elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Accessibility | Contact | Deutsch
Fontsize: [-] Text [+]

Progress on benchmarking geospatial foundation models

Marszalek, Michael and Vinge, Rikard and Koch, Amelie and Wittmann, Isabelle and Albrecht, Conrad M (2025) Progress on benchmarking geospatial foundation models. DLR Wissens Austausch Workshops Machine Learning 11, 2025-10-28 - 2025-10-30, München, Deutschland.

[img] PDF - Only accessible within DLR
6MB

Abstract

We present our efforts to establish a framework to put the promise of geospatial foundation models to the test: the generation of general embeddings one may utilize for a wide range of downstream tasks. To that end we provide a diverse set of applications from agriculture monitoring to maritime awareness that we utilized as hidden downstream tasks for the 2025 CVPR EARTHVISION data challenge. As a result we introduce the NeuCo-Bench framework that intends to grow an "Earth2Vec" community around neural compression bringing together academia, government entities, and the corporate world.

Item URL in elib:https://elib.dlr.de/218360/
Document Type:Conference or Workshop Item (Poster)
Title:Progress on benchmarking geospatial foundation models
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Marszalek, MichaelUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Vinge, RikardUNSPECIFIEDhttps://orcid.org/0000-0002-7306-3403UNSPECIFIED
Koch, AmelieIBM Research ZurichUNSPECIFIEDUNSPECIFIED
Wittmann, IsabelleUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Albrecht, Conrad MUNSPECIFIEDhttps://orcid.org/0009-0009-2422-7289UNSPECIFIED
Date:29 October 2025
Refereed publication:No
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:Earth Observation, Neural Compression, compression for machines
Event Title:DLR Wissens Austausch Workshops Machine Learning 11
Event Location:München, Deutschland
Event Type:Workshop
Event Start Date:28 October 2025
Event End Date:30 October 2025
Organizer:German Aerospace Center (DLR)
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Optical remote sensing
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Vinge, Rikard
Deposited On:10 Nov 2025 12:00
Last Modified:18 Nov 2025 14:31

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
OpenAIRE Validator logo electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.