We make history beneath the soil visible with modern space-science tools.
Preservation of archaeological heritage fails when sites are destroyed before being discovered. ARGEOS aims to prevent these losses by leveraging satellite imagery, machine learning and geospatial analysis. Our goal is the systematic detection of the hundreds of thousands of mounds, castles, monasteries and ancient settlements still waiting to be found across the world.
Within the next decade, to become the foundational discovery infrastructure for excavation institutions worldwide. A future in which every archaeologist can analyze their own research region at the click of a button.
Our methodology rests on peer-reviewed literature; results are always reported alongside confidence scores.
Customer data (KML, imagery, coordinates) is never shared with third parties under any circumstance.
Sensitive coordinates are delivered only to authorized institutions to prevent looting.
ARGEOS combines techniques from the open literature into a single production pipeline. Which models we use is proprietary; how we combine them is scientific.
Histogram, texture (LBP), shape (HOG), keypoint descriptors and modern deep-learning visual embeddings work together.
A dynamic tile cache operating in Web Mercator projection serves high-resolution imagery on a per-cell basis.
Open elevation data (Terrarium/SRTM/ASTER) is visualized around the pin with hillshade and a color map.
Non-Maximum Suppression removes duplicate detections from adjacent cells; only the best candidate reaches the expert.
We evaluate collaboration requests from universities, museums, excavation teams and national institutions. Apply for early access.
Application Form