A Machine Learning Study to Obtain an Optimal Processing Pulsed Frequency on Reactive Pulsed DC Sputtering of Aluminum Nitride Films

Xue Li Tseng, Yu Shin Chen, Hsuan Fan Chen, Hsiao Han Lo, Peter J. Wang, Yu Min Dai, Yiin Kuen Fuh, Ting-Tung Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The goal of this study was to investigate how changing the pulsed frequency affects the deposition process and correlates with AlN film properties. The resulting films were then characterized in terms of their crystallinity, microstructure, and surface roughness to identify any correlations with the pulsed frequency. This approach was used to determine the optimal pulsed conditions for film deposition. Each dataset spans the wavelength range of 190nm to 850nm, comprising 1,900 features. Following data collection, we employed traditional ensemble learning methods (Random Forest), tree-based gradient boosting (Categorical Boosting), and the improved gradient-boosted algorithm (Histogram Gradient Boosting), for predicting the quality of thin films. This analysis aimed to clarify which method excels in handling semiconductor process OES data to obtain an optimal processing pulsed frequency on reactive pulsed DC sputtering of aluminum nitride films.

Original languageEnglish
Title of host publication2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024
EditorsCor Claeys, Beichao Zhang, Bin Yu, Ru Huang, Xiaowei Li, Steve X. Liang, Jianshi Tang, Hsiang-Lan Lung, Linyong Pang, Weikang Qian, Xinping Qu, Xiaoping Shi, Ying Zhang
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350362190
DOIs
StatePublished - 2024
Event2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024 - Shanghai, China
Duration: 17 Mar 202418 Mar 2024

Publication series

Name2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024

Conference

Conference2024 Conference of Science and Technology for Integrated Circuits, CSTIC 2024
Country/TerritoryChina
CityShanghai
Period17/03/2418/03/24

Keywords

  • aluminum nitride (AlN)
  • Categorical Boosting (CatBoost)
  • Histogram-Based Gradient Boosting (HGB)
  • machine learning
  • optical emission spectroscopy (OES)
  • pulsed frequency
  • Random Forest
  • Reactive pulsed DC magnetron sputtering

Fingerprint

Dive into the research topics of 'A Machine Learning Study to Obtain an Optimal Processing Pulsed Frequency on Reactive Pulsed DC Sputtering of Aluminum Nitride Films'. Together they form a unique fingerprint.

Cite this