Abstract
Storm surge is a common nature disaster in China southern coastal area, which usually causes heavy human life and economic losses. With the economic development and population concentration of coastal cities, the storm surges may result in more impacts and damage in the future. Therefore, it is of vital importance to conduct risk assessment to identify high-risk areas and evaluate economic losses. However, quantitative study of storm surge risk assessment in undeveloped areas of China is difficult, since there is a lack of building characters and damage assessment data. Aiming at the problem of data missing in undeveloped areas of China, this paper proposes a methodology for conducting storm surge risk assessment quantitatively based on deep learning and geographic information system (GIS) techniques. Five defined storm surge inundation scenarios with different typhoon return periods are simulated by coupled FVCOM-SWAN model, the reliability of which is validated using official measurements. Building footprints of the study area are extracted through TransUNet deep learning model and Remote Sensing Image (RSI), while building heights are obtained through Unmanned Aerial Vehicle (UAV) measurement. Subsequently, economic losses are quantitatively calculated by combing the adjusted depth-damage functions and overlay analysis of the buildings exposed to storm surge inundation. Zonation maps of the study area are illustrated to display the risk levels according to the economic losses. The quantitative risk assessment and zonation maps can help the government to make storm surge disaster prevention measures and optimize land use planning, and thus to reduce the potential economic losses of the coastal area.
All Related Versions
Funding Information
  • Shenzhen Science and Technology Innovation Program (KCXFZ20211020164015024)
  • National Natural Science Foundation of China (52101332)
  • Basic and Applied Basic Research Foundation of Guangdong Province (2024A1515011805, 2023A1515240047, 2024A1515012032)

This publication has 30 references indexed in Scilit: