Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908600238080000 |
|---|---|
| author | Nam, Juno Liu, Sulin Winter, Gavin Jun, KyuJung Yang, Soojung Gómez-Bombarelli, Rafael |
| author_facet | Nam, Juno Liu, Sulin Winter, Gavin Jun, KyuJung Yang, Soojung Gómez-Bombarelli, Rafael |
| contents | Atomic transport underpins the performance of materials in technologies such as energy storage and electronics, yet its simulation remains computationally demanding. In particular, modeling ionic diffusion in solid-state electrolytes (SSEs) requires methods that can overcome the scale limitations of traditional ab initio molecular dynamics (AIMD). We introduce LiFlow, a generative framework to accelerate MD simulations for crystalline materials that formulates the task as conditional generation of atomic displacements. The model uses flow matching, with a Propagator submodel to generate atomic displacements and a Corrector to locally correct unphysical geometries, and incorporates an adaptive prior based on the Maxwell-Boltzmann distribution to account for chemical and thermal conditions. We benchmark LiFlow on a dataset comprising 25-ps trajectories of lithium diffusion across 4,186 SSE candidates at four temperatures. The model obtains a consistent Spearman rank correlation of 0.7-0.8 for lithium mean squared displacement (MSD) predictions on unseen compositions. Furthermore, LiFlow generalizes from short training trajectories to larger supercells and longer simulations while maintaining high accuracy. With speed-ups of up to 600,000$\times$ compared to first-principles methods, LiFlow enables scalable simulations at significantly larger length and time scales. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01464 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials Nam, Juno Liu, Sulin Winter, Gavin Jun, KyuJung Yang, Soojung Gómez-Bombarelli, Rafael Materials Science Machine Learning Computational Physics Atomic transport underpins the performance of materials in technologies such as energy storage and electronics, yet its simulation remains computationally demanding. In particular, modeling ionic diffusion in solid-state electrolytes (SSEs) requires methods that can overcome the scale limitations of traditional ab initio molecular dynamics (AIMD). We introduce LiFlow, a generative framework to accelerate MD simulations for crystalline materials that formulates the task as conditional generation of atomic displacements. The model uses flow matching, with a Propagator submodel to generate atomic displacements and a Corrector to locally correct unphysical geometries, and incorporates an adaptive prior based on the Maxwell-Boltzmann distribution to account for chemical and thermal conditions. We benchmark LiFlow on a dataset comprising 25-ps trajectories of lithium diffusion across 4,186 SSE candidates at four temperatures. The model obtains a consistent Spearman rank correlation of 0.7-0.8 for lithium mean squared displacement (MSD) predictions on unseen compositions. Furthermore, LiFlow generalizes from short training trajectories to larger supercells and longer simulations while maintaining high accuracy. With speed-ups of up to 600,000$\times$ compared to first-principles methods, LiFlow enables scalable simulations at significantly larger length and time scales. |
| title | Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials |
| topic | Materials Science Machine Learning Computational Physics |
| url | https://arxiv.org/abs/2410.01464 |