Predictive Scale-Bridging Simulations through Active Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929349226135552 |
|---|---|
| author | Karra, Satish Mehana, Mohamed Lubbers, Nicholas Chen, Yu Diaw, Abdourahmane Santos, Javier E. Pachalieva, Aleksandra Pavel, Robert S. Haack, Jeffrey R. McKerns, Michael Junghans, Christoph Kang, Qinjun Livescu, Daniel Germann, Timothy C. Viswanathan, Hari S. |
| author_facet | Karra, Satish Mehana, Mohamed Lubbers, Nicholas Chen, Yu Diaw, Abdourahmane Santos, Javier E. Pachalieva, Aleksandra Pavel, Robert S. Haack, Jeffrey R. McKerns, Michael Junghans, Christoph Kang, Qinjun Livescu, Daniel Germann, Timothy C. Viswanathan, Hari S. |
| contents | Throughout computational science, there is a growing need to utilize the continual improvements in raw computational horsepower to achieve greater physical fidelity through scale-bridging over brute-force increases in the number of mesh elements. For instance, quantitative predictions of transport in nanoporous media, critical to hydrocarbon extraction from tight shale formations, are impossible without accounting for molecular-level interactions. Similarly, inertial confinement fusion simulations rely on numerical diffusion to simulate molecular effects such as non-local transport and mixing without truly accounting for molecular interactions. With these two disparate applications in mind, we develop a novel capability which uses an active learning approach to optimize the use of local fine-scale simulations for informing coarse-scale hydrodynamics. Our approach addresses three challenges: forecasting continuum coarse-scale trajectory to speculatively execute new fine-scale molecular dynamics calculations, dynamically updating coarse-scale from fine-scale calculations, and quantifying uncertainty in neural network models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_09811 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Predictive Scale-Bridging Simulations through Active Learning Karra, Satish Mehana, Mohamed Lubbers, Nicholas Chen, Yu Diaw, Abdourahmane Santos, Javier E. Pachalieva, Aleksandra Pavel, Robert S. Haack, Jeffrey R. McKerns, Michael Junghans, Christoph Kang, Qinjun Livescu, Daniel Germann, Timothy C. Viswanathan, Hari S. Machine Learning Artificial Intelligence Applications Computation Throughout computational science, there is a growing need to utilize the continual improvements in raw computational horsepower to achieve greater physical fidelity through scale-bridging over brute-force increases in the number of mesh elements. For instance, quantitative predictions of transport in nanoporous media, critical to hydrocarbon extraction from tight shale formations, are impossible without accounting for molecular-level interactions. Similarly, inertial confinement fusion simulations rely on numerical diffusion to simulate molecular effects such as non-local transport and mixing without truly accounting for molecular interactions. With these two disparate applications in mind, we develop a novel capability which uses an active learning approach to optimize the use of local fine-scale simulations for informing coarse-scale hydrodynamics. Our approach addresses three challenges: forecasting continuum coarse-scale trajectory to speculatively execute new fine-scale molecular dynamics calculations, dynamically updating coarse-scale from fine-scale calculations, and quantifying uncertainty in neural network models. |
| title | Predictive Scale-Bridging Simulations through Active Learning |
| topic | Machine Learning Artificial Intelligence Applications Computation |
| url | https://arxiv.org/abs/2209.09811 |