Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917171193446400 |
|---|---|
| author | Lahouari, Adam Rogal, Jutta Tuckerman, Mark E. |
| author_facet | Lahouari, Adam Rogal, Jutta Tuckerman, Mark E. |
| contents | Machine learning interatomic potentials (MLIPs) have become powerful tools to extend molecular simulations beyond the limits of quantum methods, offering near-quantum accuracy at much lower computational cost. Yet, developing reliable MLIPs remains difficult because it requires generating high-quality datasets, preprocessing atomic structures, and carefully training and validating models. In this work, we introduce an Automated Machine Learning Pipeline (AMLP) that unifies the entire workflow from dataset creation to model validation. AMLP employs large-language-model agents to assist with electronic-structure code selection, input preparation, and output conversion, while its analysis suite (AMLP-Analysis), based on ASE supports a range of molecular simulations. The pipeline is built on the MACE architecture and validated on acridine polymorphs, where, with a straightforward fine-tuning of a foundation model, mean absolute errors of ~1.7 meV/atom in energies and ~7.0 meV/Å in forces are achieved. The fitted MLIP reproduces DFT geometries with sub-Å accuracy and demonstrates stability during molecular dynamics simulations in the microcanonical and canonical ensembles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21647 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials Lahouari, Adam Rogal, Jutta Tuckerman, Mark E. Materials Science Machine Learning Machine learning interatomic potentials (MLIPs) have become powerful tools to extend molecular simulations beyond the limits of quantum methods, offering near-quantum accuracy at much lower computational cost. Yet, developing reliable MLIPs remains difficult because it requires generating high-quality datasets, preprocessing atomic structures, and carefully training and validating models. In this work, we introduce an Automated Machine Learning Pipeline (AMLP) that unifies the entire workflow from dataset creation to model validation. AMLP employs large-language-model agents to assist with electronic-structure code selection, input preparation, and output conversion, while its analysis suite (AMLP-Analysis), based on ASE supports a range of molecular simulations. The pipeline is built on the MACE architecture and validated on acridine polymorphs, where, with a straightforward fine-tuning of a foundation model, mean absolute errors of ~1.7 meV/atom in energies and ~7.0 meV/Å in forces are achieved. The fitted MLIP reproduces DFT geometries with sub-Å accuracy and demonstrates stability during molecular dynamics simulations in the microcanonical and canonical ensembles. |
| title | Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2509.21647 |