Investigation of Laser Ablation Quality Based on Data Science and Machine Learning XGBoost Classifier

Abstract

This work proposes a matching data science approach for the laser ablation quality, reb, the study of Si3N4 film based on supervised machine learning classifiers in the CMOS-MEMS process. The study demonstrates that there exists an energy threshold, Eth, for laser ablation. If the laser energy surpasses this threshold, increasing the interval time will not contribute significantly to the recovery of pulse laser energy. Thus, reb enhancement is limited. When the energy is greater than 0.258 mJ, there exists a critical value of interval time at which the reb value is relatively low for each energy level, respectively. In addition, the variation of reb, Δreb, is independent of the interval time at the invariant point of energy between 0.32 mJ and 0.36 mJ. Energy and interval time exhibit a Pearson correlation of 0.82 and 0.53 with reb, respectively. To maintain Δreb below 0.15, green laser ablation of Si3N4 at operating energies of 0.258–0.378 mJ can adopt a baseline interval time of the initial baseline multiplied by 1/∜2. Additionally, for operating energies of 0.288–0.378 mJ during Si3N4 laser ablation, Δreb can be kept below 0.1. With the forced partition methods, namely, the k-means method and percentile method, the XGBoost (v 2.0.3) classifier maintains a competitive accuracy across test sizes of 0.20–0.40, outperforming the machine learning algorithms Random Forest and Logistic Regression, with the highest accuracy of 0.78 at a test size of 0.20.

Keywords

• machine learning
• XGBoost classifier
• laser ablation
• CMOS-MEMS
• k-means