Physics-based AI methodology for Material Parameter Extraction from Optical Data
This work addresses material parameter extraction for industrial and societal applications, representing an incremental improvement by combining existing methods in a novel way.
The authors tackled the problem of extracting material parameters from spectroscopic optical data by developing a physics-based neural network that integrates classical optimization with multi-scale object detection, achieving autonomous, robust, and time-efficient performance compared to traditional model-based approaches.
We report on a novel methodology for extracting material parameters from spectroscopic optical data using a physics-based neural network. The proposed model integrates classical optimization frameworks with a multi-scale object detection framework, specifically exploring the effect of incorporating physics into the neural network. We validate and analyze its performance on simulated transmission spectra at terahertz and infrared frequencies. Compared to traditional model-based approaches, our method is designed to be autonomous, robust, and time-efficient, making it particularly relevant for industrial and societal applications.