Detection of plastic tarps on roofs damaged by Hurricane Maria in Puerto Rico leveraging drone and Sentinel-2 imagery, with a focus on healthcare infrastructure
Topics:
Keywords: remote sensing, healthcare, deep learning, Hurricane Maria, Puerto Rico
Abstract Type: Virtual Poster Abstract
Authors:
Ying Yang, Data Analytics, Graduate School of Arts and Sciences, Tufts University, Medford MA 02155
Grace Wu, Urban and Environmental Policy and Planning, Graduate School Of Arts And Sciences, Tufts University, Medford MA 02155
Youshuang Hu, Urban and Environmental Policy and Planning, Graduate School Of Arts And Sciences, Tufts University, Medford MA 02155
Kyle M Monahan, Research Technology, Tufts Technology Services, Tufts University, Medford MA 02155
,
,
,
,
,
,
Abstract
Hurricane Maria made landfall in southeast Puerto Rico on September 20th, 2017. This powerful storm affected millions of people, causing a partial collapse of the power and healthcare systems, and placed much of the affected population at risk for adverse mental and physical health outcomes. In this work, a remotely sensed indicator of damage to infrastructure was further developed for Puerto Rico using remotely sensed blue-colored tarps placed over damaged roofs with a machine learning technique. A random forest and deep learning model were created using ArcGIS Pro, training on both drone imagery (1 meter resolution) and Sentinel-2 imagery (15 meter resolution). An additional class of damaged healthcare infrastructure was added. Results of models were compared using accuracy, F1, and sensitivity values for each class. Future work using change detection was performed.
Detection of plastic tarps on roofs damaged by Hurricane Maria in Puerto Rico leveraging drone and Sentinel-2 imagery, with a focus on healthcare infrastructure
Category
Virtual Poster Abstract
