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…
Embed2Scale partners Damien Robert and Jan Dirk Wegner (UZH) will present their current work at EGU2026, showcasing the use case “Forest Biomass Disturbance Monitoring.” Their presentation, “Forest Disturbance Monitoring with Geospatial Foundation Models,” explores how embedding‑based workflows can support faster and more accessible detection of forest disturbances such as logging, storms, fires, pests, and disease…
Embed2Scale will be represented at IGARSS 2026 with a tutorial titled “A Hands-On Introduction to Benchmarking Neural Compression and Representation Learning for Earth Observation”, held on Sunday, 9 August 2026, from 8 a.m. to 5 p.m ET. The tutorial introduces NeuCo-Bench, an open benchmarking framework developed within Embed2Scale to evaluate neural compression and representation learning…
The Embed2Scale project has released TerraCodec, an open-source family of neural compression models designed for optical Earth observation data. Earth observation satellites continuously produce massive streams of multispectral and temporal imagery, creating growing challenges for storage, transmission, and large-scale analysis. TerraCodec addresses these challenges using neural compression models that encode multispectral imagery into compact latent…
The Embed2Scale consortium met in Ljubljana on 3 and 4 March for a two‑day general assembly hosted by project partner Sinergise, bringing partners together as the project moves through its third and final year. Across the meeting, partners reviewed recent progress and aligned on the next steps for the months ahead. Advisory Board members joined…
The Embed2Scale project has launched a TerraTorch extension designed to enable Earth Observation (EO) embedding workflows. The extension adds low‑code and no‑code tools to generate, analyse, and reuse EO embeddings across a wide range of downstream tasks. What the extension enables In typical TerraTorch workflows, models are trained end‑to‑end on raw imagery. The new embedding…
On 25 February 2026, Isabelle Wittman (IBM) will speak at the AI for Good GeoAI Workshop in a session dedicated to embedding‑based workflows for Earth Observation (EO) applications. She will introduce TerraTorch, an open‑source library designed to streamline the extraction and visualisation of EO embeddings, and NeuCo‑Bench, a benchmarking framework developed within Embed2Scale that enables…