Pattern‐Aware Intelligence Enables Nondestructive, Rapid Quantification of High‐Aspect‐Ratio Silicon Etching
Authors:
Open Access
- 20 July 2026
- journal article
- Published by Wiley in Advanced Science
- Vol. 13 (57)
Abstract
High‐aspect‐ratio (HAR) structures are widely used in microelectromechanical systems (MEMS), electronic devices, and advanced packaging. Accurate characterization of post‐etch microstructural morphology is essential for process control and device reliability. However, existing metrology techniques rely on destructive methods and cannot capture the complete three‐dimensional profile. This study proposes a pattern‐aware intelligent model that transforms pattern‐dependent etching behavior into a physical prior, enabling rapid and minimally destructive reconstruction of HAR structures across pattern scales. A YOLO‐Pose‐based model is developed to automatically extract subpixel geometric features from scanning electron microscopy images, achieving a quantification accuracy of 95.11% with R 2 >0.98 for key dimensions. By incorporating the pattern‐dependent effect in HAR silicon etching as a physical prior, the model creates a topography network that captures etch behavior across feature sizes under identical process conditions. With minimal destructive observations of shallow regions of the wafer, the framework achieves a 93.96% prediction accuracy in the nondestructive retrieval of critical parameters, including etch depth, sidewall angle, and scallop texture, while demonstrating robust cross‐scale generalization across varying layout densities. This approach reduces the data acquisition time to 1 min, enabling near‐real‐time process feedback. It provides a highly interpretable, cost‐effective, and intelligent solution for intelligent manufacturing applications.Keywords
Funding Information
- National Natural Science Foundation of China (62504006)
- National Natural Science Foundation of China (52521007)
- China Postdoctoral Science Foundation (2025M770514)
This publication has 26 references indexed in Scilit:
- Wafer-scale platform for on-chip 3D radio frequency lumped passive components using metal self-rolled-up membrane techniqueNature Communications, 2025
- Innovative two-step method for efficient silicon microfluidic device fabrication: Integrating laser ablation with wet etchingMaterials Science in Semiconductor Processing, 2024
- Volumetric nondestructive metrology for 3D semiconductor packaging: A reviewMeasurement, 2023
- Etched characteristics of nanoscale TiO2 using C4F8-based and BCl3-based gasesMaterials Science in Semiconductor Processing, 2023
- Heavy-ion induced gate damage and thermal destruction in double-trench SiC MOSFETsMicroelectronics Reliability, 2022
- Plasma etching of the trench pattern with high aspect ratio mask under ion tiltingApplied Surface Science, 2022
- DREM: Infinite etch selectivity and optimized scallop size distribution with conventional photoresists in an adapted multiplexed Bosch DRIE processMicroelectronic Engineering, 2018
- Investigating stress measurement capabilities of GHz Scanning Acoustic Microscopy for 3D failure analysisMicroelectronics Reliability, 2016
- Magnetic Field Imaging for non destructive 3D IC testingMicroelectronics Reliability, 2014
- Methodology for trench capacitor etch optimization using voltage contrast inspection and special processing2010