Machine Learning for Deep Trench Bottom Width Measurements using Scatterometry : AM: Advanced Metrology
- Resource Type
- Conference
- Authors
- Srichandan, Sasmita; Heider, Franz; Polak, Yulia; Ehrentraut, Georg; Juhasz, Laszlo; Haberjahn, Martin; Sakalauskas, Egidijus; Haupt, Ronny
- Source
- 2023 34th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC) SEMI Advanced Semiconductor Manufacturing Conference (ASMC), 2023 34th Annual. :1-6 May, 2023
- Subject
- Components, Circuits, Devices and Systems
Engineered Materials, Dielectrics and Plasmas
Photonics and Electrooptics
Semiconductor device modeling
Reflectivity
Semiconductor device measurement
Three-dimensional displays
Radar measurements
Shape measurement
Machine learning
machine learning
spectral reflectometry
scatterometry
trench shape
bottom CD
CD-SEM
OCD
- Language
- ISSN
- 2376-6697
We present a machine learning enhanced metrology method to measure the bottom width of deep trenches (about 42 µm in depth) using optical scatterometry. For this study, 2D line trenches as well as circular 3D trenches with varying trench side-wall angles were investigated. A combination of reference sets from SEM cross-sections, inline CD-SEM as well as depth measurements obtained from reflectance fringes are used to train the machine learning model. The results are cross verified against SEM cross-sections.