BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Embed2Scale - ECPv6.17.0//NONSGML v1.0//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-ORIGINAL-URL:https://embed2scale.eu X-WR-CALDESC:Events for Embed2Scale REFRESH-INTERVAL;VALUE=DURATION:PT1H X-Robots-Tag:noindex X-PUBLISHED-TTL:PT1H BEGIN:VTIMEZONE TZID:UTC BEGIN:STANDARD TZOFFSETFROM:+0000 TZOFFSETTO:+0000 TZNAME:UTC DTSTART:20250101T000000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTART;TZID=UTC:20260119T100000 DTEND;TZID=UTC:20260119T113000 DTSTAMP:20260109T104648Z CREATED:20251209T144516Z LAST-MODIFIED:20260109T104648Z UID:10000014-1768816800-1768822200@embed2scale.eu SUMMARY:Advancing AI in Space Downstream Applications – EUSPA AI Week DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n\n\n\nOn 19 January 2026 (10:15–11:30 CET)\, join the “Advancing AI in Space Downstream Applications” online workshop\, part of EUSPA AI Week\, to discover how AI-driven projects are enhancing space downstream services. \n\n\n\nEmbed2Scale will be represented by Conrad Albrecht (DLR)\, who will present the latest AI developments emerging from the project. \n\n\n\nJoin the session URL:https://embed2scale.eu/event/advancing-ai-in-space-downstream-applications-euspa-ai-week/ CATEGORIES:Event ATTACH;FMTTYPE=image/png:https://embed2scale.eu/wp-content/uploads/2025/12/EUSPA-AI-WEEK-DAY-1-Downstream-apps-copy.png END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260225T140000 DTEND;TZID=UTC:20260225T153000 DTSTAMP:20260127T151510Z CREATED:20260112T141404Z LAST-MODIFIED:20260127T151510Z UID:10000016-1772028000-1772033400@embed2scale.eu SUMMARY:Embed2Scale session @AI4Good: Embedding workflows for Earth Observation tasks DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n\n\n\nThis workshop\, with Embed2Scale expert Isabelle Wittmann from IBM Research\, will demonstrate how modern Foundation Models can generate EO embeddings that preserve task-relevant information. These embeddings allow lightweight decoders up to two orders of magnitude smaller\, accelerating training and inference. \n\n\n\nIn two segments\, participants will:– Gain hands-on experience with TerraTorch\, an open-source library offering tools to extract embeddings via a no-code CLI\, adjust aggregation levels for different use cases\, visualize and analyse embedding properties and run complete workflows for downstream tasks.– Be introduced to NeuCo-Bench\, a benchmarking framework from the Embed2Scale consortium. NeuCo-Bench enables rapid evaluation of embeddings across diverse tasks within seconds\, requiring no prior setup. \n\n\n\nThe workshop will conclude by integrating TerraTorch and NeuCo-Bench in a full workflow\, showcasing instant evaluation of generated embeddings. It highlights efficiency gains\, demonstrates practical workflows\, and shows how embeddings drastically reduce computation and training time\, with interactive demos ensuring participants leave with actionable skills for EO tasks. \n\n\n\nBy the end of this session\, participants will be able to:– Get an introduction to neural embeddings and their role in modern EO workflows.– Learn to extract EO embeddings for your data using TerraTorch’s no-/low-code CLI.– Benchmark embedding methods within seconds using NeuCo-Bench.– Build your own embedding downstream task workflows and integrate NeuCo-Bench evaluations into them. \n\n\n\nRegister for the AI for Good Workshop URL:https://embed2scale.eu/event/embedding-workflows-for-earth-observation-tasks/ CATEGORIES:Event ATTACH;FMTTYPE=image/png:https://embed2scale.eu/wp-content/uploads/2026/01/AI4Good-bannersession-250226.png END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260327T150000 DTEND;TZID=UTC:20260327T160000 DTSTAMP:20260331T093601Z CREATED:20260212T160757Z LAST-MODIFIED:20260331T093601Z UID:10000023-1774623600-1774627200@embed2scale.eu SUMMARY:Webinar: "Visual Prompting for Geospatial Image Segmentation based on Embedding Maps" DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n\n\n\nThe application of Foundation Models to Earth Observation (EO) data is often slowed down by complex data preparation for fine-tuning\, creating the need for more efficient adaptation strategies.  \n\n\n\nThis webinar features the Visual Prompting for Geospatial Image Segmentation (VP‑GIS)\, a framework that utilises high-dimensional embedding maps to guide zero-shot segmentation models toward domain-specific features. Rather than modifying model weights\, the VP‑GIS approach injects learnable visual prompts into the input space\, derived from the topological structures of pre-computed embedding manifolds. By aligning the visual prompts with the latent distribution of geospatial features (e.g.\, cosine similarity)\, the segmentation mask is created based on similarity scores between prompt and image embeddings. \n\n\n\nThe webinar showcases a working prototype demonstration\, explains its functionality and opens the discussion on future work. \n\n\n\nWatch the webinar URL:https://embed2scale.eu/event/visual-prompting-for-geospatial-image-segmentation-based-on-embedding-maps/ CATEGORIES:Event ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/02/Visual-Prompting-for-Geospatial-Image-Segmentation-based-on-Embedding-Maps_Web.jpg END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260424T150000 DTEND;TZID=UTC:20260424T160000 DTSTAMP:20260429T090814Z CREATED:20260212T160142Z LAST-MODIFIED:20260429T090814Z UID:10000022-1777042800-1777046400@embed2scale.eu SUMMARY:Webinar: "Embedding Space Metrics Constrained Fine-Tuning" DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n\n\nCEST \n\n\n\n\n\n\n\n\nWhile fine-tuning Geospatial Foundation Models (GFMs) has become the standard for domain adaptation\, it often leads to catastrophic forgetting or ‘representation drift\,’ where the model’s fundamental understanding of semantic relationships is warped. This webinar introduces Embedding Space Metrics Constrained Fine-Tuning (ESM-CFT)\, an optimisation method in the TerraTorch framework designed to preserve the structural integrity of the latent space during supervised fine-tuning. \n\n\n\nUnlike traditional methods that rely solely on cross-entropy loss\, ESM-CFT incorporates a geometric constraint based on distance metrics to ensure that the relative positioning of representations in the embedding space remains stable. \n\n\n\nThe webinar presents promising preliminary experimental results and opens the stage for discussion of future work. \n\n\n\nWatch the webinar URL:https://embed2scale.eu/event/webinar-embedding-space-metrics-constrained-fine-tuning/ CATEGORIES:Event ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/02/Embedding-Space-Metrics-Constrained-Fine-Tuning_Web-1-scaled.jpg END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260505T080000 DTEND;TZID=UTC:20260508T170000 DTSTAMP:20260626T123703Z CREATED:20260417T154108Z LAST-MODIFIED:20260626T123703Z UID:10000033-1777968000-1778259600@embed2scale.eu SUMMARY:EGU 2026 DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n \n \n December 15\, 2025 \n\n \n \n – \n \n \n December 19\, 2025 \n\n \n \n \n\n\n\n\nCEST \n\n\n\n\n\n\n\n\nEmbed2Scale partners Damien Robert and Jan Dirk Wegner (UZH) present their work at EGU2026\, showcasing the use case “Forest Biomass Disturbance Monitoring.” \n\n\n\nRead More URL:https://embed2scale.eu/event/egu-2026/ CATEGORIES:Event ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/04/egu-26.jpg END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260519T080000 DTEND;TZID=UTC:20260522T170000 DTSTAMP:20260626T123542Z CREATED:20260417T154436Z LAST-MODIFIED:20260626T123542Z UID:10000034-1779177600-1779469200@embed2scale.eu SUMMARY:2nd ESA-NASA Workshop on AI Foundation Model for Earth Observation DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n \n \n December 15\, 2025 \n\n \n \n – \n \n \n December 19\, 2025 \n\n \n \n \n\n\n\n\nGMT-5 \n\n\n\n\n\n\n\n\nAfter a successful first edition in 2025\, Embed2Scale took part again 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 deployment.Romeo Kienzler and Isabelle Wittmann from IBM Research represented Embed2Scale in Huntsville\, Alabama. They contributed with a half‑day workshop\, on May 22\, titled “Building Scalable AI EO Workflows: TerraTorch Embedding Workflows & TerraTorch Iterate for Zero‑Invasive HPO and NAS Hands‑On Session.” \n\n\n\nRead More URL:https://embed2scale.eu/event/2nd-esa-nasa-workshop-on-ai-foundation-model-for-earth-observation/ CATEGORIES:Event ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/04/ESA-NASA.jpg END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260603T080000 DTEND;TZID=UTC:20260607T170000 DTSTAMP:20260626T125544Z CREATED:20260417T154716Z LAST-MODIFIED:20260626T125544Z UID:10000035-1780473600-1780851600@embed2scale.eu SUMMARY:CVPR 2026 DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n \n \n December 15\, 2025 \n\n \n \n – \n \n \n December 19\, 2025 \n\n \n \n \n\n\n\n\nGMT-6 \n\n\n\n\n\n\n\n\nEarly June 2026\, Rikard Vinge (DLR) and Luis Gilch (IBM) represented the Embed2Scale consortium at CVPR EarthVision in Denver\, USA. This year\, three papers from and supported by Embed2Scale partners were accepted.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. \n\n\n\nRead More URL:https://embed2scale.eu/event/cvpr-2026/ CATEGORIES:Event ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/04/CVPR-2026.jpg END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260609T080000 DTEND;TZID=UTC:20260612T170000 DTSTAMP:20260626T122902Z CREATED:20260428T133918Z LAST-MODIFIED:20260626T122902Z UID:10000036-1780992000-1781283600@embed2scale.eu SUMMARY:High Performance and Disruptive Computing in Remote Sensing School 2026 DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n \n \n December 15\, 2025 \n\n \n \n – \n \n \n December 19\, 2025 \n\n \n \n \n\n\n\n\nCEST \n\n\n\n\n\n\n\n\nThe summer school is organised by the High-Performance and Disruptive Computing in Remote Sensing (HDCRS) Working Group. HDCRS