Integration of Physics-Based and Data-Driven Models for Hyperspectral Image Unmixing

Abstract

Spectral unmixing is one of the most important quantitative analysis tasks in hyperspectral data processing. Conventional physics-based models are characterized by clear interpretation. However they may not be suitable for analyzing scenes with unknown complex physical characteristics. Data-driven methods have developed rapidly in recent years, in particular deep learning methods because they possess superior capability in modeling complex and nonlinear systems. Simply transferring these methods as black-boxes to conduct unmixing may lead to low physical interpretability and generalization ability. This article reviews hyperspectral unmixing works that integrate advantages of both physics-based models and data-driven methods by means of deep neural network structures design, prior design and loss design. Most of these methods derive from a common mathematical optimization framework, and combine good interpretability with high accuracy.

IEEE Signal Process. Mag., to be published. Manuscript submitted March 14, 2022; revised June 25, 2022 and July 27, 2022; accepted August 27, 2022

References in corpus (1)

• SSCU-Net: Spatial-Spectral Collaborative Unmixing Network for Hyperspectral Images

Cited by in corpus (4)

• Image Processing and Machine Learning for Hyperspectral Unmixing: An Overview and the HySUPP Python Package
• Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders
• Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors
• Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability