1st Workshop on Advances in Representation Learning for Earth Observation

Call for Papers

Two submission tracks

Accepted contributions were presented as posters; authors could indicate interest in a 10-minute oral talk.

Timeline

Topics of Interest

• · Machine Learning and AI for EO — self-supervised, multimodal, domain-adaptive, continual/online learning, foundation models, human-in-the-loop, active learning
• · Physics-based and Hybrid Modeling — Radiative Transfer Models, hybrid AI–physics for parameter retrieval and uncertainty quantification
• · Ecology and Environmental Monitoring — land use/cover change, biodiversity, phenology, biomass, canopy height, soil/vegetation condition
• · Remote Sensing and Satellite Data Processing — multispectral, SAR, LiDAR, hyperspectral; multi-resolution fusion; temporal change detection; cross-sensor harmonization
• · Embeddings and Compression — learned representations, semantic compression for large EO archives
• · Earth Science Applications — geophysical parameter estimation, urban/rural mapping, geohazards (floods, landslides, volcanic activity)
• · Data Curation, Bias, and Accessibility — globally representative datasets, bias mitigation, open benchmarks
• · Technical and Use Case Innovations — novel architectures, training strategies, pipelines

• #1

  A decade of sea ice concentration retrieved from Sentinel-1

  Wulf et al.

  Paper Poster
• #2

  A self-supervised multi-source framework and architecture for generative cross-sensor harmonization

  Dauvilliers et al.

  Paper Poster
• #3

  A Vertical Vegetation Structure Model of Europe

  Zhang et al.

  Paper Poster
• #4

  Altimeter and velocity data fusion for enhanced spatiotemporal resolution of the Ice Sheet elevation

  Naylor et al.

  Paper Poster
• #5

  Beyond Building Footprints: Probing DINOv3 to Map Roof Material and Geometry

  Guthula et al.

  Paper Poster
• #6

  Collaborative Unpaired Multimodal Representation Learning for Satellite Imagery

  Maurya et al.

  Poster
• #7

  Cryo2S1: Cross-Sensor Representation Learning for Sea Ice Radar Freeboard and Leads in Sentinel-1 SAR

  Stokholm et al.

  Paper Poster
• #8

  EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?

  Adorni et al.

  Paper Poster
• #9

  Gold Exploration using Representations from a Multispectral Autoencoder

  Tsantalidou et al.

  Paper Poster
• #10

  GOMAA-Geo: Goal Modality Agnostic Active Geo-localization

  Sarkar et al.

  Paper Poster
• #11

  Harnessing Multi-Modal Co-learning for Missing Earth Observation Modalities

  Mena et al.

  Paper Poster
• #12

  HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification

  Stoimchev et al.

  Paper
• #13

  Latent Field Reduction of Earth Observation Foundation Model

  Uebbing et al.

  Paper Poster
• #14

  Learned Image Compression for Earth Observation: Implications for Downstream Segmentation Tasks

  Mollière et al.

  Paper Poster
• #15

  LEPA: Learning Geometric Equivariance in Earth Observation with a Predictive Architecture

  Scheurer et al.

  Paper
• #16

  Leveraging Compact Satellite Embeddings and Graph Neural Networks for Large-Scale Poverty Mapping

  Pettersson et al.

  Paper
• #17

  M3DRS: Multi-Modal Multispectral Dataset for Remote Sensing

  Li et al.

  Paper Poster
• #18

  MAPLE: Multi-Path Adaptive Propagation with Level-Aware Embeddings for Hierarchical Multi-Label Image Classification

  Koloski et al.

  Paper
• #19

  Mixture of Geographical Experts: Disentangling Earth

  Rangzan et al.

  Paper Poster
• #20

  NeurEO: Dissecting Earth Observation embeddings with computational neuroscience

  Plas et al.

  Paper
• #21

  On-the-Fly OVD Adaptation with FLAME: Few-shot Localization via Active Marginal-Samples Exploration

  Refael et al.

  Paper Poster
• #22

  Overlap-Free Modality Generalization in Remote Sensing Foundation Models

  Zhambulova et al.

  Paper Poster
• #23

  SatOSM: Training geospatial foundation models with the Earth's largest open ground truth

  Zhang et al.

  Paper Poster
• #24

  Scalable Geospatial Data Generation Using AlphaEarth Foundations

  Houriez et al.

  Paper Poster
• #25

  SenForFlood: A Global Dataset for Flood Mapping

  Matosak et al.

  Paper Poster
• #26

  SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation

  Cohrs et al.

  Paper Poster
• #27

  SkyCap: Bitemporal VHR Optical–SAR Quartets for Amplitude Change Detection and Foundation-Model Evaluation

  Weinmann et al.

  Paper Poster
• #28

  SuperF: Neural Implicit Fields for Multi-Image Super-Resolution

  Jyhne et al.

  Paper
• #29

  Towards Methane Detection On Board Satellites

  Chen et al.

  Paper Video
• #30

  Towards Large Scale Geostatistical Methane Monitoring with Part-based Object Detection

  Senneville et al.

  Paper
• #31

  MoTiF: a self-supervised model for multi-source forecasting with application to tropical cyclones

  Paper
• #32

  Open-Canopy: Towards Very High Resolution Forest Monitoring

  Fogel et al. (CVPR 2025)

  Paper
• #33

  Fused Foundation Model Embeddings for Earth Observation Compression: A Winning Solution to the Embed2Scale Challenge

  Kerekes et al.

  Paper Poster