Neural network potentials for exploring condensed phase chemical reactivity
Recent advances in machine learning offer powerful tools for exploring complex reaction mechanisms in condensed phases via reactive simulations. In this tutorial review, we describe the key challenges associated with simulating reactions in condensed phases, we introduce neural network potentials an...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Académie des sciences
2024-06-01
|
| Series: | Comptes Rendus. Chimie |
| Subjects: | |
| Online Access: | https://comptes-rendus.academie-sciences.fr/chimie/articles/10.5802/crchim.315/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206054788530176 |
|---|---|
| author | Gomez, Axel de la Puente, Miguel David, Rolf Laage, Damien |
| author_facet | Gomez, Axel de la Puente, Miguel David, Rolf Laage, Damien |
| author_sort | Gomez, Axel |
| collection | DOAJ |
| description | Recent advances in machine learning offer powerful tools for exploring complex reaction mechanisms in condensed phases via reactive simulations. In this tutorial review, we describe the key challenges associated with simulating reactions in condensed phases, we introduce neural network potentials and detail how they can be trained. We emphasize the importance of active learning to construct the training set, and show how these reactive force fields can be integrated with enhanced sampling techniques, including transition path sampling. We illustrate the capabilities of these new methods with a selection of applications to chemical reaction mechanisms in solution and at interfaces. |
| format | Article |
| id | doaj-art-0b8867fcb20348f097cd0222fb3ae62e |
| institution | Kabale University |
| issn | 1878-1543 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Académie des sciences |
| record_format | Article |
| series | Comptes Rendus. Chimie |
| spelling | doaj-art-0b8867fcb20348f097cd0222fb3ae62e2025-02-07T13:41:22ZengAcadémie des sciencesComptes Rendus. Chimie1878-15432024-06-0111710.5802/crchim.31510.5802/crchim.315Neural network potentials for exploring condensed phase chemical reactivityGomez, Axel0https://orcid.org/0000-0002-0378-4352de la Puente, Miguel1https://orcid.org/0000-0002-4432-9612David, Rolf2https://orcid.org/0000-0001-5338-6267Laage, Damien3https://orcid.org/0000-0001-5706-9939PASTEUR, Department of Chemistry, École Normale Supérieure, PSL University, Sorbonne Université, CNRS, 75005 Paris, FrancePASTEUR, Department of Chemistry, École Normale Supérieure, PSL University, Sorbonne Université, CNRS, 75005 Paris, FrancePASTEUR, Department of Chemistry, École Normale Supérieure, PSL University, Sorbonne Université, CNRS, 75005 Paris, FrancePASTEUR, Department of Chemistry, École Normale Supérieure, PSL University, Sorbonne Université, CNRS, 75005 Paris, FranceRecent advances in machine learning offer powerful tools for exploring complex reaction mechanisms in condensed phases via reactive simulations. In this tutorial review, we describe the key challenges associated with simulating reactions in condensed phases, we introduce neural network potentials and detail how they can be trained. We emphasize the importance of active learning to construct the training set, and show how these reactive force fields can be integrated with enhanced sampling techniques, including transition path sampling. We illustrate the capabilities of these new methods with a selection of applications to chemical reaction mechanisms in solution and at interfaces.https://comptes-rendus.academie-sciences.fr/chimie/articles/10.5802/crchim.315/Chemical reactivityMachine learningMolecular simulations |
| spellingShingle | Gomez, Axel de la Puente, Miguel David, Rolf Laage, Damien Neural network potentials for exploring condensed phase chemical reactivity Comptes Rendus. Chimie Chemical reactivity Machine learning Molecular simulations |
| title | Neural network potentials for exploring condensed phase chemical reactivity |
| title_full | Neural network potentials for exploring condensed phase chemical reactivity |
| title_fullStr | Neural network potentials for exploring condensed phase chemical reactivity |
| title_full_unstemmed | Neural network potentials for exploring condensed phase chemical reactivity |
| title_short | Neural network potentials for exploring condensed phase chemical reactivity |
| title_sort | neural network potentials for exploring condensed phase chemical reactivity |
| topic | Chemical reactivity Machine learning Molecular simulations |
| url | https://comptes-rendus.academie-sciences.fr/chimie/articles/10.5802/crchim.315/ |
| work_keys_str_mv | AT gomezaxel neuralnetworkpotentialsforexploringcondensedphasechemicalreactivity AT delapuentemiguel neuralnetworkpotentialsforexploringcondensedphasechemicalreactivity AT davidrolf neuralnetworkpotentialsforexploringcondensedphasechemicalreactivity AT laagedamien neuralnetworkpotentialsforexploringcondensedphasechemicalreactivity |