CAREER: Towards Unbiased Long-Range Freight Planning Through Passive-Sensors and Workforce Diversity

This Faculty Early Career Development (CAREER) grant will produce freight-goods movement data at a resolution needed to make informed, data-driven, decisions about long-range transportation infrastructure investments and policies. Such decisions affect the health, safety, and prosperity of US citizens and the freight transportation industry. Since the inception of nationwide shipment surveys in the 1990s, little has changed in how public agencies collect commodity flow data, despite the increasing complexity of freight operations and supply chains.

With the 2017 federal mandates for electronic logbooks and widespread use of Global Positioning Systems, there is tremendous potential to reimagine how freight data is collected. The research objective of this grant is to derive unbiased spatial and temporally-continuous commodity and industry information from passively collected, anonymized freight movement data (specifically for truck and waterborne freight).

The work will enable researchers and practitioners to advance 20-40-year forecast models of freight movement, as well as formulate solutions to critical industry issues such as driver shortages, Hours-of-Service regulations, and lack of safe and available parking. Additionally, diversity in the transportation workforce is critical for ensuring that investment and infrastructure decisions reflect the unique needs of diverse travelers.

An innovative service-learning education plan is integrated into the project to improve job attraction and retention rates of female transportation professionals and students.

This research will yield positive societal impacts by enabling transportation agencies to leverage increasingly available samples of passively collected freight movement data for timely, unbiased decision-making regarding infrastructure investment, environmental policy, and economic development. The research will: 1) determine the extent to which activity patterns derived from passively collected mobile sensor data accurately predict commodity carried; 2) identify the extent to which vehicle body characteristics derived from roadway traffic sensors predict commodity carried; 3) establish and validate bias detection and quality measures for passively collected freight movement data.

The project will promote women’s initial engagement and ongoing career satisfaction to help close the gender gap and ensure that diverse perspectives are routinely included in transportation planning processes. The three-tiered plan implements train-the-trainer sessions during annual professional conferences where college students (tier 1) teach practicing transportation engineers (tier 2) how to deliver traffic sensor-themed K-12 (tier 3) outreach.

The broader educational impacts of this project support NSF societal outcomes by promoting: 1) full participation of women in STEM, 2) development of a more diverse, globally competitive STEM workforce, and 3) increased partnerships between academia and professional organizations.

The project is jointly funded by the Civil Infrastructure Systems (CIS) program and the Established Program to Stimulate Competitive Research (EPSCoR).

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.