% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Sedona:902093,
author = {Sedona, Rocco and Paris, Claudia and Cavallaro, Gabriele
and Bruzzone, Lorenzo and Riedel, Morris},
title = {{A} {H}igh-{P}erformance {M}ultispectral {A}daptation {GAN}
for {H}armonizing {D}ense {T}ime {S}eries of {L}andsat-8 and
{S}entinel-2 {I}mages},
journal = {IEEE journal of selected topics in applied earth
observations and remote sensing},
volume = {14},
issn = {2151-1535},
address = {New York, NY},
publisher = {IEEE},
reportid = {FZJ-2021-04028},
pages = {10134 - 10146},
year = {2021},
abstract = {The combination of data acquired by Landsat-8 and
Sentinel-2 earth observation missions produces dense time
series (TSs) of multispectral images that are essential for
monitoring the dynamics of land-cover and land-use classes
across the earth's surface with high temporal resolution.
However, the optical sensors of the two missions have
different spectral and spatial properties, thus they require
a harmonization processing step before they can be exploited
in remote sensing applications. In this work, we propose a
workflow-based on a deep learning approach to harmonize
these two products developed and deployed on an
high-performance computing environment. In particular, we
use a multispectral generative adversarial network with a
U-Net generator and a PatchGan discriminator to integrate
existing Landsat-8 TSs with data sensed by the Sentinel-2
mission. We show a qualitative and quantitative comparison
with an existing physical method [National Aeronautics and
Space Administration (NASA) Harmonized Landsat and Sentinel
(HLS)] and analyze original and generated data in different
experimental setups with the support of spectral distortion
metrics. To demonstrate the effectiveness of the proposed
approach, a crop type mapping task is addressed using the
harmonized dense TS of images, which achieved an overall
accuracy of $87.83\%$ compared to $81.66\%$ of the
state-of-the-art method.},
cin = {JSC},
ddc = {520},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
and Research Groups (POF4-511) / AISee - AI- and
Simulation-Based Engineering at Exascale (951733) / DEEP-EST
- DEEP - Extreme Scale Technologies (754304) / ADMIRE -
Adaptive multi-tier intelligent data manager for Exascale
(956748)},
pid = {G:(DE-HGF)POF4-5112 / G:(EU-Grant)951733 /
G:(EU-Grant)754304 / G:(EU-Grant)956748},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000707442300013},
doi = {10.1109/JSTARS.2021.3115604},
url = {https://juser.fz-juelich.de/record/902093},
}