In-situ and Non-contact Etch Depth Prediction in Plasma Etching via Machine Learning (ANN & BNN) and Digital Image Colorimetry

TL;DR

This paper introduces a non-contact, in-situ plasma etch depth prediction method using machine learning and digital image colorimetry, enabling real-time monitoring without contamination risks.

Contribution

It develops a novel ML framework combining ANN and BNN for etch depth prediction, incorporating RGB image data for cost-effective, non-invasive process monitoring.

Findings

ANN achieves lower MSE than linear models

BNN provides reliable uncertainty estimates

RGB data effectively predicts etch depth without process parameters

Abstract

Precise monitoring of etch depth and the thickness of insulating materials, such as Silicon dioxide and silicon nitride, is critical to ensuring device performance and yield in semiconductor manufacturing. While conventional ex-situ analysis methods are accurate, they are constrained by time delays and contamination risks. To address these limitations, this study proposes a non-contact, in-situ etch depth prediction framework based on machine learning (ML) techniques. Two scenarios are explored. In the first scenario, an artificial neural network (ANN) is trained to predict average etch depth from process parameters, achieving a significantly lower mean squared error (MSE) compared to a linear baseline model. The approach is then extended to incorporate variability from repeated measurements using a Bayesian Neural Network (BNN) to capture both aleatoric and epistemic uncertainty. Coverage analysis confirms the BNN's capability to provide reliable uncertainty estimates. In the second scenario, we demonstrate the feasibility of using RGB data from digital image colorimetry (DIC) as input for etch depth prediction, achieving strong performance even in the absence of explicit process parameters. These results suggest that the integration of DIC and ML offers a viable, cost-effective alternative for real-time, in-situ, and non-invasive monitoring in plasma etching processes, contributing to enhanced process stability, and manufacturing efficiency.