{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/5b52f454204e4a71b4fe765a650b43c1\" frameborder=\"0\" width=\"1110\" height=\"832\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":832,"width":1110,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":832,"thumbnail_width":1110,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/5b52f454204e4a71b4fe765a650b43c1-4de2ec1c838236d6.gif","duration":174.009,"title":"How Lifeline Maps Flood Cut-Offs","description":"This Loom explains how Meta’s Lifeline system helps flood rescuers determine which roads are flooded and which buildings are cut off. It uses Meta Muse Spark with before and after satellite photos plus a road map to classify road segments as flooded, dry, or uncertain, then a planner identifies isolated buildings and recommended crew entry points ranked by how many buildings they reach. The presenter tested it on Hurricane Ida tiles and found 26 isolated buildings, with 25 labeled and the remaining one marked uncertain rather than guessed, plus some cautiousness on two reachable cases. Against ground truth, it was about 90 to 98 percent accurate on heavily flooded tiles and about half on less flooded areas, and the video emphasizes that it flags uncertainty and provides evidence-backed claims."}