IEEE Geoscience and Remote Sensing Magazine - June 2021 - 52

Interpretable
Hyperspectral
Artificial
Intelligence
When nonconvex modeling meets
hyperspectral remote sensing
DANFENG HONG, WEI HE, NAOTO YOKOYA,
JING YAO, LIANRU GAO, LIANGPEI ZHANG,
JOCELYN CHANUSSOT, AND
XIAO XIANG ZHU
©SHUTTERSTOCK.COM/STEFANO GARAU
H
yperspectral (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
Digital Object Identifier 10.1109/MGRS.2021.3064051
Date of current version: 6 April 2021
52
0274-6638/21©2021IEEE
challenging HS vision tasks and currently advanced intelligent
data processing models. This article mainly presents an
advanced and cutting-edge technical survey of nonconvex
modeling toward interpretable AI models covering a broad
scope in the following topics of HS RS:
◗ HS image restoration
◗ dimensionality reduction (DR)
◗ data fusion and enhancement
◗ spectral unmixing (SU)
◗ cross-modality learning (CML) for large-scale land cover
mapping.
Around these topics, we showcase the significance of
nonconvex techniques to bridge the gap between HS RS
and interpretable AI models with a brief introduction of the
research background and motivation, an emphasis on the
resulting methodological foundations and solution, and an
intuitive clarification of illustrative examples. At the end of
each topic, we also pose the remaining challenges on how
to completely model the issues of complex spectral vision
from the perspective of intelligent ML combined with physical
priors and numerical nonconvex modeling and accordingly
point out future research directions.
This article aims to create a good entry point for the advanced
literature of experienced researchers, Ph.D. students,
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE JUNE 2021
http://www.SHUTTERSTOCK.COM/STEFANO
IEEE Geoscience and Remote Sensing Magazine - June 2021

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - June 2021
