Feasibility Study on Active Learning of Smart Surrogates for Scientific Simulations

TL;DR

This paper explores using active learning to efficiently train deep neural network surrogates for scientific simulations, reducing data generation costs and improving surrogate performance.

Contribution

It introduces active learning strategies for selecting training data in DNN surrogate models, enhancing efficiency and reducing reliance on extensive simulation data.

Findings

Active learning improves surrogate training efficiency.

Diversity- and uncertainty-based strategies are effective.

Framework supports on-the-fly data generation for simulations.

Abstract

High-performance scientific simulations, important for comprehension of complex systems, encounter computational challenges especially when exploring extensive parameter spaces. There has been an increasing interest in developing deep neural networks (DNNs) as surrogate models capable of accelerating the simulations. However, existing approaches for training these DNN surrogates rely on extensive simulation data which are heuristically selected and generated with expensive computation -- a challenge under-explored in the literature. In this paper, we investigate the potential of incorporating active learning into DNN surrogate training. This allows intelligent and objective selection of training simulations, reducing the need to generate extensive simulation data as well as the dependency of the performance of DNN surrogates on pre-defined training simulations. In the problem context of constructing DNN surrogates for diffusion equations with sources, we examine the efficacy of diversity- and uncertainty-based strategies for selecting training simulations, considering two different DNN architecture. The results set the groundwork for developing the high-performance computing infrastructure for Smart Surrogates that supports on-the-fly generation of simulation data steered by active learning strategies to potentially improve the efficiency of scientific simulations.