{"id":38841,"date":"2026-09-05T14:19:26","date_gmt":"2026-09-05T14:19:26","guid":{"rendered":"https:\/\/zephyros.solutions\/projects\/ai4eo\/"},"modified":"2026-09-05T15:21:05","modified_gmt":"2026-09-05T15:21:05","slug":"ai4eo","status":"publish","type":"page","link":"https:\/\/zephyros.solutions\/it\/projects\/ai4eo\/","title":{"rendered":"AI4EO: building footprints from space"},"content":{"rendered":"
\n
\"Radar<\/a>
Andrey Malakhov & Alessandro Patruno \/ Team Zephyros. ESA \u03a6-lab<\/a> Open full-size image \u2197<\/a><\/figcaption><\/figure>\n\n\n
\n

Model output<\/p>\n\n\n

Mapping the built environment.<\/h2>\n\n\n

Green contours show predicted building areas in radar imagery over Kirkouk, Iraq. These are Team Zephyros results published in ESA \u03a6-lab\u2019s challenge report.<\/p>\n\n<\/div>\n\n<\/div>\n\n\n

\n
\n

The challenge<\/h2>\n\n\n

Humanitarian planning needs reliable information about the built environment. The AI4EO challenge with UNOSAT addressed building-footprint mapping in Iraq, in support of reconstruction and census planning.<\/p>\n\n\n

Our contribution<\/h2>\n\n\n

Alessandro Patruno and Andrey Malakhov participated as Team Zephyros in the AI4EO initiative. Their work explored machine-learning workflows for distinguishing buildings from their surroundings in satellite data.<\/p>\n\n\n

Technical approach<\/h2>\n\n\n

Building-footprint segmentation using Sentinel-1 radar data in VV\/VH polarisations and WorldView optical imagery. The task connects image processing, machine learning and geospatial analysis across large areas.<\/p>\n\n\n

Why it matters<\/h2>\n\n\n

The work demonstrates how scientific computing can turn Earth-observation imagery into information relevant to humanitarian and environmental questions. ESA \u03a6-lab\u2019s challenge report credits Team Zephyros for example predictions over Kirkouk and Baghdad.<\/p>\n\n\n

A closer look at the results<\/h2>\n\n\n
\"Radar<\/a>
A second prediction over Baghdad. Andrey Malakhov & Alessandro Patruno \/ Team Zephyros. ESA \u03a6-lab<\/a> Open full-size figure \u2197<\/a><\/figcaption><\/figure>\n\n<\/div>\n\n\n
\n

Initiative<\/h2>\n\n\n

AI4EO Challenge with UNOSAT \/ ESA \u03a6-lab<\/p>\n\n\n

Period<\/h2>\n\n\n

2020 initiative<\/p>\n\n\n

People<\/h2>\n\n\n

Alessandro Patruno
Andrey Malakhov<\/p>\n\n\n

Methods<\/h2>\n\n\n

Semantic segmentation
Sentinel-1 VV\/VH
WorldView optical imagery
Geospatial analysis<\/p>\n\n\n

Reference<\/h2>\n\n\n

ESA \u03a6-lab: AI4EO challenge \u2197<\/a><\/p>\n\n<\/div>\n\n<\/div>\n\n\n

\n
\n

Start a conversation<\/p>\n\n\n

A difficult problem is a good place to start.<\/h2>\n\n\n

Tell us what you\u2019re working on. We welcome technical challenges, research collaborations and new partnerships.<\/p>\n\n<\/div>\n\n\n

\n
Get in touch \u2197<\/a><\/div>\n\n<\/div>\n\n<\/div>","protected":false},"excerpt":{"rendered":"

Machine learning for building-footprint segmentation, bringing Earth-observation data to humanitarian planning.<\/p>","protected":false},"author":0,"featured_media":38861,"parent":38839,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"page-project.php","meta":[],"_links":{"self":[{"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/pages\/38841"}],"collection":[{"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/types\/page"}],"replies":[{"embeddable":true,"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/comments?post=38841"}],"version-history":[{"count":2,"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/pages\/38841\/revisions"}],"predecessor-version":[{"id":38868,"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/pages\/38841\/revisions\/38868"}],"up":[{"embeddable":true,"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/pages\/38839"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/media\/38861"}],"wp:attachment":[{"href":"https:\/\/zephyros.solutions\/it\/wp-json\/wp\/v2\/media?parent=38841"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}