Discovery of materials for solar thermochemical hydrogen combining machine learning, computational chemistry, experiments and system simulations

This study integrates first-principles calculations, computational chemistry, system simulations, experiments, and machine learning to identify redox perovskite oxides for solar thermochemical hydrogen production. Using two random forest regressions and one classification model, the approach predict...

Descripción completa

Detalles Bibliográficos
Autores: Perry, Jonathan, Molina, Laura, Calle, Alberto de la, Peño, Raúl, Jones, Timothy W., Ganduglia Pirovano, Verónica, Jiménez Fernández, Silvia|||0000-0002-2065-1754, Donne, Scott W., Coronado, Juan M., Bayón, Alicia
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/68217
Acceso en línea:http://hdl.handle.net/10017/68217
https://dx.doi.org/10.1038/s41524-025-01726-y
Access Level:acceso abierto
Palabra clave:Energías Renovables/Energías Alternativas
Alternative energies
Descripción
Sumario:This study integrates first-principles calculations, computational chemistry, system simulations, experiments, and machine learning to identify redox perovskite oxides for solar thermochemical hydrogen production. Using two random forest regressions and one classification model, the approach predicts materials" stability and the enthalpy of oxygen vacancy formation (Deltaho), a critical property for selecting materials for thermochemical hydrogen production. B-site composition significantly influences Deltaho predictions. The methodology led to the discovery of Ba0.875Ca0.125Zr0.875Mn0.125O3 (BCZM), which reduces at temperatures up to 250 °C lower than CeO2 and is expected to outperform other perovskites in water splitting. However, CeO2 remains the benchmark for solar thermochemical hydrogen production. The combined use of machine learning and DFT calculations refined 4ho predictions and provided insights into experimental results. This framework not only enhances database creation for material screening but also establishes a novel approach for perovskite discovery for hydrogen production applications.