Addressing computational challenges in physical system simulations with machine learning
This work addresses computational challenges for researchers using simulations in physical sciences, offering an incremental improvement by integrating existing machine learning techniques.
The paper tackles the problem of high computational costs and limited data in physical system simulations by introducing a machine learning-based data generator framework, which combines supervised and reinforcement learning to produce accurate simulation-like data without running expensive simulations, as demonstrated in case studies on earthquake rupture physics and new material development.
In this paper, we present a machine learning-based data generator framework tailored to aid researchers who utilize simulations to examine various physical systems or processes. High computational costs and the resulting limited data often pose significant challenges to gaining insights into these systems or processes. Our approach involves a two-step process: initially, we train a supervised predictive model using a limited simulated dataset to predict simulation outcomes. Subsequently, a reinforcement learning agent is trained to generate accurate, simulation-like data by leveraging the supervised model. With this framework, researchers can generate more accurate data and know the outcomes without running high computational simulations, which enables them to explore the parameter space more efficiently and gain deeper insights into physical systems or processes. We demonstrate the effectiveness of the proposed framework by applying it to two case studies, one focusing on earthquake rupture physics and the other on new material development.