AtomProNet: Data flow to and from machine learning interatomic potentials in materials science
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916581475352576 |
|---|---|
| author | Galib, Musanna Isiet, Mewael Ponga, Mauricio |
| author_facet | Galib, Musanna Isiet, Mewael Ponga, Mauricio |
| contents | As the atomistic simulations of materials science move from traditional potentials to machine learning interatomic potential (MLIP), the field is entering the second phase focused on discovering and explaining new material phenomena. While MLIP development relies on curated data and flexible datasets from ab-initio simulations, transitioning seamlessly between ab-initio workflows and MLIP frameworks remains challenging. A global survey was conducted to understand the current standing (progress and bottleneck) of the machine learning-guided materials science research. The survey responses have been implemented to design an open-source software to reduce the access barriers of MLIP models for the global scientific community. Here, we present AtomProNet, an open-source Python package that automates obtaining atomic structures, prepares and submits ab-initio jobs, and efficiently collects batch-processed data for streamlined neural network (NN) training. Finally, we compared empirical and start-of-the-art machine learning potential, showing the practicality of using MLIPs based on computational time and resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14039 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AtomProNet: Data flow to and from machine learning interatomic potentials in materials science Galib, Musanna Isiet, Mewael Ponga, Mauricio Materials Science As the atomistic simulations of materials science move from traditional potentials to machine learning interatomic potential (MLIP), the field is entering the second phase focused on discovering and explaining new material phenomena. While MLIP development relies on curated data and flexible datasets from ab-initio simulations, transitioning seamlessly between ab-initio workflows and MLIP frameworks remains challenging. A global survey was conducted to understand the current standing (progress and bottleneck) of the machine learning-guided materials science research. The survey responses have been implemented to design an open-source software to reduce the access barriers of MLIP models for the global scientific community. Here, we present AtomProNet, an open-source Python package that automates obtaining atomic structures, prepares and submits ab-initio jobs, and efficiently collects batch-processed data for streamlined neural network (NN) training. Finally, we compared empirical and start-of-the-art machine learning potential, showing the practicality of using MLIPs based on computational time and resources. |
| title | AtomProNet: Data flow to and from machine learning interatomic potentials in materials science |
| topic | Materials Science |
| url | https://arxiv.org/abs/2501.14039 |