% 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{Morata:916745,
author = {Morata, Miguel and Siegmann, Bastian and Perez-Suay, Adrian
and Garcia-Soria, Jose Luis and Rivera-Caicedo, Juan Pablo
and Verrelst, Jochem},
title = {{N}eural {N}etwork {E}mulation of {S}ynthetic
{H}yperspectral {S}entinel-2-like {I}magery with
{U}ncertainty},
journal = {IEEE journal of selected topics in applied earth
observations and remote sensing},
volume = {16},
issn = {1939-1404},
address = {New York, NY},
publisher = {IEEE},
reportid = {FZJ-2023-00073},
pages = {762-772},
year = {2023},
abstract = {Hyperspectral satellite imagery provides highly-resolved
spectral information for large areas and can provide vital
information. However, only a few imaging spectrometer
missions are currently in operation. Aiming to generate
synthetic satellite-based hyperspectral imagery potentially
covering any region, we explored the possibility of applying
statistical learning, i.e. emulation. Based on the
relationship of a Sentinel-2 (S2) scene and a hyperspectral
HyPlant airborne image, this work demonstrates the
possibility to emulate a hyperspectral S2-like image. We
tested the role of different machine learning regression
algorithms (MLRA) and varied the image-extracted training
dataset size. We found superior performance of Neural
Network (NN) as opposed to the other algorithms when trained
with large datasets (up to 100'000 samples). The developed
emulator was then applied to the L2A (bottom-of-atmosphere
reflectance) S2 subset, and the obtained S2-like
hyperspectral reflectance scene was evaluated. The
validation of emulated against reference spectra
demonstrated the potential of the technique. R2 values
between 0.75-0.9 and NRMSE between $2-5\%$ across the full
402-2356 nm range were obtained. Moreover, epistemic
uncertainty is obtained using the dropout technique,
revealing spatial fidelity of the emulated scene. We
obtained highest SD values of 0.05 (CV of $8\%)$ in clouds
and values below 0.01 (CV of $7\%)$ in vegetation land
covers. Finally, the emulator was applied to an entire S2
tile (5490x5490 pixels) to generate a hyperspectral
reflectance datacube with the texture of S2 (60Gb, at a
speed of 0.14sec/10000pixels). As the emulator can convert
any S2 tile into a hyperspectral image, such scenes give
perspectives how future satellite imaging spectroscopy will
look like.},
cin = {IBG-2},
ddc = {520},
cid = {I:(DE-Juel1)IBG-2-20101118},
pnm = {2173 - Agro-biogeosystems: controls, feedbacks and impact
(POF4-217)},
pid = {G:(DE-HGF)POF4-2173},
typ = {PUB:(DE-HGF)16},
pubmed = {36644656},
UT = {WOS:000981757000002},
doi = {10.1109/JSTARS.2022.3231380},
url = {https://juser.fz-juelich.de/record/916745},
}