%0 Conference Paper
%A Buffat, Jim
%A Pato, Miguel
%A Alonso, Kevin
%A Auer, Stefan
%A Carmona, Emiliano
%A Maier, Stefan
%A Müller, Rupert
%A Rademske, Patrick
%A Rascher, Uwe
%A Scharr, Hanno
%T DEEP LEARNING BASED PREDICTION OF SUN-INDUCED FLUORESCENCE FROM HYPLANT IMAGERY
%I IEEE
%M FZJ-2023-04569
%P 2993 - 2996
%D 2023
%Z This work is funded by the Helmholtz Initiative and Networking Fund, Helmholtz AI, Deutsches Zentrum für Luft- und Raumfahrt and Forschungszentrum Jülich GmbH. The authors gratefully acknowledge the computing time granted by the JARA Vergabegremium and provided on the JARA Partition part of the supercomputer JURECA [1] at Forschungszentrum Jülich.Jülch Supercomputing Centre, “JURECA: Data Centric and Booster Modules implementing the Modular Supercomputing Architecture at Jülch Supercomputing Centre,” Journal of large-scale research facilities, vol. 7, no. A182, 2021. [Online]. Available: http://dx.doi.org/10.17815/jlsrf-7-182
%X The retrieval of sun-induced fluorescence (SIF) from hyper- spectral imagery is an ill-posed problem that has been tackled in different ways. We present a novel retrieval method com- bining semi-supervised deep learning with an existing spec- tral fitting method. A validation study with in-situ SIF mea- surements shows high sensitivity of the deep learning method to SIF changes even though systematic shifts deteriorate its absolute prediction accuracy. A detailed analysis of diurnal SIF dynamics and SIF prediction in topographically variable terrain highlights the benefits of this deep learning approach.
%B International Geoscience and Remote Sensing Symposium
%C 21 Jun 2023 - 21 Jun 2023, Pasadena (USA)
Y2 21 Jun 2023 - 21 Jun 2023
M2 Pasadena, USA
%F PUB:(DE-HGF)8
%9 Contribution to a conference proceedings
%U <Go to ISI:>//WOS:001098971603050
%R 10.1109/IGARSS52108.2023.10282828
%U https://juser.fz-juelich.de/record/1018125