elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Spatial Loss Function for Super-Resolution of Geoscientific Data

Dahal, Ashok und van den Bout, Bastian und van Westen, Cees und Nolde, Michael (2022) Spatial Loss Function for Super-Resolution of Geoscientific Data. ESA Living Planet Symposium, 23.-27. Mai 2022, Bonn.

Dieses Archiv kann nicht den Volltext zur Verfügung stellen.

Kurzfassung

Super Resolution is a method for artificially increasing the imaging system's resolution by post processing without having to collect new datasets. It is mostly developed and used in computer graphics by the computer science community for image and video enhancement due to its capacity to add spatial variations in the data and perform better than conventional interpolation methods such as bicubic interpolation been used extensively in the geoscience community. After the advancement of deep learning-based super-resolution methods in the 2010s, it has shown great potential for use in data scare regions where high-resolution geoscientific data are not available, and collection of such data is also not possible due to financial and technical reasons. Even though Super-Resolution is used geospatial data, the loss functions to optimize those models are mostly used as it is from computer vision, and they do not account for the spatial relationship between neighbouring pixels. For example, in the case of elevation data, the relative elevation between two pixels (slope) and their direction (aspect) is more important compared to absolute elevation in the case of geoscientific modelling. However, those relations which must be valid in the ground observation are not well considered in Super-Resolution of Geospatial data. Our research aims to develop a loss function that can respect the spatial relationship between pixel and its neighbours, representing the ground reality. In contrast to existing methods, these new loss functions are better in generating the geospatial datasets that can be further used in geoscientific analysis and modelling approaches rather than mere visualization. The developed loss function is tested with multiple super-resolution models, both generative adversarial networks and the end-to-end models trained with geoscientific data. Our research shows that using spatial relation aware loss function and the super-resolution model can better reconstruct the ground reality even though training them is more complex than using simple mean squared error loss functions. The use of such a novel loss function can also generate better terrain in the case of Digital Elevation Models, which can be observed in the slope and aspect of such datasets.

elib-URL des Eintrags:https://elib.dlr.de/186631/
Dokumentart:Konferenzbeitrag (Poster)
Titel:Spatial Loss Function for Super-Resolution of Geoscientific Data
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Dahal, Ashoka.dahal (at) utwente.nlNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
van den Bout, Bastianb.vandenbout (at) utwente.nlNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
van Westen, Ceesc.j.vanwesten (at) utwente.nlNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Nolde, Michaelmichael.nolde (at) dlr.dehttps://orcid.org/0000-0002-6981-9730NICHT SPEZIFIZIERT
Datum:24 Mai 2022
Referierte Publikation:Nein
Open Access:Nein
Gold Open Access:Nein
In SCOPUS:Nein
In ISI Web of Science:Nein
Seitenbereich:Seite 1
Status:veröffentlicht
Stichwörter:Super Resolution, Spatial Loss Function, Digital Elevation Model, Deep Learning
Veranstaltungstitel:ESA Living Planet Symposium
Veranstaltungsort:Bonn
Veranstaltungsart:internationale Konferenz
Veranstaltungsdatum:23.-27. Mai 2022
Veranstalter :European Space Agency
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Erdbeobachtung
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R EO - Erdbeobachtung
DLR - Teilgebiet (Projekt, Vorhaben):R - Geowissenschaftl. Fernerkundungs- und GIS-Verfahren, R - Fernerkundung u. Geoforschung
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Deutsches Fernerkundungsdatenzentrum > Georisiken und zivile Sicherheit
Hinterlegt von: Nolde, Dr. Michael
Hinterlegt am:27 Jun 2022 09:22
Letzte Änderung:27 Jun 2022 09:22

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.