Wafer-Level Etch Spatial Profiling for Process Monitoring from Time-Series with Time-LLM

TL;DR

This paper introduces a Time-LLM-based spatial regression model that predicts wafer-level etch depth distributions from in-situ process time series, enabling advanced process monitoring with limited data.

Contribution

The paper presents a novel application of Time-LLM reprogramming for wafer-level spatial estimation in plasma etching, extending time-series forecasting to spatial process monitoring.

Findings

Stable performance with limited data demonstrated

Effective wafer-level spatial distribution prediction

Supports feasibility of LLM-based process monitoring

Abstract

Understanding wafer-level spatial variations from in-situ process signals is essential for advanced plasma etching process monitoring. While most data-driven approaches focus on scalar indicators such as average etch rate, actual process quality is determined by complex two-dimensional spatial distributions across the wafer. This paper presents a spatial regression model that predicts wafer-level etch depth distributions directly from multichannel in-situ process time series. We propose a Time-LLM-based spatial regression model that extends LLM reprogramming from conventional time-series forecasting to wafer-level spatial estimation by redesigning the input embedding and output projection. Using the BOSCH plasma-etching dataset, we demonstrate stable performance under data-limited conditions, supporting the feasibility of LLM-based reprogramming for wafer-level spatial monitoring.