[19p-141-1~8] Plasma Informatics - Development of Plasma Science by Taking Advantage of Big Data and Analytics

[19p-141-6] Optimization of Plasma Etching Profile Utilizing Machine Learning

〇Takeshi Ohmori¹, Hyakka Nakada¹, Masayoshi Ishikawa¹, Naoyuki Kofuji¹, Tatehito Usui¹, Masaru Kurihara¹ (1.Hitachi, Ltd., R&D Group)

Keywords:plasma, etching, machine learning

The number of control parameters in an etcher has increased to achieve nano-scale semiconductor processing. However, it has been difficult to optimize recipes with the large number of parameters for obtaining a desirable etching profile. In this work, we developed a method of predicting and optimizing etching profiles to obtain a target profile using machine learning. We will present the results of experimental verification using the predicted recipes and obtained vertical etching profiles.