Jon López-Zorrilla
Research Subjects
Jon López-Zorrilla has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Hegoi Manzano
University of the Basque Country UPV/EHU
6 shared publications - Xabier Mendez Aretxabaleta
Unibersity of the Basque Country UPV/EHU
4 shared publications - Nongnuch Artrith
Utrecht University
3 shared publications - Iñigo Etxebarria
Fisika Aplikatua II Saila, Zientzia eta Teknologia Fakultatea, Euskal Herriko Unibertsitatea, P.K. 644, 48080 Bilbao, Spain
2 shared publications Xabier M. Aretxabaleta
Physics Department, University of the Basque Country UPV/EHU,Basque Country, 48940 Leioa, Spain
2 shared publications- Akira Yamaguchi
Department of Materials Science and Engineering, School of Materials and Chemical Technology, Institute of Science Tokyo, 2-12-1 Ookayama, Meguro-ku, Tokyo 152-8552, Japan
1 shared publication
Latest Publications
- Open Access
- 19 July 2025
- Published by Elsevier in Cement and Concrete Research
- Vol. 198
Mechanistic insights into calcium-silicate-hydrate nucleation from molecular dynamics simulations
- 19 July 2025
- Published by Elsevier in Cement and Concrete Research
- Vol. 198
Open AccessMechanistic insights into calcium-silicate-hydrate nucleation from molecular dynamics simulations
- Open Access
- 27 December 2024
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry C
- Vol. 129 (1) , 658-669
Cost-Effective Strategy of Enhancing Machine Learning Potentials by Transfer Learning from a Multicomponent Data Set on ænet-PyTorch
Machine learning potentials (MLPs) offer efficient and accurate material simulations, but constructing the reference ab initio database remains a significant challenge, particularly for catalyst-adsorbate systems. Training an MLP with a small data set can lead to overfitting, thus limiting its practical applications. This study explores the feasibility of developing computationally cost-effective and accurate MLPs for catalyst-adsorbate systems with a limited number of ab initio references by leveraging a transfer learning strategy from subsets of a comprehensive public database. Using the Open Catalyst Project 2020 (OC20)-a data set closely related to our system of interest-we pretrained MLP models on OC20 subsets using the ænet-PyTorch framework. We compared several strategies for database subset selection. Our findings indicate that MLPs constructed via transfer learning exhibit better generalizability than those constructed from scratch, as demonstrated by the consistency in the dynamics simulations. Remarkably, transfer learning enhances the stability and accuracy of MLPs for the CuAu/H2O system with approximately 600 reference data points. This approach achieved excellent extrapolation performance in molecular dynamics simulations for the larger CuAu/6H2O system, maintaining stable and accurate predictions for up to 250 ps, whereas MLPs without transfer learning become unstable before reaching 50 ps. We also examine the potential limitations of this strategy. This work proposes an alternative, cost-effective approach for constructing MLPs for the challenging simulation of catalytic systems. Finally, we anticipate that this methodology will pave the way for broader applications in materials science and catalysis research, facilitating more efficient and accurate simulations across various systems.
