[1Fa01-05] Data-driven research and development focused on data generation/storage/analysis: Data-Driven Surface Science Division's Session

[1Fa04] Machine-learning based spectral analysis of chemical vapor deposited monolayer MoS₂–Nb-doped MoS₂ lateral homojunctions

*Mitsuhiro Okada¹, Naoka Nagamura², Tarojiro Matsumura³, Yasunobu Ando³, Toshitaka Kubo⁴, Takatoshi Yamada¹ (1. Nano Carbon Device Research Center, National Institute of Advanced Industrial Science and Technology (AIST), 2. Center for Basic Research on Materials, National Institute for Materials Science, 3. Research Center for Computational Design of Advanced Functional Materials, National Institute of Advanced Industrial Science and Technology (AIST), 4. Nanomaterials Research Institute, National Institute of Advanced Industrial Science and Technology (AIST))

Emerging the application of machine-learning in materials science and the automation of the measurements have made the burden of the analysis of the obtained datasets precisely. In this presentation, we demonstrate the machine-learning-based spectral analysis to the electron spectroscopy for chemical analysis (ESCA) datasets measured from a chemical vapor-deposition grown monolayer MoS₂–Nb-doped MoS₂ lateral homojunctions. The ESCA measurement and following analysis successfully visualized the spatial distribution of the existence of Nb⁴⁺ atoms and the binding energy shift of Mo⁴⁺ 3d_5/2, indicating the partial doping of Nb and corresponding co-existence of p- and n-type nature in the same MoS₂ crystals. The analysis took only a few days to make the results. Thus, the autonomous spectral fitting techniques can allow us to use more time to not analyze the results, but experiments.