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

Leveraging Neural Compression for Earth Observation

Wittmann, Isabelle und Jakubik, Johannes und Gomes, Carlos und Blumenstiel, Benedikt und Brunschwiler, Thomas und Albrecht, Conrad M (2025) Leveraging Neural Compression for Earth Observation. 2025 ESA Living Planet Symposium, 2025-06-23 - 2025-06-27, Vienna, Austria.

Dieses Archiv kann nicht den Volltext zur Verfügung stellen.

Offizielle URL: https://lps25.esa.int/programme/programme-session/?id=3B6EF15D-E53F-4BAA-8C8C-F6F7C253C8F0&presentationId=427577B0-BEA3-4BBA-A2BC-8CC374338FC6

Kurzfassung

The exponential growth of satellite data marks a new era in Earth observation (EO) and enables a better understanding of our planet, with applications such as crop mapping and the detection of natural hazards. However, the sheer volume of this data poses challenges for transmission, storage, and accessibility, ultimately limiting its usability. Image compression offers ways to efficiently store and transfer data. In recent years, data driven neural compression approaches have demonstrated improved performance in compressing images, compared to handcrafted algorithms (e.g., JPEG). Our work builds on that progress and focuses on the application of neural compression specifically on satellite images. We explore adaptations of neural compression models that leverage EO-specific characteristics including location and timestamp information. This metadata may offer potential to tailor and improve compression performance. Our research reveals fundamental differences in the input pixel distribution and entropy of satellite images compared to standard natural image datasets. Interstingly, EO data reveils a substantially lower entropy compared to ImageNet samples. We demonstrate that applying neural compression to EO data improves compression performance within a few hours of training, requiring lower bit rates and fewer parameters than models trained on natural images. We further investigate the effect of ingesting encoded metadata information on neural compression techniques. Our results suggest that neural models extract enough image features to make additional spatial and metadata inputs redundant. Finally, we compare specialized neural compression models, trained on specific seasons or geolocations, with general neural EO compressor trained on the entire EO data set. Our results indicate that although the specialized models are learning on different input distributions, general neural EO compressors are still beneficial in many cases. In low-entropy, strongly skewed distribution scenarios, specialized model outperform general neural EO compressors. These results underline that the specific nature of EO data may benefit from individual processing for certain parts of the data, while the majority can be compressed with a general neural EO compressor. Overall, we demonstrate superior perfromance of neural compressors relative to classical methods. Further, our findings suggest that tailoring neural compression to EO data partly requires specialization, as significant differences in input distribution and entropy can enable more specialized compression. We show that the extent to which neural compression models benefit from dataset diversity versus specialization is an essential trade-off, which requires further research from the EO domain. While tailoring neural compression to EO is generally challenging, we show that low entropy image samples allow for lightweight, specialized compressors, which can be very helpful for different EO scenes such as oceans, deserts or forests.

elib-URL des Eintrags:https://elib.dlr.de/214937/
Dokumentart:Konferenzbeitrag (Vortrag)
Titel:Leveraging Neural Compression for Earth Observation
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Wittmann, IsabelleIBM Research EuropeNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Jakubik, JohannesIBM Research EuropeNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Gomes, CarlosIBM Research EuropeNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Blumenstiel, BenediktIBM Research EuropeNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Brunschwiler, ThomasIBM Research EuropeNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Albrecht, Conrad MConrad.Albrecht (at) dlr.dehttps://orcid.org/0009-0009-2422-7289NICHT SPEZIFIZIERT
Datum:28 Juni 2025
Referierte Publikation:Nein
Open Access:Nein
Gold Open Access:Nein
In SCOPUS:Nein
In ISI Web of Science:Nein
Status:veröffentlicht
Stichwörter:neural compression, Earth observation
Veranstaltungstitel:2025 ESA Living Planet Symposium
Veranstaltungsort:Vienna, Austria
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:23 Juni 2025
Veranstaltungsende:27 Juni 2025
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 - Künstliche Intelligenz, R - Optische Fernerkundung
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Methodik der Fernerkundung > EO Data Science
Hinterlegt von: Albrecht, Conrad M
Hinterlegt am:15 Jul 2025 12:30
Letzte Änderung:06 Aug 2025 11:13

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

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