Predicting bandgap is a crucial topic in materials informatics, however, it is still difficult when the available dataset is limited and unbalanced. Here, we applied a machine learning approach to construct a prediction model for transition metal dichalcogenides and oxides. Using an oversampling technique and atomistic feature engineering, we successfully constructed the machine learning model and analyzed the correlation with other physical properties. Furthermore, we also utilized the model to obtain a compressive sensing model based on physical quantities for analytic interpretation and quick prediction.
We gratefully acknowledge support from the National Research Foundation of Korea, South Korea ( 2020M3H4A3081867 and 2022R1F1A1063060 ). The computations were carried out using resources from Korea Supercomputing Center (KSC-2021-RND-0025). Upendra Kumar is profoundly thankful to Dr. Seung-Cheol Lee (Director at Indo-Korea Science and Technology Center and a Principal Research Scientist, Center for Electronic Materials Research, Korea Institute of Science and Technology) for giving him the motivation to work in machine learning.We gratefully acknowledge support from the National Research Foundation of Korea, South Korea (2020M3H4A3081867 and 2022R1F1A1063060). The computations were carried out using resources from Korea Supercomputing Center (KSC-2021-RND-0025). Upendra Kumar is profoundly thankful to Dr. Seung-Cheol Lee (Director at Indo-Korea Science and Technology Center and a Principal Research Scientist, Center for Electronic Materials Research, Korea Institute of Science and Technology) for giving him the motivation to work in machine learning.The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Sung Beom Cho reports financial support was provided by National Research Foundation of Korea.
