Blind Hyperspectral Unmixing Using Autoencoders: A Critical Comparison

Deep learning (DL) has heavily impacted the data-intensive field of remote sensing. Autoencoders are a type of DL methods that have been found to be powerful for blind hyperspectral unmixing (HU). HU is the process of resolving the measured spectrum of a pixel into a combination of a set of spectral signatures called endmembers and simultaneously determining their fractional abundances in the pixel. This article details the various autoencoder architectures used in HU and provides a critical comparison of some of the existing published blind unmixing methods based on autoencoders. Eleven different autoencoder methods and one traditional method will be compared in blind unmixing experiments using four real datasets and four synthetic datasets with different spectral variability. Additionally, extensive ablation experiments with a simple spectral unmixing autoencoder will be performed. The results are interpreted in terms of the various implementation details, and the question of why autoencoder methods are so powerful compared to traditional methods is unraveled. The source codes for all methods implemented in this article can be found at https://github.com/burknipalsson/hu_autoencoders.

Automated summary

This article explores the application of deep learning, specifically autoencoders, in remote sensing, focusing on blind hyperspectral unmixing. Through comparative experiments with 11 different autoencoder methods and one traditional method, as well as extensive ablation experiments with a simple spectral unmixing autoencoder, the article unravels the power of autoencoder methods and examines the impact of implementation details on the results.