Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensing

TL;DR

This paper discusses the integration of non-convex modeling techniques with hyperspectral remote sensing to enhance interpretability and handle complex data, addressing challenges of traditional convex models in processing high-dimensional spectral information.

Contribution

It introduces the application of non-convex modeling in hyperspectral AI, demonstrating its potential to improve interpretability and effectiveness over convex optimization methods.

Findings

Non-convex models better capture complex spectral variabilities.

Enhanced interpretability of hyperspectral data analysis.

Potential for more accurate and efficient remote sensing applications.

Abstract

Hyperspectral imaging, also known as image spectrometry, is a landmark technique in geoscience and remote sensing (RS). In the past decade, enormous efforts have been made to process and analyze these hyperspectral (HS) products mainly by means of seasoned experts. However, with the ever-growing volume of data, the bulk of costs in manpower and material resources poses new challenges on reducing the burden of manual labor and improving efficiency. For this reason, it is, therefore, urgent to develop more intelligent and automatic approaches for various HS RS applications. Machine learning (ML) tools with convex optimization have successfully undertaken the tasks of numerous artificial intelligence (AI)-related applications. However, their ability in handling complex practical problems remains limited, particularly for HS data, due to the effects of various spectral variabilities in the process of HS imaging and the complexity and redundancy of higher dimensional HS signals. Compared to the convex models, non-convex modeling, which is capable of characterizing more complex real scenes and providing the model interpretability technically and theoretically, has been proven to be a feasible solution to reduce the gap between challenging HS vision tasks and currently advanced intelligent data processing models.