Predictive Scale-Bridging Simulations through Active Learning
- URL: http://arxiv.org/abs/2209.09811v1
- Date: Tue, 20 Sep 2022 15:58:50 GMT
- Title: Predictive Scale-Bridging Simulations through Active Learning
- Authors: Satish Karra, Mohamed Mehana, Nicholas Lubbers, Yu Chen, Abdourahmane
Diaw, Javier E. Santos, Aleksandra Pachalieva, Robert S. Pavel, Jeffrey R.
Haack, Michael McKerns, Christoph Junghans, Qinjun Kang, Daniel Livescu,
Timothy C. Germann, and Hari S. Viswanathan
- Abstract summary: We use 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, dynamically updating coarse-scale from fine-scale calculations, and quantifying uncertainty in neural network models.
- Score: 43.48102250786867
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Multi-fidelity Hierarchical Neural Processes [79.0284780825048]
Multi-fidelity surrogate modeling reduces the computational cost by fusing different simulation outputs.
We propose Multi-fidelity Hierarchical Neural Processes (MF-HNP), a unified neural latent variable model for multi-fidelity surrogate modeling.
We evaluate MF-HNP on epidemiology and climate modeling tasks, achieving competitive performance in terms of accuracy and uncertainty estimation.
arXiv Detail & Related papers (2022-06-10T04:54:13Z) - Accurate Machine Learned Quantum-Mechanical Force Fields for
Biomolecular Simulations [51.68332623405432]
Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes.
Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations.
This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations.
arXiv Detail & Related papers (2022-05-17T13:08:28Z) - Designing Machine Learning Surrogates using Outputs of Molecular
Dynamics Simulations as Soft Labels [0.0]
We show that statistical uncertainties associated with the outputs of molecular dynamics simulations can be utilized to train artificial neural networks.
We design soft labels for the simulation outputs by incorporating the uncertainties in the estimated average output quantities.
The approach is illustrated with the design of a surrogate for molecular dynamics simulations of confined electrolytes.
arXiv Detail & Related papers (2021-10-27T19:00:40Z) - Quantum-based Molecular Dynamics Simulations Using Tensor Cores [2.3551989288556774]
We show how tensor cores can be applied with high efficiency to the Born-Oppenheimer molecular dynamics problem.
The interatomic forces are calculated on-the-fly from an electronic structure that is obtained from a generalized deep neural network.
A canonical ensemble simulation scheme is also presented, where the additional numerical noise in the calculated forces is absorbed into a Langevin-like dynamics.
arXiv Detail & Related papers (2021-07-06T17:11:45Z) - Scientific multi-agent reinforcement learning for wall-models of
turbulent flows [5.678337324555036]
We introduce scientific multi-agent reinforcement learning (SciMARL) for the discovery of wall models for large-eddy simulations.
The present simulations reduce by several orders of magnitude the computational cost over fully-resolved simulations.
arXiv Detail & Related papers (2021-06-21T14:30:10Z) - Deep Bayesian Active Learning for Accelerating Stochastic Simulation [74.58219903138301]
Interactive Neural Process (INP) is a deep active learning framework for simulations and with active learning approaches.
For active learning, we propose a novel acquisition function, Latent Information Gain (LIG), calculated in the latent space of NP based models.
The results demonstrate STNP outperforms the baselines in the learning setting and LIG achieves the state-of-the-art for active learning.
arXiv Detail & Related papers (2021-06-05T01:31:51Z) - Learning Neural Generative Dynamics for Molecular Conformation
Generation [89.03173504444415]
We study how to generate molecule conformations (textiti.e., 3D structures) from a molecular graph.
We propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
arXiv Detail & Related papers (2021-02-20T03:17:58Z) - Learning the exchange-correlation functional from nature with fully
differentiable density functional theory [0.0]
We train a neural network to replace the exchange-correlation functional within a fully-differentiable three-dimensional Kohn-Sham density functional theory framework.
Our trained exchange-correlation network provided improved prediction of atomization and ionization energies across a collection of 110 molecules.
arXiv Detail & Related papers (2021-02-08T14:25:10Z) - Machine learning for rapid discovery of laminar flow channel wall
modifications that enhance heat transfer [56.34005280792013]
We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels and machine learning models predicting drag coefficient and Stanton number.
We show that convolutional neural networks (CNN) can accurately predict the target properties at a fraction of the time of numerical simulations.
arXiv Detail & Related papers (2021-01-19T16:14:02Z) - Modeling nanoconfinement effects using active learning [1.58501955991843]
Predicting the spatial configuration of gas molecules in nanopores of shale formations is crucial for fluid flow forecasting and hydrocarbon reserves estimation.
We present a method for building and training physics-based deep learning surrogate models to predict molecular configurations of gas inside nanopores.
arXiv Detail & Related papers (2020-05-06T04:01:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.