High pressure hydrogen by machine learning and quantum Monte Carlo

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tirelli, Andrea, Tenti, Giacomo, Nakano, Kousuke, Sorella, Sandro
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916647272448000
author Tirelli, Andrea
Tenti, Giacomo
Nakano, Kousuke
Sorella, Sandro
author_facet Tirelli, Andrea
Tenti, Giacomo
Nakano, Kousuke
Sorella, Sandro
contents We have developed a technique combining the accuracy of quantum Monte Carlo in describing the electron correlation with the efficiency of a Machine Learning Potential (MLP). We use kernel regression in combination with SOAP (Smooth Overlap of Atomic Position) features, implemented here in a very efficient way. The key ingredients are: i) a sparsification technique, based on farthest point sampling, ensuring generality and transferability of our MLPs and ii) the so called $Δ$-learning, allowing a small training data set, a fundamental property for highly accurate but computationally demanding calculations, such as the ones based on quantum Monte Carlo. As the first application we present a benchmark study of the liquid-liquid transition of high-pressure hydrogen and show the quality of our MLP, by emphasizing the importance of high accuracy for this very debated subject, where experiments are difficult in the lab, and theory is still far from being conclusive.
format Preprint
id arxiv_https___arxiv_org_abs_2112_11099
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle High pressure hydrogen by machine learning and quantum Monte Carlo
Tirelli, Andrea
Tenti, Giacomo
Nakano, Kousuke
Sorella, Sandro
Strongly Correlated Electrons
Artificial Intelligence
Machine Learning
Computational Physics
We have developed a technique combining the accuracy of quantum Monte Carlo in describing the electron correlation with the efficiency of a Machine Learning Potential (MLP). We use kernel regression in combination with SOAP (Smooth Overlap of Atomic Position) features, implemented here in a very efficient way. The key ingredients are: i) a sparsification technique, based on farthest point sampling, ensuring generality and transferability of our MLPs and ii) the so called $Δ$-learning, allowing a small training data set, a fundamental property for highly accurate but computationally demanding calculations, such as the ones based on quantum Monte Carlo. As the first application we present a benchmark study of the liquid-liquid transition of high-pressure hydrogen and show the quality of our MLP, by emphasizing the importance of high accuracy for this very debated subject, where experiments are difficult in the lab, and theory is still far from being conclusive.
title High pressure hydrogen by machine learning and quantum Monte Carlo
topic Strongly Correlated Electrons
Artificial Intelligence
Machine Learning
Computational Physics
url https://arxiv.org/abs/2112.11099