Transfer Learning for Deep Learning-based Prediction of Lattice Thermal Conductivity

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Klochko, L., d'Aquin, M., Togo, A., Chaput, L.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929607302709248
author Klochko, L.
d'Aquin, M.
Togo, A.
Chaput, L.
author_facet Klochko, L.
d'Aquin, M.
Togo, A.
Chaput, L.
contents Machine learning promises to accelerate the material discovery by enabling high-throughput prediction of desirable macro-properties from atomic-level descriptors or structures. However, the limited data available about precise values of these properties have been a barrier, leading to predictive models with limited precision or the ability to generalize. This is particularly true of lattice thermal conductivity (LTC): existing datasets of precise (ab initio, DFT-based) computed values are limited to a few dozen materials with little variability. Based on such datasets, we study the impact of transfer learning on both the precision and generalizability of a deep learning model (ParAIsite). We start from an existing model (MEGNet~\cite{Chen2019}) and show that improvements are obtained by fine-tuning a pre-trained version on different tasks. Interestingly, we also show that a much greater improvement is obtained when first fine-tuning it on a large datasets of low-quality approximations of LTC (based on the AGL model) and then applying a second phase of fine-tuning with our high-quality, smaller-scale datasets. The promising results obtained pave the way not only towards a greater ability to explore large databases in search of low thermal conductivity materials but also to methods enabling increasingly precise predictions in areas where quality data are rare.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18259
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transfer Learning for Deep Learning-based Prediction of Lattice Thermal Conductivity
Klochko, L.
d'Aquin, M.
Togo, A.
Chaput, L.
Machine Learning
Computational Physics
Machine learning promises to accelerate the material discovery by enabling high-throughput prediction of desirable macro-properties from atomic-level descriptors or structures. However, the limited data available about precise values of these properties have been a barrier, leading to predictive models with limited precision or the ability to generalize. This is particularly true of lattice thermal conductivity (LTC): existing datasets of precise (ab initio, DFT-based) computed values are limited to a few dozen materials with little variability. Based on such datasets, we study the impact of transfer learning on both the precision and generalizability of a deep learning model (ParAIsite). We start from an existing model (MEGNet~\cite{Chen2019}) and show that improvements are obtained by fine-tuning a pre-trained version on different tasks. Interestingly, we also show that a much greater improvement is obtained when first fine-tuning it on a large datasets of low-quality approximations of LTC (based on the AGL model) and then applying a second phase of fine-tuning with our high-quality, smaller-scale datasets. The promising results obtained pave the way not only towards a greater ability to explore large databases in search of low thermal conductivity materials but also to methods enabling increasingly precise predictions in areas where quality data are rare.
title Transfer Learning for Deep Learning-based Prediction of Lattice Thermal Conductivity
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2411.18259