Remote Sensing (RS) has become an indispensable cornerstone for quantifying, monitoring,
and predicting Earth\u2019s environmental dynamics. Rapid technological progress is reflected in
an expanding global ecosystem of multi-scale observations, spanning ground-based
instruments, Unmanned Aerial Vehicles (UAVs), airborne campaigns, and satellite
constellations.
However, the exponential growth in the volume, velocity, and variety of geospatial big data
presents fundamental computational bottlenecks. Transforming these raw observations into
reliable, actionable information requires next-generation algorithms, including machine
learning (ML) and computer vision architectures. Furthermore, developing and
benchmarking these models relies heavily on the availability of high-quality, openly
accessible reference datasets. Finally, executing these workflows at scale demands efficient,
interoperable, and reproducible tools built on open-source software, cloud computing
environments, and high-performance computing (HPC) infrastructures.
This session invites contributions addressing the modern geocomputational challenges of
visualizing, processing, and analyzing big remote sensing data. We welcome submissions
covering algorithmic innovations, open hardware\/software tools, and benchmark datasets
that advance real-world remote sensing applications.<\/p>\n\n\n\n
List of topics:<\/strong><\/p>\n\n\n\n Dr. George P. Petropoulos <\/strong>(MSc, PhD), Associate Professor of Geoinformatics, Dr. Stefanos Georganos<\/strong>, Karlstads Universitet, Karlstad, Sweden\n
Organizers<\/h4>\n\n\n\n
Department of Geography, Harokopio University of Athens, Eleftheriou Venizelou
Ave., 70, GR-176 76, Athens, Greece (gpetropoulos@hua.gr<\/a>)
<\/p>\n\n\n\n
(stefanos.georganos@kau.se<\/a>)
<\/p>\n\n\n\n