Machine learning for improved density functional theory thermodynamics

Abstract The predictive accuracy of density functional theory (DFT) for alloy formation enthalpies is often limited by intrinsic energy resolution errors, particularly in ternary phase stability calculations. In this work, we present a machine learning (ML) approach to systematically correct these e...

Full description

Saved in:
Bibliographic Details
Main Authors: Sergei I. Simak, Erna K. Delczeg-Czirjak, Olle Eriksson
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-02088-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849726154989109248
author Sergei I. Simak
Erna K. Delczeg-Czirjak
Olle Eriksson
author_facet Sergei I. Simak
Erna K. Delczeg-Czirjak
Olle Eriksson
author_sort Sergei I. Simak
collection DOAJ
description Abstract The predictive accuracy of density functional theory (DFT) for alloy formation enthalpies is often limited by intrinsic energy resolution errors, particularly in ternary phase stability calculations. In this work, we present a machine learning (ML) approach to systematically correct these errors, improving the reliability of first-principles predictions. A neural network model has been trained to predict the discrepancy between DFT-calculated and experimentally measured enthalpies for binary and ternary alloys and compounds. The model utilizes a structured feature set comprising elemental concentrations, atomic numbers, and interaction terms to capture key chemical and structural effects. By applying supervised learning and rigorous data curation we ensure a robust and physically meaningful correction. The model is implemented as a multi-layer perceptron (MLP) regressor with three hidden layers, optimized through leave-one-out cross-validation (LOOCV) and k-fold cross-validation to prevent overfitting. We illustrate the effectiveness of this method by applying it to the Al–Ni–Pd and Al–Ni–Ti systems, which are of interest for high-temperature applications in aerospace and protective coatings.
format Article
id doaj-art-36067d9bcafc46b1bfaceaf2c2531374
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-36067d9bcafc46b1bfaceaf2c25313742025-08-20T03:10:17ZengNature PortfolioScientific Reports2045-23222025-05-011511910.1038/s41598-025-02088-7Machine learning for improved density functional theory thermodynamicsSergei I. Simak0Erna K. Delczeg-Czirjak1Olle Eriksson2Department of Physics, Chemistry and Biology (IFM), Linköping UniversityDepartment of Physics and Astronomy, Uppsala UniversityDepartment of Physics and Astronomy, Uppsala UniversityAbstract The predictive accuracy of density functional theory (DFT) for alloy formation enthalpies is often limited by intrinsic energy resolution errors, particularly in ternary phase stability calculations. In this work, we present a machine learning (ML) approach to systematically correct these errors, improving the reliability of first-principles predictions. A neural network model has been trained to predict the discrepancy between DFT-calculated and experimentally measured enthalpies for binary and ternary alloys and compounds. The model utilizes a structured feature set comprising elemental concentrations, atomic numbers, and interaction terms to capture key chemical and structural effects. By applying supervised learning and rigorous data curation we ensure a robust and physically meaningful correction. The model is implemented as a multi-layer perceptron (MLP) regressor with three hidden layers, optimized through leave-one-out cross-validation (LOOCV) and k-fold cross-validation to prevent overfitting. We illustrate the effectiveness of this method by applying it to the Al–Ni–Pd and Al–Ni–Ti systems, which are of interest for high-temperature applications in aerospace and protective coatings.https://doi.org/10.1038/s41598-025-02088-7
spellingShingle Sergei I. Simak
Erna K. Delczeg-Czirjak
Olle Eriksson
Machine learning for improved density functional theory thermodynamics
Scientific Reports
title Machine learning for improved density functional theory thermodynamics
title_full Machine learning for improved density functional theory thermodynamics
title_fullStr Machine learning for improved density functional theory thermodynamics
title_full_unstemmed Machine learning for improved density functional theory thermodynamics
title_short Machine learning for improved density functional theory thermodynamics
title_sort machine learning for improved density functional theory thermodynamics
url https://doi.org/10.1038/s41598-025-02088-7
work_keys_str_mv AT sergeiisimak machinelearningforimproveddensityfunctionaltheorythermodynamics
AT ernakdelczegczirjak machinelearningforimproveddensityfunctionaltheorythermodynamics
AT olleeriksson machinelearningforimproveddensityfunctionaltheorythermodynamics