POMs‐GibbsNet: A Deep Neural Network for the Prediction of Thermodynamic Parameters of Polyoxometalates
Journal of Computational Chemistry · 30.10.2026 · 47 (28)
DOI: 10.1002/jcc.70510 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational Chemistry, online erschienen am 21.10.2026. Verfasst von Jordi Buils und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Chemical Research of Catalonia (ICIQ), Tarragona, Spain. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerio de Ciencia, Innovación y Universidades, Generalitat de Catalunya, RCN FRIPRO (catLEGOS project).
Abstract (Originalsprache)
Polyoxometalates (POMs) are versatile metal–oxo clusters with remarkable structural diversity and applications spanning catalysis, energy storage, and materials science. However, accurately predicting their thermodynamic properties remains computationally demanding due to the large system sizes and the cost of density functional theory (DFT) frequency calculations required to obtain Gibbs free energies. In this work, we present POMs‐GibbsNet, a deep neural network designed to predict the thermal free energy correction () of polyoxometalates by combining graph‐based molecular representations with DFT‐derived descriptors. Molecular structures were encoded using variants of the AABBA autocorrelation graph kernel, which captures atom–atom, bond–bond, and atom–bond correlations together with quantum‐derived features including QTAIM descriptors. POMs‐GibbsNet was trained on a dataset of 1419 POM structures spanning 19 chemical systems to obtain good results ( and RMSE = 1.9 kcal mol −1 . To evaluate the performance, a benchmark against 10 classical regressors was performed. Additionally, an uncertainty study was added to the methodology. External validation using POMSimulator reaction networks comprising over 10,819 reactions shows excellent agreement between predicted and DFT reaction energies (), with errors typically within a few kcal mol −1 . Error cancellation was also studied during this step. Notably, simplified atom–atom autocorrelation descriptors already provide robust performance while reducing model complexity. These results demonstrate that POMs‐GibbsNet enables efficient estimation of thermodynamic corrections in POM systems, providing a powerful framework for accelerating the computational exploration of polyoxometalate speciation and self‐assembly across large chemical spaces.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Chemical Research of Catalonia (ICIQ), Tarragona, Spain.
- Departament de Química Física I Inorgànica, Universitat Rovira i Virgili, Tarragona, Spain.
- Hylleraas Centre for Quantum Molecular Sciences, Department of Chemistry, University of Oslo, Oslo, Norway.
ORCID-Profile: Jordi Buils, Carles Bo
Förderung
- Ministerio de Ciencia, Innovación y Universidades
- Generalitat de Catalunya
- RCN FRIPRO (catLEGOS project)
- RCN (National Centers of Excellence (Hylleraas Centre))
- Norwegian Supercomputing Program (NOTUR)
Zitieren
APA
Buils, J., Bo, C., & Balcells, D. (2026). POMs‐GibbsNet: A Deep Neural Network for the Prediction of Thermodynamic Parameters of Polyoxometalates. Journal of Computational Chemistry, 47(28). https://doi.org/10.1002/jcc.70510
Vancouver
Buils J, Bo C, Balcells D. POMs‐GibbsNet: A Deep Neural Network for the Prediction of Thermodynamic Parameters of Polyoxometalates. Journal of Computational Chemistry. 2026;47(28). doi:10.1002/jcc.70510
BibTeX
@article{Buils2026,
author = {Buils, Jordi and Bo, Carles and Balcells, David},
title = {POMs‐GibbsNet: A Deep Neural Network for the Prediction of Thermodynamic Parameters of Polyoxometalates},
journal = {Journal of Computational Chemistry},
year = {2026},
volume = {47},
number = {28},
doi = {10.1002/jcc.70510}
}
EUVIMED