.svg)
Search The Site
.svg)
Search The Site
Earth Observation (EO) data are increasingly central to Big Data research and practice. Modern satellite constellations collect massive volumes of heterogeneous imagery every day at varying spatial, spectral, and temporal resolutions and with global coverage. From multispectral and hyperspectral missions (Sentinel-2, Landsat-9, PRISMA, EnMAP) to Synthetic Aperture Radar (Sentinel-1, COSMO-SkyMed) and thermal sensors, EO provides a continuously growing stream of observations that must be managed, fused, and analyzed at scale.
The EO4CUR 2026 workshop brings together researchers and practitioners working at the intersection of EO, Big Data systems, machine learning, and operational resilience applications. The workshop focuses on scalable EO data processing, multimodal fusion, foundation models, federated learning, and reproducible cloud-native pipelines for climate and urban resilience.
EO4CUR 2026 will provide an informal and vibrant forum for discussing emerging challenges, sharing practical development experiences, and fostering collaboration across the remote sensing, geospatial AI, and Big Data communities.
Main Goals:
EO4CUR welcomes original research contributions, applied papers, benchmark studies, dataset papers, system demonstrations, and position papers on, but not limited to:
•Big EO data infrastructure: scalable cloud pipelines, STAC/COG/Zarr-based workflows, distributed EO data management, indexing, compression, and retrieval
•Distributed and stream processing: real-time and near-real-time EO analytics, streaming architectures for satellite data, edge-cloud continuum for EO
•Multi-sensor and multimodal fusion: multi-resolution, multi-temporal, and cross-modal fusion of optical, SAR, hyperspectral, and thermal data
•Foundation models and self-supervised learning for EO: large-scale pre-training on EO archives, transfer learning, multi-modal EO transformers
•Resilient mobility and transportation: EO-driven analytics for disaster-resilient transit, evacuation routing, and monitoring of critical transport infrastructure
•Federated and privacy-preserving learning: federated learning across distributed EO data silos, differential privacy for geospatial AI
•Benchmarks and reproducibility: curated EO datasets, open-source toolchains, FAIR data principles, standard evaluation protocols for EO tasks
•Climate and urban risk analytics: EO-based flood, wildfire, windstorm, landslide, and urban heat island mapping; exposure and vulnerability modeling; infrastructure risk assessment
•Causal and scenario modeling: what-if analyses, digital twins, scenario-driven resilience assessment
•Decision support and early-warning systems: EO-driven dashboards, early-warning pipelines, evidence-based adaptation planning
•Integration with heterogeneous sources: fusion of EO with in-situ sensor networks, mobility traces, OpenStreetMap, and administrative/census data
•Explainable and trustworthy AI for EO: uncertainty quantification, model interpretability, bias in EO-based models
•Operational case studies: industrial deployments, public-sector pilots, and lessons learned from production-scale EO systems
Committee
Affiliation: Latitudo 40, Naples, ItalyData ScientistEO for climate and urban resilience; co-organizer of FLUIDHRAAI 2025 and FL-on-BigData@IEEE BigData 2024
✓diletta.chiaro@latitudo40.com
Affiliation: Latitudo 40, Naples, ItalyHead of Data Science — deep learning for multispectral imagery, land-surface temperature downscaling, scalable urban thermal comfort modeling
✓ paolo.depiano@latitudo40.com
Affiliation: Oak Ridge National Laboratory, Oak Ridge, TN, USAR&D Associate, Geospatial Data Modeling group — deep learning for population, built environment, and energy infrastructure; publications in Nature, IEEE BigData, Computers, Environment and Urban Systems
Affiliation: Univ. Gustave Eiffel / ENTPE, Lyon, FranceSenior Researcher / Research Director in Computer Science for Urban Mobility — multi-source mobility data fusion, multimodal demand modeling, resilience of interdependent urban systems under disruptive conditions
Affiliation: UC Berkeley / LBNL, Berkeley, CA, USAProfessor of Civil & Environmental Engineering and City & Regional Planning; Fellow of the Network Science Society — urban sciences, human mobility, and transportation networks; data-driven tools for resilient urban solutions
Call for papers released — TBA
Paper submission deadlines — TBA
Notification of acceptance — TBA
Camera-ready & author registration — TBA
Workshop date — TBA
EO4CUR 2026 welcomes the following contribution types:
• Full research papers — original research results
• Applied & industry papers — real-world deployments and case studies
•Benchmark & dataset papers — curated datasets and evaluation protocols
• Short demo papers — system demonstrations (8 min + 2 min Q&A)
•Position papers — open challenges and research agendas
Submissions must follow the IEEE Big Data formatting guidelines. All papers will undergo double-blind peer review. Accepted papers will appear in the IEEE Big Data 2026 Workshop Proceedings.Authors of selected high-quality papers may be invited to extend their work for a special issue in a relevant journal (under negotiation).
Affiliation: Latitudo 40, Naples, Italy — Data Scientist
✓diletta.chiaro@latitudo40.com
Affiliation: Latitudo 40, Naples, Italy — Head of Data Science
✓paolo.depiano@latitudo40.com
Latitudo 40 is an innovative startup in the field of Earth Observation, born from the passion, expertise, and experience of a team united by a common goal: to improve the planet through satellite technologies. We define ourselves as a lean organization, basing our success on the principles of user-centered design.
