News

Embed2Scale partner Dr. Conrad M. Albrecht (University of Oxford) recently presented a colloquium titled “Self-Supervised Learning for Spectral Remote Sensing: Opportunities and Limitations” at the Max Planck Institute for Biogeochemistry. The talk addressed how the rapid emergence of AI “Foundation Models” is reshaping the remote sensing landscape. With specialized hyperspectral satellite missions (such as DLR’s…

As satellite constellation revisit rates increase, the sheer volume of high-resolution Synthetic Aperture Radar (SAR) imagery creates a significant “data gravity” bottleneck for real-time monitoring. Transferring and processing uncompressed image tiles across distributed cloud architectures or to remote operational nodes causes critical latency in time-sensitive applications like maritime domain awareness (MDA). To address this challenge,…

Addressing the exponential growth of weather and climate model data requires urgent solutions that safely reduce file sizes while preserving critical data properties. To tackle this challenge, the ESiWACE3 Data Compression Hackathon brought together climate researchers, modeling teams, and data compression developers in a hybrid event featuring experts from DKRZ, NVIDIA Earth-2, the University of…

At IGARSS 2026, Embed2Scale (E2S) showcased how open datasets, neural compression, reproducible benchmarking and community collaboration can help turn Earth observation embeddings into practical, scalable tools.  A full day focused on neural compression and representation learning  On Aug 9, Conrad M. Albrecht (University of Oxford) orchestrated the full-day tutorial “A Hands-On Introduction to Benchmarking Neural…

The Embed2Scale project is pleased to support the next Geo-Embeddings Sprint, taking place on 27–28 October 2026 in Zürich, Switzerland. Hosted by IBM and organised together with Cloud-Native Geospatial (CNG), Clark University, and Planet, the event will bring together leading researchers, foundation model developers, data providers, and Earth Observation (EO) practitioners to advance the future of geospatial AI.  The second Geo-Embeddings Sprint builds…

At the CVPR EarthVision Workshop 2026, and soon at IGARSS 2026, the Embed2Scale consortium presented NeuCo‑Bench, a model‑agnostic framework designed to address the often fragmented benchmarking landscape of Geospatial Foundation Models and other embedding approaches in Earth Observation (EO). While the EO community increasingly adopts embedding‑based methods for their efficiency and versatility, the lack of…

In late May, members of the Embed2Scale consortium from IBM Research and UZH attended the ESA–NASA Workshop on Foundation Models for Earth Observation. While foundation models were naturally central to the agenda, one theme surfaced repeatedly across talks, discussions, and hallway conversations: geospatial embeddings have become a major topic in the EO community. What stood…

The High‑Performance and Disruptive Computing in Remote Sensing (HDCRS) Summer School 2026 will feature a full workshop day led by Forschungszentrum Jülich (FZJ) on 11 June 2026, focusing on Geospatial Foundation Models and hands‑on experimentation with TerraMind for downstream Earth observation tasks.   The summer school is organised by the High‑Performance and Disruptive Computing in Remote…

Embed2Scale partners will take part in CVPR EarthVision 2026 this June in Denver, USA. The event brings together the Earth observation, computer vision, and machine learning communities to advance scalable and trustworthy analysis of large‑scale geospatial data for environmental and societal applications. Last year, Embed2Scale organised the Embed2Scale Data Challenge at CVPR EarthVision. This year,…

After a successful first edition in 2025, Embed2Scale will again take part in the second ESA/NASA EO Foundation Models Workshop. The event brings together the Earth observation and AI foundation model communities to advance scalable, trustworthy, and operational AI systems for EO, with this year’s programme focusing on benchmarking, multimodal modelling, efficient adaptation, and real‑world…