Large-Scale Non-Adiabatic Dynamics Simulation Based on Machine Learning Hamiltonian and Force Field: The Case of...

We present an efficient and reliable large-scale non-adiabatic dynamics simulation method based on machine learning Hamiltonian and force field. The quasi-diabatic Hamiltonian network (DHNet) is trained in the Wannier basis based on well-designed translation and rotation invariant structural descriptors, which can effectively capture both local and nonlocal environmental information. Using the representative two-dimensional transition metal dichalcogenide MoS₂ as an illustration, we show that density functional theory (DFT) calculations of only ten structures are sufficient to generate the training set for DHNet due to the high efficiency of Wannier analysis and orbital classification in sampling the interorbital couplings. DHNet demonstrates good transferability, thus enabling direct construction of the electronic Hamiltonian matrices for large systems. Compared with direct DFT calculations, DHNet significantly reduces the computational cost by about 5 orders of magnitude. By combining DHNet with the DeePMD machine learning force field, we successfully simulate electron transport in monolayer MoS₂ with up to 3675 atoms and 13475 electronic levels by using a state-of-the-art surface hopping method. The electron mobility is calculated to be 110 cm²/(V s), which is in good agreement with the extensive experimental results in the range of 3-200 cm²/(V s) during 2013-2023. Due to the high performance, the proposed DHNet and large-scale non-adiabatic dynamics methods have great potential to be applied to study charge carrier dynamics in a wide range of material systems.