Abstract
Geologic hazards including slope failures, landslides, mudflows, debris flows, etc. and hydrological hazards related to floods and stormwater surge can be destructive to transportation infrastructure and threaten property and human life along the highway and roads. Landslides alone cause thousands of deaths and many billions of dollars in damage every year.
Morgan State University team proposes a multi-phase (multi-year) project focusing on safety of transportation infrastructure systems by preventing geohazard, specifically slope failure and landslides and minimizing impacts of geohazard. This project will employ an integrated approach of geotechnical and AI/Machine Learning methods for assessing conditions of geotechnical assets, such as cut slopes and embankment of the DOT SHA and delineating landslides and high-risk areas.
The objectives (tasks) of the proposal include: (1) with AI/Machine Learning approaches assess the risks of landslides based on soil/rock types, weather conditions, mechanical properties of slope materials, and the status of existing retaining structures along the selected highway sections, using Maryland as case studies, (2) identify and map the high-risk areas based on controlling factors such as geometry and mechanical properties of soil or rock, and triggering factors, including gravitational and hydraulic forces, using available survey data, remote sensing and LIDAR data and and other factors like transportation modes, (3) design and test protocols for real time monitoring at selected sites in consultation with DOT SHA staff, and (4) recommend strategies for reducing the risks of landslides with real-time monitoring for the high-risk areas, and improving the safety of the transportation infrastructure. All the methods and strategies can be transferred to other states or regions with similar geological conditions and engineering configurations. Phase 1 of this project will primarily cover task 1 and part of task 2. This project will primarily complement ongoing projects sponsored by the Maryland DOT SHA (see more information in TRID) led by Zhuping Sheng.
Dr. Jiang Li has experience in both transportation research and environmental hazards. The former focuses on the mechanical behavior of road subgrades and the latter addresses the geological or hydrological hazards that may adversely affect the regional transportation infrastructure and traffic safety. As PI Dr. Li will coordinate the efforts in collaboration with MDOT/SHA and advise other faculty and postdoctoral research associates and graduate students to carry out the project. The team includes Co-PIs, Zhuping Sheng, Oludare Owolabi and Yi Liu who are currently conducting research supported by MDOT SHA, which provides a strong foundation for future collaboration with the partner MDOT SHA and others for technical transfer.
This program includes a summer internship program with two students and one graduate team for development of future workforce in transportation safety in cooperation with MSU AI/ML program led by Dr. Owolabi. Students will also participate in exchange programs and deployment partners symposium and other activities. Through this project the MSU team is expected to expand collaboration with CMU and other partner institutes via faculty meetings, seminars, national summit, and other venues, which provides great opportunity for professional development.
Description
Timeline
Strategic Description / RD&T
The proposed project will address transportation safety, especially physical infrastructure systems and roadway design, covering the following US DOT goals:
1. Update roadway design standards to protect vulnerable road users and vehicle occupants.
2. Use regulatory and policy tools to advance roadway safety to reduce fatalities and injuries across modes.
3. Support the adoption and maturation of safety management systems across modes.
4. Use data and data analytics to take proactive actions to address emerging safety risks and support compliance.
The project will provide technical assistance to better identify, assess, and address critical physical vulnerabilities.
1. Incorporate physical protections in the standards for design of emerging automated and connected systems and technologies, such as real time sensing and monitoring systems.
2. Strengthen system response and recovery plans and protocols to minimize the effects of system disruptions and hasten system recovery from the natural disasters.
3. Promote guidelines on vulnerability assessments with enhancement of AI/ML approaches.
The project will assess and mitigate the vulnerability of transportation infrastructure to climate change and natural disasters:
1. Assess the vulnerability of assets and identify novel climate adaptation and mitigation strategies.
2. Enhance resilience throughout transportation planning and project development processes by updating guidance and regulations.
3. Conduct case studies and pilot projects to develop and evaluate new and innovative adaptation and resiliency technologies, tools, and opportunities, such as motion sensors and early warning systems.
This project will build research capacity in the critical area of designing resilient infrastructure for geohazards and changing climate conditions. It will also provide educational opportunities for Ph.D. and undergraduate students to gain knowledge and experience in this important new area for sustainable and resilient engineering. Thus, the project will also build human capacity to address the challenge of geohazards adaptation related to transportation systems.
Deployment Plan
Quarter 1 (July – September)
Initiate partnership with MDOT SHA based on ongoing project(s) and discussed intention to propose the complement work with support from UTC.
Share the work plan with and request information related to landslides from the partner and arrange site visits and sample collection.
Quarter 2 (October- December)
Share UTC work at the Quarterly meeting in October and seek inputs from the partner.
Seek assistance in landslides mapping and sample collection for selected sites.
Quarter 3 (January - March)
Share UTC work at the Quarterly meeting in January and seek inputs from the partner.
Plan and prepare for a workshop to be held next quarter.
Quarter 4 (April - June)
Share UTC work at the Quarterly meeting in April and seek inputs from the partner.
Organize the workshop for MDOT SHA staff and other professionals on MSU campus.
Organize internship activities in collaboration with MSU AI/ML program - National Center for Equitable Artificial Intelligence and Machine Learning Systems (CEAMLS): Organize sequence of workshops in-order to create a community of resilient engineers.
The research will sponsor two doctoral students (Ph. D. in Sustainable and Resilient Infrastructure Engineering) and two STEM undergraduate students at MSU. During the summer these students will acquire knowledge about how emerging technologies (AI/ML) will be used in adapting transportation infrastructure against geohazards. We shall provide a sequence of workshops in-order to create a community of resilient engineers that will be committed to adapting our highway infrastructure systems against geohazards. An extensive public involvement program will be undertaken to make sure that all the stakeholders including students at lower levels of education are aware of this project.
