihood, timing, and nature of events is a major goal of modeling stochastic dynamical systems. When the event is rare in comparison with the timescales of simulation and/or measurement needed to resolve the elemental dynamics, accurate prediction from direct observations becomes c...
| Veröffentlicht in: | Journal of computational physics. - 1986. - 488(2023) vom: 01. Sept. |
|---|---|
| 1. Verfasser: | |
| Weitere Verfasser: | , , |
| Format: | Online-Aufsatz |
| Sprache: | English |
| Veröffentlicht: |
2023
|
| Zugriff auf das übergeordnete Werk: | Journal of computational physics |
| Schlagworte: | Journal Article Feynman-Kac equation Holton-Mass model adaptive sampling high-dimensional PDE neural network rare event |
| Online verfügbar |
Volltext |