Salvato in:
Dettagli Bibliografici
Autori principali: Kim, Hyunwoo, Lee, Munyoung, Jeon, Seung Hyub, Lee, Kyu Sung
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.23576
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918407420510208
author Kim, Hyunwoo
Lee, Munyoung
Jeon, Seung Hyub
Lee, Kyu Sung
author_facet Kim, Hyunwoo
Lee, Munyoung
Jeon, Seung Hyub
Lee, Kyu Sung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23576
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Wafer-Level Etch Spatial Profiling for Process Monitoring from Time-Series with Time-LLM
Kim, Hyunwoo
Lee, Munyoung
Jeon, Seung Hyub
Lee, Kyu Sung
Applications
Artificial Intelligence
Machine Learning
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.
title Wafer-Level Etch Spatial Profiling for Process Monitoring from Time-Series with Time-LLM
topic Applications
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.23576