Predictive Deep Learning for Flash Flood Management

This research was completed in tandem as a project funded through MoDOT and the Mid-America Transportation Center. It used deep learning methods, along with weather information from NOAA/National Weather Service and geospatial data from the USGS National Map and other public geospatial data sources, to develop forecasting tools capable of assessing the probability of flash flooding in high risk areas. These tools build on existing models developed by the USGS, FEMA, and others and were used to determine evacuation routing and detours to mitigate the potential for loss of life during flash floods. The project scope included analysis of publicly available data in Greene county in and around Springfield, MO as part of a pilot project in Missouri. This data was then used to determine the probability of flash flooding in order to model evacuation or detour planning modules that can be implemented to assure the safety of the community and highway personnel. These modules used existing rainfall data and weather forecasts in a three-day sliding window to include soil moisture in the flash flood predictions. The transportation safety or disaster planner can use these results to produce planning documents based on geospatial data and information to develop region-specific tools and response methods to potential flash flood events.

• Record URL:
  https://spexternal.modot.mo.gov/sites/cm/CORDT/cmr21-001.pdf
• Record URL:
  https://rosap.ntl.bts.gov/view/dot/58157
• Corporate Authors:

  Missouri University of Science and Technology, Rolla

  Department of Engineering Management and Systems Engineering
  600 W 14th Street
  Rolla, MO  United States  65409-1330

  Missouri Department of Transportation

  Construction and Materials Division
  Jefferson City, MO  United States  65102

  Federal Highway Administration

  1200 New Jersey Avenue, SE
  Washington, DC  United States  20590

  U.S. Department of Transportation

  1200 New Jersey Avenue, SE
  Washington, DC  United States  20590
• Authors:
  • Corns, Steven M
  • 0000-0002-3685-2892
  • Long, Suzanna K
  • 0000-0001-6589-5528
  • Hale, Jacob
  • Kanwar, Bhanu
  • Price, Lauren
• Publication Date: 2021-1

Language

• English

Media Info

• Media Type: Digital/other
• Edition: Final Report
• Features: Figures; Maps; References; Tables;
• Pagination: 51p

Subject/Index Terms

• TRT Terms: Detours; Disaster preparedness; Evacuation; Floods; Geospatial data; Machine learning; Pilot studies; Predictive models; Routing
• Identifier Terms: National Map; U.S. National Oceanic and Atmospheric Administration; U.S. National Weather Service; United States Geological Survey
• Geographic Terms: Greene County (Missouri)
• Subject Areas: Environment; Highways; Hydraulics and Hydrology; Safety and Human Factors; Security and Emergencies;

Filing Info

• Accession Number: 01762778
• Record Type: Publication
• Report/Paper Numbers: cmr 21-001, Project number TR202023
• Contract Numbers: MoDOT project # TR202023
• Files: NTL, TRIS, ATRI, USDOT, STATEDOT
• Created Date: Jan 27 2021 10:10AM