EllipsoNet: Deep-learning-enabled optical ellipsometry for complex thin films

TL;DR

EllipsoNet leverages deep learning to enable optical ellipsometry using simple equipment, accurately determining complex refractive indices of thin films on complex substrates without prior knowledge, surpassing traditional methods.

Contribution

This work introduces EllipsoNet, a deep learning model that performs computational ellipsometry with minimal instrumentation and no prior substrate knowledge, a significant advancement over traditional techniques.

Findings

High-accuracy prediction of complex refractive indices.

Model spontaneously learns physical principles like Kramers-Kronig relations.

Enables in-operando optical characterization in complex structures.

Abstract

Optical spectroscopy is indispensable for research and development in nanoscience and nanotechnology, microelectronics, energy, and advanced manufacturing. Advanced optical spectroscopy tools often require both specifically designed high-end instrumentation and intricate data analysis techniques. Beyond the common analytical tools, deep learning methods are well suited for interpreting high-dimensional and complicated spectroscopy data. They offer great opportunities to extract subtle and deep information about optical properties of materials with simpler optical setups, which would otherwise require sophisticated instrumentation. In this work, we propose a computational ellipsometry approach based on a conventional tabletop optical microscope and a deep learning model called EllipsoNet. Without any prior knowledge about the multilayer substrates, EllipsoNet can predict the complex refractive indices of thin films on top of these nontrivial substrates from experimentally measured optical reflectance spectra with high accuracies. This task was not feasible previously with traditional reflectometry or ellipsometry methods. Fundamental physical principles, such as the Kramers-Kronig relations, are spontaneously learned by the model without any further training. This approach enables in-operando optical characterization of functional materials within complex photonic structures or optoelectronic devices.