Improve Highway Safety by Reducing the Risks of Landslides (Phase 2)

Details

• Creators:
  Sheng, Zhuping ; Owolabi, Oludare ; Liu, Yi
• Corporate Creators:
  Morgan State University. Department of Civil and Environmental Engineering
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology ; Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)
• Subject/TRT Terms:
  Artificial Intelligence Highway Safety Landslides Machine Learning Mapping Monitoring Risk Management Slope Failure
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States;Maryland
• Edition:
  Final Report
• Corporate Publisher:
  Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)
• Abstract:
  This report summaries research findings of Phase 2 of the project titled Improve Highway Safety by Reducing the Risks of Landslides, sponsored by National UTC – Safety 21 program. To prevent landslides hazards, multiple approaches were integrated to develop a framework for detecting and monitoring slope instability and assessing landslides risks along the state highways, railroads, and roads. In Phase 2, we reviewed geotechnical asset management (GAM) framework, current status and recommendations for implementation in Maryland. Field and lab investigations was continued with geotechnical test results. LiDAR data was utilized in detection and characterization of landslides in Prince George’s County. Soil moisture mapping procedures was tested using Sentinel I data with ML approaches with a case study in Prince George’s County Maryland. Numerical model development for quantitative landslide risk assessment was initiated aiming at establishing a robust, interpretable, and quantitatively grounded framework for Landslide Risk Assessment (LRA) by integrating physics-based numerical modeling with machine learning approaches. Integrating GIS-based susceptibility mapping and machine learning framework was initiated for landslide prediction and early warning with a case study in in in Baltimore County, Maryland.
• Format:
  PDF
• Funding:
  69A3552344811, 69A3552348316
• Collection(s):
  University Transportation Centers
• Main Document Checksum:
  urn:sha-512:8760df08b13f83b0a97ccd03e23e082b92f49ed752bad9a185332fc7806a59d368144c6d4392917717c263a7189329ad52cf2619b073b5c46dab4be25d483012
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/85731/dot_85731_DS1.pdf
• File Type:
  [PDF - 8.03 MB ]