_version_ 1866918459787444224
author Luise, Giulia
Huang, Chin-Wei
Vogels, Thijs
Kooi, Derk P.
Ehlert, Sebastian
Lanius, Stephanie
Giesbertz, Klaas J. H.
Karton, Amir
Gunceler, Deniz
Battaglia, Stefano
Simm, Gregor N. C.
Szabó, P. Bernát
Stanley, Megan
Bruinsma, Wessel P.
Huang, Lin
Wei, Xinran
Torres, José Garrido
Katbashev, Abylay
Zavaleta, Rodrigo Chavez
Máté, Bálint
Kaba, Sékou-Oumar
Sordillo, Roberto
Chen, Yingrong
Williams-Young, David B.
Bishop, Christopher M.
Hermann, Jan
Berg, Rianne van den
Gori-Giorgi, Paola
author_facet Luise, Giulia
Huang, Chin-Wei
Vogels, Thijs
Kooi, Derk P.
Ehlert, Sebastian
Lanius, Stephanie
Giesbertz, Klaas J. H.
Karton, Amir
Gunceler, Deniz
Battaglia, Stefano
Simm, Gregor N. C.
Szabó, P. Bernát
Stanley, Megan
Bruinsma, Wessel P.
Huang, Lin
Wei, Xinran
Torres, José Garrido
Katbashev, Abylay
Zavaleta, Rodrigo Chavez
Máté, Bálint
Kaba, Sékou-Oumar
Sordillo, Roberto
Chen, Yingrong
Williams-Young, David B.
Bishop, Christopher M.
Hermann, Jan
Berg, Rianne van den
Gori-Giorgi, Paola
contents Density Functional Theory (DFT) underpins much of modern computational chemistry and materials science. Yet, the reliability of DFT-derived predictions of experimentally measurable properties remains fundamentally limited by the need to approximate the unknown exchange-correlation (XC) functional. The traditional paradigm for improving accuracy has relied on increasingly elaborate hand-crafted functional forms. This approach has led to a longstanding trade-off between computational efficiency and accuracy, which remains insufficient for reliable predictive modelling of laboratory experiments. Here we introduce Skala, a deep learning-based XC functional that surpasses state-of-the-art hybrid functionals in accuracy across the main-group chemistry benchmark set GMTKN55 with an error of 2.8 kcal/mol, while retaining the lower computational cost characteristic of semi-local DFT. This demonstrated departure from the historical trade-off between accuracy and efficiency is enabled by learning non-local representations of electronic structure directly from data, bypassing the need for increasingly costly hand-engineered features. Leveraging an unprecedented volume of high-accuracy reference data from wavefunction-based methods, we establish that modern deep learning enables systematically improvable neural exchange-correlation models as training datasets expand, positioning first-principles simulations to become progressively more predictive.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14665
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accurate and scalable exchange-correlation with deep learning
Luise, Giulia
Huang, Chin-Wei
Vogels, Thijs
Kooi, Derk P.
Ehlert, Sebastian
Lanius, Stephanie
Giesbertz, Klaas J. H.
Karton, Amir
Gunceler, Deniz
Battaglia, Stefano
Simm, Gregor N. C.
Szabó, P. Bernát
Stanley, Megan
Bruinsma, Wessel P.
Huang, Lin
Wei, Xinran
Torres, José Garrido
Katbashev, Abylay
Zavaleta, Rodrigo Chavez
Máté, Bálint
Kaba, Sékou-Oumar
Sordillo, Roberto
Chen, Yingrong
Williams-Young, David B.
Bishop, Christopher M.
Hermann, Jan
Berg, Rianne van den
Gori-Giorgi, Paola
Chemical Physics
Artificial Intelligence
Computational Engineering, Finance, and Science
Machine Learning
Computational Physics
Density Functional Theory (DFT) underpins much of modern computational chemistry and materials science. Yet, the reliability of DFT-derived predictions of experimentally measurable properties remains fundamentally limited by the need to approximate the unknown exchange-correlation (XC) functional. The traditional paradigm for improving accuracy has relied on increasingly elaborate hand-crafted functional forms. This approach has led to a longstanding trade-off between computational efficiency and accuracy, which remains insufficient for reliable predictive modelling of laboratory experiments. Here we introduce Skala, a deep learning-based XC functional that surpasses state-of-the-art hybrid functionals in accuracy across the main-group chemistry benchmark set GMTKN55 with an error of 2.8 kcal/mol, while retaining the lower computational cost characteristic of semi-local DFT. This demonstrated departure from the historical trade-off between accuracy and efficiency is enabled by learning non-local representations of electronic structure directly from data, bypassing the need for increasingly costly hand-engineered features. Leveraging an unprecedented volume of high-accuracy reference data from wavefunction-based methods, we establish that modern deep learning enables systematically improvable neural exchange-correlation models as training datasets expand, positioning first-principles simulations to become progressively more predictive.
title Accurate and scalable exchange-correlation with deep learning
topic Chemical Physics
Artificial Intelligence
Computational Engineering, Finance, and Science
Machine Learning
Computational Physics
url https://arxiv.org/abs/2506.14665