Abstract

Achieving high classification accuracy on trace chemical residues in active spectroscopic sensing is challenging due to the limited amount of training data available to the classifier. Such classifiers often rely on physics-based models for generating training data though these models are not always accurate when compared to measured data. To overcome this challenge, we developed a physics-guided neural network (PGNN) for predicting chemical reflectance for a set of parameterized inputs that is more accurate than the state-of-the-art physics-based signature model for chemical residues. After training the PGNN, we use it to generate a library of predicted spectra for training a classifier. We compare the classification accuracy when using this PGNN library versus a library generated by the physics-based model. Using the PGNN, the average classification accuracy increases from 0.623 to 0.813 on real chemical reflectance data, including data from chemicals not included in the PGNN training set.

© 2021 Optical Society of America

Physics-guided neural network for tissue optical properties estimation

Kian Chee Chong and Manojit Pramanik
Biomed. Opt. Express 14(6) 2576-2590 (2023)

Physics-guided neural network for channeled spectropolarimeter spectral reconstruction

Chan Huang, Huanwen Liu, Su Wu, Xiaoyun Jiang, Leiming Zhou, and Jigang Hu
Opt. Express 31(15) 24387-24403 (2023)

Neural network pattern recognition of thermal-signature spectra for chemical defense

Arthur H. Carrieri and Pascal I. Lim
Appl. Opt. 34(15) 2623-2635 (1995)

Small obstacle size prediction based on a GA-BP neural network

Yu Ning, Yongping Jin, Youduo Peng, and Jian Yan
Appl. Opt. 61(1) 177-187 (2022)

Using an artificial neural network to predict the residual stress induced by laser shock processing

Jiajun Wu, Xuejun Liu, Hongchao Qiao, Yongjie Zhao, Xianliang Hu, Yuqi Yang, and Jibin Zhao
Appl. Opt. 60(11) 3114-3121 (2021)