LanguageTerm (authority = ISO 639-3:2007); (type = text)
English
Abstract
A combination of mobile data collection and new damage assessment methods with spatial analysis and machine learning algorithms were used to correlate structural characteristics with damage and iterate upon damage assessment protocols for further development. More specifically, data was collected using a mobile scanning vehicle, reducing volunteer exposure to the harsh post-disaster environment, collecting high volumes of panoramic and LiDAR imagery in a relatively short period of time. This new data collection method was deployed in Texas during Hurricane Harvey. Among many datasets collected by this method, the dataset used in this study consisted of almost purely wind-caused damage from Hurricane Harvey to 553 homes in southeast Texas. A damage assessment methodology was created, combining lessons learned and protocols from previous studies, to increase efficiency and include more external public sources of data for better damage analysis. Statistical analysis was combined with spatial analysis revealing structural components which can be expected to reduce or increase damage from single-hazard wind damage. Spatial analysis indicated that damage rating was related to peak wind speed and explanatory regression revealed that the most significant variables to classification were: Age, Latitude, Metal Roofs, Distance to Coast, Total Area, Asphalt Roofs, Wood Siding, Stucco Siding, Two Story Buildings, and Building Value. Machine Learning classifiers were used improve the efficiency of damage assessments by indicating the multicollinearity and the feature importance of each variable. The variables with the highest feature importance include: Distance to Coast, Longitude, Single-Family, Age, Total Area, Wind Speed, and Single Story. These variables should be prioritized in future studies, while variables with low feature importance, such as Grade Level Entry, Intersecting or Overlapping Roofs, 10/12 Roof Pitch, Commercial uses, and Vinyl Siding, should be reconsidered in future damage assessments.
Subject (authority = local)
Topic
Hurricane
Subject (authority = RUETD)
Topic
Civil and Environmental Engineering
Subject (authority = ETD-LCSH)
Topic
Spatial analysis (Statistics)
Subject (authority = ETD-LCSH)
Topic
Hurricane Harvey, 2017
Subject (authority = ETD-LCSH)
Topic
Hurricane damage -- Texas
Subject (authority = ETD-LCSH)
Topic
Data mining
Subject (authority = ETD-LCSH)
Topic
Cell phones
RelatedItem (type = host)
TitleInfo
Title
Rutgers University Electronic Theses and Dissertations
I hereby grant to the Rutgers University Libraries and to my school the non-exclusive right to archive, reproduce and distribute my thesis or dissertation, in whole or in part, and/or my abstract, in whole or in part, in and from an electronic format, subject to the release date subsequently stipulated in this submittal form and approved by my school. I represent and stipulate that the thesis or dissertation and its abstract are my original work, that they do not infringe or violate any rights of others, and that I make these grants as the sole owner of the rights to my thesis or dissertation and its abstract. I represent that I have obtained written permissions, when necessary, from the owner(s) of each third party copyrighted matter to be included in my thesis or dissertation and will supply copies of such upon request by my school. I acknowledge that RU ETD and my school will not distribute my thesis or dissertation or its abstract if, in their reasonable judgment, they believe all such rights have not been secured. I acknowledge that I retain ownership rights to the copyright of my work. I also retain the right to use all or part of this thesis or dissertation in future works, such as articles or books.