Allegro-FM: Towards Equivariant Foundation Model for Exascale Molecular Dynamics Simulations
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_ | 1866929721967640576 |
|---|---|
| author | Nomura, Ken-ichi Hattori, Shinnosuke Ohmura, Satoshi Kanemasu, Ikumi Shimamura, Kohei Dasgupta, Nabankur Nakano, Aiichiro Kalia, Rajiv K. Vashishta, Priya |
| author_facet | Nomura, Ken-ichi Hattori, Shinnosuke Ohmura, Satoshi Kanemasu, Ikumi Shimamura, Kohei Dasgupta, Nabankur Nakano, Aiichiro Kalia, Rajiv K. Vashishta, Priya |
| contents | We present a foundation model for exascale molecular dynamics simulations by leveraging an E(3) equivariant network architecture (Allegro) and a set of large-scale organic and inorganic materials datasets merged by Total Energy Alignment (TEA) framework. Thanks to the large-scale training sets, the obtained model (Allegro-FM) is versatile for various materials simulations for diverse downstream tasks covering 89 elements in the periodic table. Allegro-FM exhibits excellent agreements with high-level quantum chemistry theories in describing structural, mechanical, and thermodynamic properties, while exhibiting emergent capabilities for structural correlations, reaction kinetics, mechanical strengths, fracture, and solid/liquid dissolution, for which the model has not been trained. Furthermore, we demonstrate the robust predictability and generalizability of Allegro-FM for chemical reactions using the Transition1x that consists of 10k organic reactions and 9.6 million configurations including transition state data, as well as calcium silicate hydrates as a testbed. With its computationally efficient, strictly-local network architecture, Allegro-FM scales up to multi-billion-atom systems with a parallel efficiency of 0.964 on the exaflop/s Aurora supercomputer at Argonne Leadership Computing Facility. The approach presented in this work demonstrates the potential of the foundation model for a novel materials design and discovery based on large-scale atomistic simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06073 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Allegro-FM: Towards Equivariant Foundation Model for Exascale Molecular Dynamics Simulations Nomura, Ken-ichi Hattori, Shinnosuke Ohmura, Satoshi Kanemasu, Ikumi Shimamura, Kohei Dasgupta, Nabankur Nakano, Aiichiro Kalia, Rajiv K. Vashishta, Priya Materials Science We present a foundation model for exascale molecular dynamics simulations by leveraging an E(3) equivariant network architecture (Allegro) and a set of large-scale organic and inorganic materials datasets merged by Total Energy Alignment (TEA) framework. Thanks to the large-scale training sets, the obtained model (Allegro-FM) is versatile for various materials simulations for diverse downstream tasks covering 89 elements in the periodic table. Allegro-FM exhibits excellent agreements with high-level quantum chemistry theories in describing structural, mechanical, and thermodynamic properties, while exhibiting emergent capabilities for structural correlations, reaction kinetics, mechanical strengths, fracture, and solid/liquid dissolution, for which the model has not been trained. Furthermore, we demonstrate the robust predictability and generalizability of Allegro-FM for chemical reactions using the Transition1x that consists of 10k organic reactions and 9.6 million configurations including transition state data, as well as calcium silicate hydrates as a testbed. With its computationally efficient, strictly-local network architecture, Allegro-FM scales up to multi-billion-atom systems with a parallel efficiency of 0.964 on the exaflop/s Aurora supercomputer at Argonne Leadership Computing Facility. The approach presented in this work demonstrates the potential of the foundation model for a novel materials design and discovery based on large-scale atomistic simulations. |
| title | Allegro-FM: Towards Equivariant Foundation Model for Exascale Molecular Dynamics Simulations |
| topic | Materials Science |
| url | https://arxiv.org/abs/2502.06073 |