Besides direct interaction with the partner, faculty and students will participate in DOT National Safety Summit and Safety 21 Deployment Partners Consortium Symposium, Safety Faculty Meetings, Safety Seminar, CUTC Summer Conference, and other professional conferences and meetings.
Expected Outcomes/Impacts
Besides advance in research and teaching related to transportation safety and disaster management, the project is expected to bring broad positive impacts on transportation system in the following aspects:
Reliable assessment of landslide risk could help with preventive maintenance to avoid slope failures, assuring safe and reliable roadways and saving costs by reducing the impacts of potential failures.
Early detection of slope failure with warning and monitoring systems, especially those recurring landslides sites could help to take measures to minimize damage to the infrastructures and provide safe routing to avoid injury to vehicle occupants.
Research findings will help policy makers to improve the roadway design standards and secure resources to assure long-term safety of transportation systems under climate change.
Research results, including assessment approaches and design protocols, are transferable to other states and regions with similar geological and hydrological conditions and roadway designs.
In addition, this project will support initiatives that enhance doctoral achievement in the STEM and non-STEM disciplines for under-represented students of color and provide educational opportunities for student assistants to gain knowledge and experience for civil and environmental engineering. Faculty and researchers will participate in the Black Engineer of the Year Awards STEM Conference, reaching out to students, professionals, entrepreneurs, and employers in science, technology, engineering, and math fields.
Expected Outputs
The following are expected outputs for the Phase 1 of the proposed project:
• 1 to 2 Journal articles on methodology and case studies
• 4 to 5 conference presentations at professional conferences and technical meetings
• GIS coverages of detail delineation of selected landslides
• Initial set up of database of geotechnical properties of soils
• 1 training workshops for SHA staff and other professionals in transportation safety and disaster management
• AI/ML models for landslides risk assessment with physical models (modified or new)
Upon the completion of the whole project, the following deliverables are expected:
• Maps of landslides risks and make them accessible through DOT SHA or UTC;
• Curricular materials (methodology, case studies of landslides, monitoring protocols and more) for classroom teaching for slope stability analysis and risk assessment of landslides and improvement of transportation safety.
• Protocols for monitoring of slope movement and failure as well as warning systems, and
• Guidelines for mapping risk areas and the real-time monitoring and alarm system for high-risk areas in cooperation with DOT SHA.
TRID
We have made the following searches on TRID:
1. Landslides Maryland (4 records)
2. Landslides Warning System (36 records)
3. Landslides Risk Assessment (214 records)
4. Landslides (2777 records)
This project is unique in integrating geotechnical and machine learning approaches in assessing slope instability and risk of landslides. This project is built upon ongoing MDOT efforts in geotechnical asset management and the proposed work will complement the research project funded by MDOT SHA, focusing on effects of precipitation on slope failure as one of major triggering factors. MDOT SHA is supportive to our proposed and has confirmed that SHA funding can be used as non-federal matching funds.
Information related to the ongoing project supported by MDOT SHA can be found from the following web link.
1. Incorporating Precipitation Data into Geotechnical Asset Management.
https://rip.trb.org/view/2118359
MSU PI: Sheng: 150,000
2. Develop a Mode Choice Model to Estimate Walk and Bike Trips in the Statewide Model (PI: Liu; 150,000).
3. Effectiveness of Short Solid Barriers to Reduce Noise Generated by Different Types of Highway Vehicle (PI: Owolabi; 150,000.
Individuals Involved
Email |
Name |
Affiliation |
Role |
Position |
Jiang.Li@morgan.edu |
Li, Jiang |
Morgan State University |
Co-PI |
Faculty - Tenured |
yi.liu@morgan.edu |
Liu, Yi |
Morgan State University |
Co-PI |
Faculty - Tenured |
Oludare.Owolabi@morgan.edu |
Owolabi, Oludare |
Morgan Statee University |
Co-PI |
Faculty - Tenured |
zhuping.sheng@morgan.edu |
Sheng, Zhuping |
Morgan State University |
PI |
Faculty - Tenured |
Budget
Amount of UTC Funds Awarded
$300000.00
Total Project Budget (from all funding sources)
$600000.00
Documents
Type |
Name |
Uploaded |
Data Management Plan |
UTCSafety21-DMP-MSU.pdf |
Aug. 17, 2023, 10:34 p.m. |
Presentation |
Highlights on the Project: Improve highway safety by reducing the risks of landslides |
March 30, 2024, 4:20 p.m. |
Presentation |
Incorporating Precipitation Data into Geotechnical Asset Management – Initial Work |
March 30, 2024, 4:20 p.m. |
Presentation |
Modal choice Model to Estimate Walk and bike trips in a statewide model: Literature Review |
March 30, 2024, 4:20 p.m. |
Presentation |
Real-time pavement damage detection using YOLOv8 |
March 30, 2024, 6:49 p.m. |
Progress Report |
425_Progress_Report_2024-03-31 |
March 30, 2024, 4:48 p.m. |
Presentation |
Application of Artificial Neural Network to Predict Pavement Longitudinal Distresses Induced by Extreme Temperature |
March 30, 2024, 6:49 p.m. |
Presentation |
Application of Machine Learning, and Computer Vision in a SMART Transportation Management System of an Underserved Community |
March 30, 2024, 6:49 p.m. |
Match Sources
No match sources!
Partners
Name |
Type |
Maryland Department of Transportation |
Deployment & Equity Partner Deployment & Equity Partner |