Discipline: Technology & Engineering
Subcategory: STEM Research
Leila Hashemi Beni - North Carolina A&T State University
Co-Author(s): Asmamaw Gebrehiwot, North Carolina A&T State University
Unmanned aerial vehicles (UAVs) offer a great potential alternative to conventional platforms for acquiring high-resolution remote sensing data at lower cost and increased operational flexibility for flood modeling and management. Data processing and measurement is a key step in the development of UAV remote sensing for flood modeling and management. Various approaches have been developed and applied for accurate and near real time extraction of orthorectified, DEM and the flood extent from UAV data including structure from motion (SFM) and image classifiers. These methods perform well when a very limited amount of data is used; however, the complexity grows as the data size increases when using a UAV for flood management and floodplain mapping. This project investigates an integrated method using Machine Learning and LiDAR analysis for near real time inundation mapping and extracting water depth from UAV data (RGB and infrared) collected by the NC Division of Emergency Management over: Princeville during flooding after hurricane Matthew in 2016; Lumberton and Fair Bluff during flooding after Hurricane Florencel; amd NCAT & NCGS testbed in Tarboro for floodplain mapping in 2019. The results are compared and validate using USGS data.
Funder Acknowledgement(s): This research is supported by the U.S. National Science Foundation (NSF), grant number 1800768 and North Carolina Collaboratory policy.
Faculty Advisor: None Listed,
NSF Affiliation: HBCU-UP