Deep-learning atomistic semi-empirical pseudopotential model for nanomaterials

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Kailai, Coley-O'Rourke, Matthew J., Rabani, Eran
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909978380468224
author Lin, Kailai
Coley-O'Rourke, Matthew J.
Rabani, Eran
author_facet Lin, Kailai
Coley-O'Rourke, Matthew J.
Rabani, Eran
contents The semi-empirical pseudopotential method (SEPM) has been widely applied to provide computational insights into the electronic structure, photophysics, and charge carrier dynamics of nanoscale materials. We present "DeepPseudopot", a machine-learned atomistic pseudopotential model that extends the SEPM framework by combining a flexible neural network representation of the local pseudopotential with parameterized non-local and spin-orbit coupling terms. Trained on bulk quasiparticle band structures and deformation potentials from GW calculations, the model captures many-body and relativistic effects with very high accuracy across diverse semiconducting materials, as illustrated for silicon and group III-V semiconductors. DeepPseudopot's accuracy, efficiency, and transferability make it well-suited for data-driven in silico design and discovery of novel optoelectronic nanomaterials.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09846
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep-learning atomistic semi-empirical pseudopotential model for nanomaterials
Lin, Kailai
Coley-O'Rourke, Matthew J.
Rabani, Eran
Materials Science
Mesoscale and Nanoscale Physics
Computational Physics
The semi-empirical pseudopotential method (SEPM) has been widely applied to provide computational insights into the electronic structure, photophysics, and charge carrier dynamics of nanoscale materials. We present "DeepPseudopot", a machine-learned atomistic pseudopotential model that extends the SEPM framework by combining a flexible neural network representation of the local pseudopotential with parameterized non-local and spin-orbit coupling terms. Trained on bulk quasiparticle band structures and deformation potentials from GW calculations, the model captures many-body and relativistic effects with very high accuracy across diverse semiconducting materials, as illustrated for silicon and group III-V semiconductors. DeepPseudopot's accuracy, efficiency, and transferability make it well-suited for data-driven in silico design and discovery of novel optoelectronic nanomaterials.
title Deep-learning atomistic semi-empirical pseudopotential model for nanomaterials
topic Materials Science
Mesoscale and Nanoscale Physics
Computational Physics
url https://arxiv.org/abs/2505.09846