is part of the IEEE Geoscience and Remote Sensing Society (GRSS)\, within the Earth Science Informatics (ESI) Technical Committee.The school is an opportunity to connect with students\, young professionals\, and senior researchers working in remote sensing and in interdisciplinary areas involving high‑performance and distributed computing\, disruptive computing approaches\, and parallel programming models using specialised hardware.Project partner FZJ presented the project\, with a focus on the use case “Crop Stress and Yield Early Detection”\, and provided hands‑on demonstrations. \n\n\n\nDiscover more URL:https://embed2scale.eu/event/high-performance-and-disruptive-computing-in-remote-sensing-school-2026/ CATEGORIES:Event ATTACH;FMTTYPE=image/png:https://embed2scale.eu/wp-content/uploads/2026/04/Screenshot-2026-04-28-153638.png END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260809T080000 DTEND;TZID=UTC:20260814T170000 DTSTAMP:20260729T102056Z CREATED:20260211T085312Z LAST-MODIFIED:20260729T102056Z UID:10000021-1786262400-1786726800@embed2scale.eu SUMMARY:IGARSS 2026 DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n\n\n\nOn August 9\, during IGARSS 2026\, Embed2Scale experts will deliver an introduction and hands‑on session on NeuCo‑Bench (https://github.com/embed2scale/NeuCo-Bench/tree/main)\, a benchmark framework that emerged from the 2025 CVPR EARTHVISION workshop (https://www.grss-ieee.org/events/earthvision-2025/?tab=challenge). NeuCo‑Bench is designed as an extendable\, community‑driven framework for evaluating neural compression and representation learning methods in the context of Earth Observation (EO)\, without requiring heavy compute resources. The growing volume and complexity of EO data calls for standardized\, scalable\, and reproducible tools that can assess the quality and utility of learned representations across diverse downstream tasks. NeuCo‑Bench and its associated Earth2Vec community (https://earth2vec.github.io)\, which grew out of the Horizon Europe project Embed2Scale\, address this need by offering a modular evaluation pipeline built around fixed‑size\, task‑agnostic embeddings. This enables researchers and practitioners to consistently compare neural compression methods. \n\n\n\nRead more URL:https://embed2scale.eu/event/igarss-2026/ CATEGORIES:Event ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/02/IGARSS-2026.jpg END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20260914T080000 DTEND;TZID=UTC:20260917T170000 DTSTAMP:20260428T134843Z CREATED:20260428T134841Z LAST-MODIFIED:20260428T134843Z UID:10000037-1789372800-1789664400@embed2scale.eu SUMMARY:SPIE Security + Defence DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n \n \n December 15\, 2025 \n\n \n \n – \n \n \n December 19\, 2025 \n\n \n \n \n\n\n\n\nCEST \n\n\n\n\n\n\n\n\nSPIE Security + Defence is the leading international conference for engineers and scientists involved in the latest developments in sensing\, data and signal analysis\, optronics\, quantum science\, optical technologies\, and funding programmes. \n\n\n\nRead More URL:https://embed2scale.eu/event/spie-security-defence/ CATEGORIES:Event ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/04/1000x600-ESI24-Security-Defence-1.jpg END:VEVENT BEGIN:VEVENT DTSTART;TZID=UTC:20261110T100000 DTEND;TZID=UTC:20261110T110000 DTSTAMP:20260727T133749Z CREATED:20260724T095428Z LAST-MODIFIED:20260727T133749Z UID:10000040-1794304800-1794308400@embed2scale.eu SUMMARY:Enhancing maritime domain awareness using AI and embeddings DESCRIPTION:Home » Event » Page 2\n\n\n\n\n\n\n\n\n\n\n\n\nAGU25\n\n\n\n\n\n\n\nCET \n\n\n\n\n\n\n\n\nThe webinar\, organised by SatCen\, showcases how the use of AI and latent spaces with Earth Observation (EO) data could improve the current practices of Maritime Domain Awareness (MDA). The study introduces a methodology that\, instead of detecting vessels using original Sentinel-1 and -2 imagery\, uses highly compressed embeddings derived from TerraMind\, a Geospatial Foundational Model (GFM) developed by IBM and ESA. Relying on a dataset of 100\,000 balanced embeddings\, this work demonstrates that critical MDA tasks can be performed using embeddings that are up to 100x smaller than the original data\, with an accuracy aligned to the one obtained with original images. The study will show the application of the methodology  on a large scale area\, represented by the Mediterranean Sea.  The webinar will collect feedback from the audience\, in order to foster discussions on potential applications\, align solutions with user needs\, and encourage the adoption of the pilot’s outcomes to address real-world scenarios. \n\n\n\nRead More URL:https://embed2scale.eu/event/enhancing-maritime-domain-awareness-using-ai-and-embeddings/ CATEGORIES:Event,Maritime Awareness UC Event ATTACH;FMTTYPE=image/jpeg:https://embed2scale.eu/wp-content/uploads/2026/07/Enhancing-Maritime-Domain-Awareness-using-AI-and-embeddings-scaled.jpg END:VEVENT END:VCALENDAR