PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 21, 2026Journal of Astronomy and Space Sciences2 citationsOpen Access

Deep Learning-Based Prediction of Tool Influence Function for Nanometric Control in Space Optical Material

SHSeung Ho HanJHJeong-Yeol HanJLJiwoo Lee

Key Points

  • The research aims to develop a deep learning model to predict the tool influence function for polishing Silicon Carbide mirrors.
  • Developed a deep learning-based model for TIF prediction
  • Utilized 231 experimental measurements for training
  • Augmented data with Gaussian noise to improve model robustness
  • Evaluated model performance using mean absolute error metrics
  • Achieved a validation mean absolute error of 4.24 nm
  • Tested with a mean absolute error of 3.99 nm
  • On additional experimental cases, a mean absolute error of 6.75 nm was observed
  • Demonstrated improved robustness to experimental variability through data augmentation

Abstract

Polishing is a critical process in fabricating space-telescope mirrors because it determines the surface figure and consequently optical performance. Deterministic polishing relies on the tool influence function (TIF), which describes the spatial material-removal profile. At nanometric removal depths, the TIF becomes highly sensitive to process conditions, limiting the accuracy of analytic models such as Preston’s equation. In this study, we propose a deep learning-based approach to predict TIF depth for polishing a Silicon Carbide (SiC) mirror surface. To mitigate data scarcity, we augment 231 experimental measurements with Gaussian noise consistent with the repeatability observed in repeated trials (≈ 20 nm peak-to-peak). The resulting model achieves a validation mean absolute error (MAE) of 4.24 nm and a test MAE of 3.99 nm; on nine additional experimental cases, the MAE is 6.75 nm. These results indicate that the proposed augmentation improves robustness to experimental variability and supports the development of a data-driven, automated polishing workflow.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Han et al. (2026) studied this question.

synapsesocial.com/papers/69be37866e48c4981c677409https://doi.org/10.5140/jass.2026.43.1.21
Ask AI
Helpful
Bookmark
Share
View Full Paper