- 27 December 2024
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry C
- Vol. 129 (1) , 658-669
Open AccessCost-Effective Strategy of Enhancing Machine Learning Potentials by Transfer Learning from a Multicomponent Data Set on ænet-PyTorch
Machine learning potentials (MLPs) offer efficient and accurate material simulations, but constructing the reference ab initio database remains a significant challenge, particularly for catalyst-adsorbate systems. Training an MLP with a small data set can lead to overfitting, thus limiting its practical applications. This study explores the feasibility of developing computationally cost-effective and accurate MLPs for catalyst-adsorbate systems with a limited number of ab initio references by leveraging a transfer learning strategy from subsets of a comprehensive public database. Using the Open Catalyst Project 2020 (OC20)-a data set closely related to our system of interest-we pretrained MLP models on OC20 subsets using the ænet-PyTorch framework. We compared several strategies for database subset selection. Our findings indicate that MLPs constructed via transfer learning exhibit better generalizability than those constructed from scratch, as demonstrated by the consistency in the dynamics simulations. Remarkably, transfer learning enhances the stability and accuracy of MLPs for the CuAu/H2O system with approximately 600 reference data points. This approach achieved excellent extrapolation performance in molecular dynamics simulations for the larger CuAu/6H2O system, maintaining stable and accurate predictions for up to 250 ps, whereas MLPs without transfer learning become unstable before reaching 50 ps. We also examine the potential limitations of this strategy. This work proposes an alternative, cost-effective approach for constructing MLPs for the challenging simulation of catalytic systems. Finally, we anticipate that this methodology will pave the way for broader applications in materials science and catalysis research, facilitating more efficient and accurate simulations across various systems.
- 22 August 2024
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (17) , 7682-7690
Exploring the Polymorphism of Dicalcium Silicates Using Transfer Learning Enhanced Machine Learning Atomic Potentials
Belitic cements are a greener alternative to Ordinary Portland Cement due to the lower CO2 associated with their production. However, their low reactivity with water is currently a drawback, resulting in longer setting times. In this study, we utilize a combination of evolutionary algorithms and machine learning atomic potentials (MLPs) to identify previously unreported belite polymorphs that may exhibit higher hydraulic reactivity than the known phases. To address the high computational demand of this methodology, we propose a novel transfer learning approach for generating MLPs. First, the models are pretrained on a large set of classical data (ReaxFF) and then retrained with density functional theory (DFT) data. We demonstrate that the transfer learning enhanced potentials exhibit higher accuracy, require less training data, and are more transferable than those trained exclusively on DFT data. The generated machine learning potential enables a fast, exhaustive, and reliable exploration of the dicalcium silicate polymorphs. This includes studying their stability through phonon analysis and calculating their structural and elastic properties. Overall, we identify ten new belite polymorphs within the energy range of the existing ones, including a layered phase with potentially high reactivity.
- 22 August 2024
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (17) , 7682-7690
Exploring the Polymorphism of Dicalcium Silicates Using Transfer Learning Enhanced Machine Learning Atomic Potentials
Belitic cements are a greener alternative to Ordinary Portland Cement due to the lower CO2 associated with their production. However, their low reactivity with water is currently a drawback, resulting in longer setting times. In this study, we utilize a combination of evolutionary algorithms and machine learning atomic potentials (MLPs) to identify previously unreported belite polymorphs that may exhibit higher hydraulic reactivity than the known phases. To address the high computational demand of this methodology, we propose a novel transfer learning approach for generating MLPs. First, the models are pretrained on a large set of classical data (ReaxFF) and then retrained with density functional theory (DFT) data. We demonstrate that the transfer learning enhanced potentials exhibit higher accuracy, require less training data, and are more transferable than those trained exclusively on DFT data. The generated machine learning potential enables a fast, exhaustive, and reliable exploration of the dicalcium silicate polymorphs. This includes studying their stability through phonon analysis and calculating their structural and elastic properties. Overall, we identify ten new belite polymorphs within the energy range of the existing ones, including a layered phase with potentially high reactivity.
- Open Access
- 10 April 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Exploring the polymorphism of dicalcium silicates using transfer learning enhanced machine learning atomic potentials
Belitic cements are a greener alternative to Ordinary Portland Cements due to the lower CO2 associated to their production. However, their low reactivity with water is currently a drawback, resulting in longer setting times. In this study, we utilize a combination of evolutionary algorithms and machine learning atomic potentials (MLPs) to identify previously unreported belite polymorphs that may exhibit higher hydraulic reactivity than the known phases. To address the high computational demand of this methodology, we propose a novel transfer learning approach for generating MLPs. First, the models are pre-trained on a large set of classical data (ReaxFF) and then re-trained with Density Functional Theory (DFT) data. We demonstrate that the transfer learning enhanced potentials exhibit higher accuracy, require less training data, and are more transferable than those trained exclusively on DFT data. The generated machine learning potential enables a fast, exhaustive, and reliable exploration of the dicalcium silicate polymorphs. This includes studying their stability through phonon analysis and calculating their structural and elastic properties. Overall, we identify ten new belite polymorphs within the energy range of the existing ones, including a layered phase with potentially high reactivity.
