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“DeepPs...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.展开更多
基金supported by the National Science Foundation Division of Chemistry, under the Chemical Theory, Models and Computational Methods (CTMC) program, grant number CHE-2449564Methods used to describe the vibronic properties of NCs were provided by the center on “Traversing the death valley separating short and long times in non-equilibrium quantum dynamical simulations of real materials”, which is funded by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research and Office of Basic Energy Sciences, Scientific Discovery through Advanced Computing (SciDAC) program, under Award No. DE-SC0022088+2 种基金Measured optical properties of III-V NCs were supported by the National Science Foundation Science and Technology Center (STC) for Integration of Modern Optoelectronic Materials on Demand (IMOD) under Cooperative Agreement No. DMR-2019444This research used resources of the National Energy Research Scientific Computing Center (NERSC)a DOE Office of Science User Facility supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231 using NERSC award BES-ERCAP0032503.
文摘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.
