تقرير
Generative Learning for Forecasting the Dynamics of Complex Systems
| العنوان: | Generative Learning for Forecasting the Dynamics of Complex Systems |
|---|---|
| المؤلفون: | Gao, Han, Kaltenbach, Sebastian, Koumoutsakos, Petros |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science Physics (Other) Statistics |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Physics - Computational Physics, Physics - Fluid Dynamics, Statistics - Machine Learning |
| الوصف: | We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high dimensional data are down sampled to a lower dimensional manifold that is evolved through an auto-regressive attention mechanism. In turn, Bayesian diffusion models, that map this low-dimensional manifold onto its corresponding high-dimensional space, capture the statistics of the system dynamics. We demonstrate the capabilities and drawbacks of G-LED in simulations of several benchmark systems, including the Kuramoto-Sivashinsky (KS) equation, two-dimensional high Reynolds number flow over a backward-facing step, and simulations of three-dimensional turbulent channel flow. The results demonstrate that generative learning offers new frontiers for the accurate forecasting of the statistical properties of complex systems at a reduced computational cost. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2402.17157 |
| رقم الأكسشن: | edsarx.2402.17157 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |