Efficient and accurate atomistic modeling of dopant migration using deep neural network. (1st June 2022)

• Record Type: Journal Article
• Authors: Ding, Xi; Tao, Ming; Li, Junhua; Li, Mingyuan; Shi, Mengchao; Chen, Jiashu; Tang, Zhen; Benistant, Francis; Liu, Jie
• Is Part Of: Materials science in semiconductor processing. Volume 143(2022)
• Publication Date: 2022-06-01
• Subjects: Deep neural network -- Nudged elastic band -- Ab-initio TCAD -- Dopant -- Density functional theory; Semiconductors -- Periodicals; Integrated circuits -- Materials -- Periodicals; Semiconducteurs -- Périodiques; Circuits intégrés -- Matériaux -- Périodiques; Electronic journals; 621.38152
• DOI: 10.1016/j.mssp.2022.106513
• Languages: English
• ISSNs: 1369-8001

Abstract

Abstract: This paper proposes an efficient and accurate method to model atomistic dopant migration, by leveraging the emerging deep neural network (DNN). By performing nudged elastic band (NEB) simulations of three prototype systems (B-doped Si, Li-doped Si, and C-doped GaN), it is shown that the proposed DNN-based method runs about 10 4 -10 5 times faster than the widely-used atomistic dopant migration modeling method based on density functional theory (DFT), meanwhile keeping DFT-level high accuracy. Active learning is used to reduce training set redundancy, and the DNN model is further optimized for more accurate NEB calculation. As a result, the dopant atomic position in saddle-point and the dopant migration energy barrier in the migration energy path (MEP) predicted by the proposed DNN-based NEB deviate merely about 10 −2 Å and 10 −2 eV, respectively, from those predicted by the established DFT-based NEB. Given its efficiency and accuracy, the proposed DNN-based method might be useful to develop future-generation atomic-scale technology computer-aided design (TCAD) tools.