Monitoring Urban Deprived Areas with Remote Sensing and Machine Learning in Case of Disaster Recovery

Rapid urbanization and increasing population in cities with a large portion of them settled deprived neighborhoods, mostly defined as slum areas, have escalated inequality vulnerability to natural disasters. As result, monitoring such areas is essential provide information support decision-makers urban planners, especially case disaster recovery. Here, we developed an approach monitor the over four-year period after super Typhoon Haiyan, which struck Tacloban city, Philippines, 2013, using high-resolution satellite images machine learning methods. A Support Vector Machine classification method supported by local binary patterns feature extraction model was initially performed detect pre-disaster, just after/event, post-disaster images. Afterward, dense conditional random fields employed produce final maps. The detected accuracies 83%. We produced damage recovery maps based on change analysis areas. results revealed that most were reconstructed 4 years thus, city returned pre-existing level.