Electronic Structure Prediction of Multi-million Atom Systems Through Uncertainty Quantification Enabled Transfer Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pathrudkar, Shashank, Thiagarajan, Ponkrshnan, Agarwal, Shivang, Banerjee, Amartya S., Ghosh, Susanta
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910429692821504
author Pathrudkar, Shashank
Thiagarajan, Ponkrshnan
Agarwal, Shivang
Banerjee, Amartya S.
Ghosh, Susanta
author_facet Pathrudkar, Shashank
Thiagarajan, Ponkrshnan
Agarwal, Shivang
Banerjee, Amartya S.
Ghosh, Susanta
contents The ground state electron density -- obtainable using Kohn-Sham Density Functional Theory (KS-DFT) simulations -- contains a wealth of material information, making its prediction via machine learning (ML) models attractive. However, the computational expense of KS-DFT scales cubically with system size which tends to stymie training data generation, making it difficult to develop quantifiably accurate ML models that are applicable across many scales and system configurations. Here, we address this fundamental challenge by employing transfer learning to leverage the multi-scale nature of the training data, while comprehensively sampling system configurations using thermalization. Our ML models are less reliant on heuristics, and being based on Bayesian neural networks, enable uncertainty quantification. We show that our models incur significantly lower data generation costs while allowing confident -- and when verifiable, accurate -- predictions for a wide variety of bulk systems well beyond training, including systems with defects, different alloy compositions, and at unprecedented, multi-million-atom scales. Moreover, such predictions can be carried out using only modest computational resources.
format Preprint
id arxiv_https___arxiv_org_abs_2308_13096
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Electronic Structure Prediction of Multi-million Atom Systems Through Uncertainty Quantification Enabled Transfer Learning
Pathrudkar, Shashank
Thiagarajan, Ponkrshnan
Agarwal, Shivang
Banerjee, Amartya S.
Ghosh, Susanta
Materials Science
Disordered Systems and Neural Networks
Computational Physics
Quantum Physics
The ground state electron density -- obtainable using Kohn-Sham Density Functional Theory (KS-DFT) simulations -- contains a wealth of material information, making its prediction via machine learning (ML) models attractive. However, the computational expense of KS-DFT scales cubically with system size which tends to stymie training data generation, making it difficult to develop quantifiably accurate ML models that are applicable across many scales and system configurations. Here, we address this fundamental challenge by employing transfer learning to leverage the multi-scale nature of the training data, while comprehensively sampling system configurations using thermalization. Our ML models are less reliant on heuristics, and being based on Bayesian neural networks, enable uncertainty quantification. We show that our models incur significantly lower data generation costs while allowing confident -- and when verifiable, accurate -- predictions for a wide variety of bulk systems well beyond training, including systems with defects, different alloy compositions, and at unprecedented, multi-million-atom scales. Moreover, such predictions can be carried out using only modest computational resources.
title Electronic Structure Prediction of Multi-million Atom Systems Through Uncertainty Quantification Enabled Transfer Learning
topic Materials Science
Disordered Systems and Neural Networks
Computational Physics
Quantum Physics
url https://arxiv.org/abs/2308.13096