Enhancing the Quality and Reliability of Machine Learning Interatomic Potentials through Better Reporting Practices
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917558386425856 |
|---|---|
| author | Maxson, Tristan Soyemi, Ademola Chen, Benjamin W. J. Szilvási, Tibor |
| author_facet | Maxson, Tristan Soyemi, Ademola Chen, Benjamin W. J. Szilvási, Tibor |
| contents | Recent developments in machine learning interatomic potentials (MLIPs) have empowered even non-experts in machine learning to train MLIPs for accelerating materials simulations. However, the current literature lacks clear standards for documenting the use of MLIPs, which hinders the reproducibility and independent evaluation of the presented results. In this perspective, we aim to provide guidance on best practices for documenting MLIP use while walking the reader through the development and deployment of MLIPs including hardware and software requirements, generating training data, training models, validating predictions, and MLIP inference. We also suggest useful plotting practices and analyses to validate and boost confidence in the deployed models. Finally, we provide a step-by-step checklist for practitioners to use directly before publication to standardize the information to be reported. Overall, we hope that our work will encourage reliable and reproducible use of these MLIPs, which will accelerate their ability to make a positive impact in various disciplines including materials science, chemistry, and biology, among others. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_02284 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing the Quality and Reliability of Machine Learning Interatomic Potentials through Better Reporting Practices Maxson, Tristan Soyemi, Ademola Chen, Benjamin W. J. Szilvási, Tibor Chemical Physics Materials Science Recent developments in machine learning interatomic potentials (MLIPs) have empowered even non-experts in machine learning to train MLIPs for accelerating materials simulations. However, the current literature lacks clear standards for documenting the use of MLIPs, which hinders the reproducibility and independent evaluation of the presented results. In this perspective, we aim to provide guidance on best practices for documenting MLIP use while walking the reader through the development and deployment of MLIPs including hardware and software requirements, generating training data, training models, validating predictions, and MLIP inference. We also suggest useful plotting practices and analyses to validate and boost confidence in the deployed models. Finally, we provide a step-by-step checklist for practitioners to use directly before publication to standardize the information to be reported. Overall, we hope that our work will encourage reliable and reproducible use of these MLIPs, which will accelerate their ability to make a positive impact in various disciplines including materials science, chemistry, and biology, among others. |
| title | Enhancing the Quality and Reliability of Machine Learning Interatomic Potentials through Better Reporting Practices |
| topic | Chemical Physics Materials Science |
| url | https://arxiv.org/abs/2401.02284 |