Deep Learning Models and Tools for Disaster Evacuation and Routing

Details

• Creators:
  Corns, Steven M ; Long, Suzanna K ; Edara, Praveen ; Hale, Jacob ; Chang, Dae Yeol ; Bennett, Rick ; Kutheis, Nick
• Corporate Creators:
  Missouri University of Science and Technology. Dept. of Engineering Management and Systems Engineering ; University of Idaho ; University of Missouri--Columbia. Department of Civil and Environmental Engineering ; WSP USA Inc.
• Corporate Contributors:
  Missouri. Dept. of Transportation. Division of Construction and Materials ; United States. Department of Transportation. Federal Highway Administration ; Missouri Center for Transportation Innovation
• Subject/TRT Terms:
  • Disasters and emergency operations
  • Evacuation
  • Machine learning
  • Routes and routing
  • Disasters
  • Earthquakes
  • Emergencies
  • Seismic prospecting
  • Scale models Mercalli Intensity Scale
• Publication/ Report Number:
  cmr 22-014
• Resource Type:
  Tech Report
• Geographical Coverage:
  Missouri;United States
• Edition:
  Final Report (January 2022-October 2022)
• Corporate Publisher:
  Missouri. Department of Transportation. Construction and Materials Division
• Abstract:
  Engineering managers and transportations planners need robust tools to communicate evacuation routing plans following disruptions from earthquake events. The project will use the New Madrid Seismic Zone in South-East Missouri as a testbed for modeling the response to an earthquake and aftershocks at Magnitude 8+. This area was chosen as it allows solutions to specific regions with inadequate road networks, limited communications protocols, and high likelihood of structural damage for the proposed scenario. Research tasks include identifying road structure damage based on the Mercalli Intensity Scale, running traffic simulations for post-earthquake evacuation to determine the desired routes out of the area. This research will then be able to display the warning of the earthquake event along with the desired route for the end user. Effectively providing the safest navigation routes are a vital part of these planning efforts.
• Format:
  PDF
• Funding:
  MoDOT project # TR202202
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/65825/dot_65825_DS1.pdf
• File Type:
  [PDF - 4.20 MB]
• Collection(s):
  US Transportation Collection
• Main Document Checksum:
  urn:sha-512:2f0877c73ebbf8ec3707bda21583ab8838ad83530aaceae94bef5d9082dbdc74808d1458aabac8be741523aedf5e215f6e2a004b3607cc75e29a1affcd3476e2