- 10 April 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessExploring the polymorphism of dicalcium silicates using transfer learning enhanced machine learning atomic potentials
Belitic cements are a greener alternative to Ordinary Portland Cements due to the lower CO2 associated to their production. However, their low reactivity with water is currently a drawback, resulting in longer setting times. In this study, we utilize a combination of evolutionary algorithms and machine learning atomic potentials (MLPs) to identify previously unreported belite polymorphs that may exhibit higher hydraulic reactivity than the known phases. To address the high computational demand of this methodology, we propose a novel transfer learning approach for generating MLPs. First, the models are pre-trained on a large set of classical data (ReaxFF) and then re-trained with Density Functional Theory (DFT) data. We demonstrate that the transfer learning enhanced potentials exhibit higher accuracy, require less training data, and are more transferable than those trained exclusively on DFT data. The generated machine learning potential enables a fast, exhaustive, and reliable exploration of the dicalcium silicate polymorphs. This includes studying their stability through phonon analysis and calculating their structural and elastic properties. Overall, we identify ten new belite polymorphs within the energy range of the existing ones, including a layered phase with potentially high reactivity.
- Top Cited PapersOpen Access
- 2 December 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-9
Multi-step nucleation pathway of C-S-H during cement hydration from atomistic simulations
The Calcium Silicate Hydrate (C-S-H) nucleation is a crucial step during cement hydration and determines to a great extent the rheology, microstructure, and properties of the cement paste. Recent evidence indicates that the C-S-H nucleation involves at least two steps, yet the underlying atomic scale mechanism, the nature of the primary particles and their stability, or how they merge/aggregate to form larger structures is unknown. In this work, we use atomistic simulation methods, specifically DFT, evolutionary algorithms (EA), and Molecular Dynamics (MD), to investigate the structure and formation of C-S-H primary particles (PPs) from the ions in solution, and then discuss a possible formation pathway for the C-S-H nucleation. Our simulations indicate that even for small sizes the most stable clusters encode C-S-H structural motifs, and we identified a C4S4H2 cluster candidate to be the C-S-H basic building block. We suggest a formation path in which small clusters formed by silicate dimers merge into large elongated aggregates. Upon dehydration, the C-S-H basic building blocks can be formed within the aggregates, and eventually crystallize.
- 2 December 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-9
Top Cited PapersOpen AccessMulti-step nucleation pathway of C-S-H during cement hydration from atomistic simulations
The Calcium Silicate Hydrate (C-S-H) nucleation is a crucial step during cement hydration and determines to a great extent the rheology, microstructure, and properties of the cement paste. Recent evidence indicates that the C-S-H nucleation involves at least two steps, yet the underlying atomic scale mechanism, the nature of the primary particles and their stability, or how they merge/aggregate to form larger structures is unknown. In this work, we use atomistic simulation methods, specifically DFT, evolutionary algorithms (EA), and Molecular Dynamics (MD), to investigate the structure and formation of C-S-H primary particles (PPs) from the ions in solution, and then discuss a possible formation pathway for the C-S-H nucleation. Our simulations indicate that even for small sizes the most stable clusters encode C-S-H structural motifs, and we identified a C4S4H2 cluster candidate to be the C-S-H basic building block. We suggest a formation path in which small clusters formed by silicate dimers merge into large elongated aggregates. Upon dehydration, the C-S-H basic building blocks can be formed within the aggregates, and eventually crystallize.
