Exploring flood mitigation governance by estimating first-floor elevation via deep learning and google street view in coastal Texas

Ge Gao, Xinyue Ye, Shoujia Li, Xiao Huang, Huan Ning, David Retchless, Zhenlong Li

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Flood mitigation governance is critical for coastal regions where flooding has caused considerable damage. Raising the First-Floor Elevation (FFE) above the base flood elevation (BFE) is an effective mitigation measure for buildings with a high risk of flooding. In the U.S., measuring FFE is necessary to obtain an Elevation Certificate (E.C.) for the National Flood Insurance Program (NFIP) and has traditionally required labor-consuming field surveys. However, the advances in computer vision technology have facilitated the handling of large image datasets, leading to new FFE measurement approaches. Taking Galveston Island (including the cities of Galveston and Jamaica Beach) in Coastal Texas as a case study, we explore how these new approaches may inform flood risk management and governance, including how FFE estimates may be combined with BFE estimates from flood inundation probability mapping to model the predicted cost of raising buildings’ FFE above their BFE. After establishing the FFE model’s accuracy by comparing its results with previously validated FFE estimates in three districts of Galveston, we generalize the workflow to building footprints across Galveston Island. By combining the FFE data derived from our workflow with multidimensional building information, we further analyze the future flood control and post-disaster maintenance strategies. Our findings present valuable data collection paradigms and methodological concepts that inform flood governance for Galveston Island. The proposed workflow can be extended to flood management and research for other vulnerable coastal communities.

Original languageEnglish (US)
Pages (from-to)296-313
Number of pages18
JournalEnvironment and Planning B: Urban Analytics and City Science
Issue number2
StatePublished - Feb 2024
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Geography, Planning and Development
  • Architecture
  • Urban Studies
  • Nature and Landscape Conservation
  • Management, Monitoring, Policy and Law


  • deep learning
  • first-floor elevation
  • flood mitigation
  • street view


Dive into the research topics of 'Exploring flood mitigation governance by estimating first-floor elevation via deep learning and google street view in coastal Texas'. Together they form a unique fingerprint.

Cite this