Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR

The extraordinary progress of strategies coupling ab initio calculations and machine learning (ML) has opened the door for both fast and accurate chemical/physical property predictions and for the virtual design of materials. However, these techniques are very often used as a black box with the sole...

Descripción completa

Detalles Bibliográficos
Autores: Vassilev-Galindo, Valentín, Llorca, Javier
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Universidad Pública de Navarra
Repositorio:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
OAI Identifier:oai:academica-e.unavarra.es:2454/55868
Acceso en línea:https://hdl.handle.net/2454/55868
Access Level:acceso abierto
Palabra clave:Explainable artificial intelligence (XAI)
Machine
Chemisorption
Chemistry
Model
id ES_85b9cdbbfe9e5403eedc440e88a7d9e1
oai_identifier_str oai:academica-e.unavarra.es:2454/55868
network_acronym_str ES
network_name_str España
repository_id_str
spelling Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORRVassilev-Galindo, ValentínLlorca, JavierExplainable artificial intelligence (XAI)MachineChemisorptionChemistryModelThe extraordinary progress of strategies coupling ab initio calculations and machine learning (ML) has opened the door for both fast and accurate chemical/physical property predictions and for the virtual design of materials. However, these techniques are very often used as a black box with the sole objective of obtaining high accuracy with scarce or no special attention on how ML models obtain their predictions. This can be improved by leveraging explainability of ML models, which, at the same time, would increase the chance of ML to offer new insights into the chemistry and physics of materials. Hence, the next generation of ML models in these realms must guarantee explainability by embedding explainable artificial intelligence (XAI) tools into their pipelines. Specifically, ML-assisted materials discovery and design can take great advantage of the use of XAI. Enabling explanations would increase the impact of these approaches by providing not only a set of candidates, but also insights into what makes a given material better than others. With this in mind, using the example of heterogeneous catalysts for hydrogen production and energy generation, here we propose a novel strategy for materials design based on counterfactual explanations. We were able to find materials featuring properties close to the design targets that were later validated with density functional theory calculations. Explanations were devised by comparing original samples, counterfactuals, and discovered candidates. Such explanations allowed us to unveil subtle relationships between the most relevant features, other, in principle, less important features, and the target property. Since this approach can be applied to different applications, this work provides an alternative to already available designing strategies, such as high-throughput screening or generative models, but that, for the first time, incorporates explainability as its main driving mechanism.VV-G acknowledges support through the project HighHydrogenML (GA number 101105610) funded by the Horizon Europe program of the European Union. This investigation was also partly supported by the project High-throughput strategies for the discovery of new catalysts for the hydrogen economy through elastic strain engineering (CATbyESE), funded in the call for Oriented Projects for the Ecological and Digital Transition, Spanish Ministry of Science and Innovation (TED2021-129497B-I00), and by the project Digital strategies for autonomous discovery of materials for engineering applications (DIGIMATER-CM, reference TEC-2024/TEC-102), funded in the call of Programas de Actividades de I + D of the Comunidad de Madrid. Computational resources and technical assistance provided by the Centro de Supercomputacion y Visualizacion de Madrid (CeSViMa) are gratefully acknowledged.Royal Society of ChemistryEstadística, Informática y MatemáticasEstatistika, Informatika eta Matematika2025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/2454/55868reponame:Academica-e. Repositorio Institucional de la Universidad Pública de Navarrainstname:Universidad Pública de NavarraInglésinfo:eu-repo/grantAgreement/European Commission/Horizon 2020 Framework Programme/101105610info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/TED2021-129497B-I00© 2025 The Author(s). Published by the Royal Society of Chemistry. This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.https://creativecommons.org/licenses/by-nc/3.0/info:eu-repo/semantics/openAccessoai:academica-e.unavarra.es:2454/558682026-06-17T12:41:47Z
dc.title.none.fl_str_mv Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR
title Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR
spellingShingle Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR
Vassilev-Galindo, Valentín
Explainable artificial intelligence (XAI)
Machine
Chemisorption
Chemistry
Model
title_short Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR
title_full Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR
title_fullStr Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR
title_full_unstemmed Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR
title_sort Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR
dc.creator.none.fl_str_mv Vassilev-Galindo, Valentín
Llorca, Javier
author Vassilev-Galindo, Valentín
author_facet Vassilev-Galindo, Valentín
Llorca, Javier
author_role author
author2 Llorca, Javier
author2_role author
dc.contributor.none.fl_str_mv Estadística, Informática y Matemáticas
Estatistika, Informatika eta Matematika
dc.subject.none.fl_str_mv Explainable artificial intelligence (XAI)
Machine
Chemisorption
Chemistry
Model
topic Explainable artificial intelligence (XAI)
Machine
Chemisorption
Chemistry
Model
description The extraordinary progress of strategies coupling ab initio calculations and machine learning (ML) has opened the door for both fast and accurate chemical/physical property predictions and for the virtual design of materials. However, these techniques are very often used as a black box with the sole objective of obtaining high accuracy with scarce or no special attention on how ML models obtain their predictions. This can be improved by leveraging explainability of ML models, which, at the same time, would increase the chance of ML to offer new insights into the chemistry and physics of materials. Hence, the next generation of ML models in these realms must guarantee explainability by embedding explainable artificial intelligence (XAI) tools into their pipelines. Specifically, ML-assisted materials discovery and design can take great advantage of the use of XAI. Enabling explanations would increase the impact of these approaches by providing not only a set of candidates, but also insights into what makes a given material better than others. With this in mind, using the example of heterogeneous catalysts for hydrogen production and energy generation, here we propose a novel strategy for materials design based on counterfactual explanations. We were able to find materials featuring properties close to the design targets that were later validated with density functional theory calculations. Explanations were devised by comparing original samples, counterfactuals, and discovered candidates. Such explanations allowed us to unveil subtle relationships between the most relevant features, other, in principle, less important features, and the target property. Since this approach can be applied to different applications, this work provides an alternative to already available designing strategies, such as high-throughput screening or generative models, but that, for the first time, incorporates explainability as its main driving mechanism.
publishDate 2025
dc.date.none.fl_str_mv 2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/2454/55868
url https://hdl.handle.net/2454/55868
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/grantAgreement/European Commission/Horizon 2020 Framework Programme/101105610
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/TED2021-129497B-I00
dc.rights.none.fl_str_mv https://creativecommons.org/licenses/by-nc/3.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc/3.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Royal Society of Chemistry
publisher.none.fl_str_mv Royal Society of Chemistry
dc.source.none.fl_str_mv reponame:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
instname:Universidad Pública de Navarra
instname_str Universidad Pública de Navarra
reponame_str Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
collection Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412321339637760
score 15,811543

Similares en LA Referencia