- Open Access
- 25 April 2023
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 158 (16)
ænet-PyTorch: A GPU-supported implementation for machine learning atomic potentials training
In this work, we present ænet-PyTorch, a PyTorch-based implementation for training artificial neural network-based machine learning interatomic potentials. Developed as an extension of the atomic energy network (ænet), ænet-PyTorch provides access to all the tools included in ænet for the application and usage of the potentials. The package has been designed as an alternative to the internal training capabilities of ænet, leveraging the power of graphic processing units to facilitate direct training on forces in addition to energies. This leads to a substantial reduction of the training time by one to two orders of magnitude compared to the central processing unit implementation, enabling direct training on forces for systems beyond small molecules. Here, we demonstrate the main features of ænet-PyTorch and show its performance on open databases. Our results show that training on all the force information within a dataset is not necessary, and including between 10% and 20% of the force information is sufficient to achieve optimally accurate interatomic potentials with the least computational resources.
- 25 April 2023
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 158 (16)
Open Accessænet-PyTorch: A GPU-supported implementation for machine learning atomic potentials training
In this work, we present ænet-PyTorch, a PyTorch-based implementation for training artificial neural network-based machine learning interatomic potentials. Developed as an extension of the atomic energy network (ænet), ænet-PyTorch provides access to all the tools included in ænet for the application and usage of the potentials. The package has been designed as an alternative to the internal training capabilities of ænet, leveraging the power of graphic processing units to facilitate direct training on forces in addition to energies. This leads to a substantial reduction of the training time by one to two orders of magnitude compared to the central processing unit implementation, enabling direct training on forces for systems beyond small molecules. Here, we demonstrate the main features of ænet-PyTorch and show its performance on open databases. Our results show that training on all the force information within a dataset is not necessary, and including between 10% and 20% of the force information is sufficient to achieve optimally accurate interatomic potentials with the least computational resources.
- Open Access
ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
In this work, we present ænet-PyTorch, a PyTorch-based implementation for training artificial neural network-based machine learning interatomic potentials. Developed as an extension of the atomic energy network (ænet), ænet-PyTorch provides access to all the tools included in ænet for the application and usage of the potentials. The package has been designed as an alternative to the internal training capabilities of ænet, leveraging the power of graphic processing units to facilitate direct training on forces in addition to energies. This leads to a substantial reduction of the training time by one to two orders of magnitude compared to the CPU implementation, enabling direct training on forces for systems beyond small molecules. Here we demonstrate the main features of ænet-PyTorch and show its performance on open databases. Our results show that training on all the force information within a data set is not necessary, and including between 10% to 20% of the force information is sufficient to achieve optimally accurate interatomic potentials with the least computational resources.
Open Accessænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
In this work, we present ænet-PyTorch, a PyTorch-based implementation for training artificial neural network-based machine learning interatomic potentials. Developed as an extension of the atomic energy network (ænet), ænet-PyTorch provides access to all the tools included in ænet for the application and usage of the potentials. The package has been designed as an alternative to the internal training capabilities of ænet, leveraging the power of graphic processing units to facilitate direct training on forces in addition to energies. This leads to a substantial reduction of the training time by one to two orders of magnitude compared to the CPU implementation, enabling direct training on forces for systems beyond small molecules. Here we demonstrate the main features of ænet-PyTorch and show its performance on open databases. Our results show that training on all the force information within a data set is not necessary, and including between 10% to 20% of the force information is sufficient to achieve optimally accurate interatomic potentials with the least computational resources.
- Open Access
- 21 October 2021
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 6 (43) , 28561-28568
Relationship between Atomic Structure, Composition, and Dielectric Constant in Zr–SiO2 Glasses
- 21 October 2021
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 6 (43) , 28561-28568
Open AccessRelationship between Atomic Structure, Composition, and Dielectric Constant in Zr–SiO2 Glasses