News

As part of our commitment to advancing AI-driven geospatial analytics, the Embed2Scale consortium is thrilled to organize the 2025 CVPR EarthVision workshop Data Challenge. This challenge invites researchers and AI practitioners to develop cutting-edge Lossy Neural Compression for Geospatial Analytics techniques, optimizing how Earth Observation (EO) data is processed and utilized. Co-sponsored by Embed2Scale and…

We are excited to announce that the research paper “Lossy Neural Compression for Geospatial Analytics: A Review“, co-authored by the partners of the entire Embed2Scale consortium, has been accepted for publication in the prestigious IEEE Geoscience and Remote Sensing Magazine (GRSM) and will be officially released in June 2025. About the Paper With the explosion…

On the 4th & 5th of February 2025, the Embed2Scale consortium convened in Oxford, UK, for a two-day plenary meeting, hosted at the Atmospheric, Oceanic and Planetary Physics Clarendon Laboratory of the University of Oxford. This gathering marked a key milestone in the project’s journey, bringing together the project’s partners from academia, industry and research…

For more detailed information about the workshop The upcoming ESA-NASA International Workshop on AI Foundation Models for Earth Observation, scheduled for May 5-7, 2025, at ESA-ESRIN in Frascati, Italy, represents a significant milestone in the integration of advanced AI methodologies into geospatial and Earth science research. This collaborative event aims to unite experts from various…

Embed2Scale was present at SatSummit 2024, held on 18-19 November in Lisbon, Portugal. This annual event gathers a global audience of satellite and Earth Observation (EO) experts, bringing together industry leaders, researchers and innovators to discuss the most pressing challenges and opportunities in space-based technologies. As part of this event, Thomas Brunschwiler from IBM Research,…

We’re thrilled to announce the release of our introductory video for Embed2Scale! This new video provides an inside look at the project’s mission to revolutionise Earth Observation (EO) data access and processing. By combining state-of-the-art AI compression and high-performance computing, Embed2Scale aims to make geospatial data more accessible and efficient than ever before. The video…

We are excited to announce that the Embed2Scale project has been selected for a session at the upcoming EGU General Assembly 2025, one of the leading geoscience conferences in Europe, which will take place in Vienna, Austria & online on 27 April–2 May 2025.  Our session, titled “Pre-training Strategies for Geospatial Foundation Models” will showcase…

Embed2Scale’s partner IBM Research represented  FAST-EO at the AI+Environment EcoHackathon kickoff, organised by the ETH AI Center and GainForest. The EcoHackathon is focused on sparking interest in environmental conservation and developing solutions to tackle pressing environmental challenges using AI and data visualisation, with a specific aim towards the preservation of the Amazon Rainforest. During the…

For more details on this work and to explore the full paper, visit our Publications section. The recent paper titled “Multi-Spectral Remote Sensing Image Retrieval Using Geospatial Foundation Models“ marks an advancement in the accessibility and efficiency of satellite imagery analysis. Authored by a team from IBM Research – Europe, including Benedikt Blumenstiel, Viktoria Moor,…

The full paper, detailing the NEC methodology and its implications for future EO systems, can be accessed here: We are thrilled to announce an initial milestone in the Embed2Scale project with the presentation of a research paper at the prestigious EGU General Assembly 2024. Authored by Carlos Gomes and Thomas Brunschwiler from IBM Research –…