Interpretable Hyperspectral Artificial Intelligence: When nonconvex modeling meets hyperspectral remote sensing

Hyperspectral (HS) 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 HS products, mainly by seasoned experts. However, with an ever-growing volume of data, the bulk of costs in manpower and material resources poses new challenges for reducing the burden of manual labor and improving efficiency. For this reason, it is urgent that more intelligent and automatic approaches for various HS RS applications be developed. Machine learning (ML) tools with convex optimization have successfully undertaken the tasks of numerous artificial intelligence (AI)-related applications; however, their ability to handle 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 convex models, nonconvex modeling, which is capable of characterizing more complex real scenes and providing model interpretability technically and theoretically, has proven to be a feasible solution that reduces the gap between challenging HS vision tasks and currently advanced intelligent data processing models.

Automated summary

Hyperspectral imaging, a landmark technique in geoscience and remote sensing, has posed challenges in processing and analyzing the data due to the large manpower and material costs involved. Developing more intelligent and automatic approaches is urgently needed to reduce manual labor burden and improve efficiency. Nonconvex modeling has shown promise in bridging the gap between challenging hyperspectral vision tasks and current advanced data processing models.