Texas A&M as a Living Laboratory for Data Science
Texas A&M University is a large and complex organization, with over 69,000 students enrolled in programs over 19 Colleges and Schools in which research and instruction is led by roughly 4,000 faculty. The main College Station campus occupies 5,200 acres. Many functions of University infrastructure—including transportation, facilities, utilities, libraries and administration—routinely collect data during their operation. The resulting data are used to manage these functions across a range of timescales—ranging from planning, through daily operations, to troubleshooting and event response—and over the large and varied campus. Due to the constraints and demands of daily operations management, the potential for such data to improve the operations of the Texas A&M Infrastructure has not been fully realized.
The Operational Data Science Lab is a joint enterprise between the Texas A&M Institute of Data Science (TAMIDS) and the Texas A&M Center for Geospatial Science, Applications, and Technology (GEOSAT) to develop partnerships with operational organizations in Texas A&M that capitalize on institutional data investments to improve campus operations and achieve research and academic goals:
- Identify new data-driven research problems arising from operational contexts;
- Derive new insights and analyses from data and embody these in software tools;
- Engage the broader community of researchers with operational data challenges;
- Provide hands-on opportunities for students to work with real-world data;
- Leverage the results for funding proposals and outreach.
Achieving these goals has the potential to transform Texas A&M into a living laboratory for Data Science, accelerating the pace and effectiveness of Texas A&M’s teaching, research, and outreach mission.
- Dr. Nick Duffield, Director TAMIDS & Royce E Wisenbaker Professor I in Electrical and Computer Engineering
- Dr. Dan Goldberg, Director Texas A&M GEOSAT & Associate Professor in Geography and Computer Science & Engineering
Project Partner Organizations
- Texas A&M Transportation Services; Texas A&M Transportation Institute (TTI); University Libraries; Division of Research
Events and Community
- TAMIDS Workshop on Operational Data Science, February 2019
- GIS Day Workshop on Geospatial Data Science and Campus Operations, November 2019
How to Get Involved
- As an operational unit with data or problems, or
- As a researcher with creative ideas, or
- As a student who wishes to join new data projects:
AI-based Traffic Measurement from Video Imaging
- Amir Behzadan, Construction Science
- Nick Duffield, TAMIDS & ECE
- Tim Lomax, Texas A&M Transportation Institute
- Yalong Pi, TAMIDS
Partners: Transportation Services, TTI
Project: This work is applying AI-based methods to video imaging from road and facilities infrastructure at Texas A&M to provide counts of vehicles traversing road junctions and using facilities such as parking garages. This information will be used to support planning and operations for transportation services, for example, to optimize traffic flows during high-volume periods such as game days
Research Areas: AI-based object classification; motion tracking; transportation; Data Types: video, geospatial
Research Organizational Intelligence
- Jack Baldauf, Division of Research & Oceanography
- Nick Duffield, TAMIDS & ECE
- Bruce Herbert, University Libraries & Geology/Geophysics
- Srujan Jabbireddy, Graduate Student, Industrial and Systems Engineering
- Jian Tao, TAMIDS/ TEES / HPRC / ECE
- Zengyu Wei, Undergraduate Student, Computer Science and Engineering
Partners: Division of Research, University Libraries
Project: This work uses information concerning faculty publications, grant proposals, and other data to profile Texas A&M’s research in thematic research areas and to identify unexplored opportunities for future research. This project will develop and use software tools that enable exploration and characterization of current and trending research, visualized research collaborations through coauthorship networks and identify latent and emerging opportunities for collaboration through subgraph prediction.
Research Areas: graph analysis, graph clustering, link prediction, keyword analysis.
Data types: text, bibliographic, publications, citations
Bikeshare Effectiveness and Operations
Project: This work uses the real-time locations of TAMU rideshare bikes (starting with Ofo and now using VeoRide) and their paths to measure the effectiveness of the bikeshare program and assist with the operational rebalancing efforts to ensure that bikes are where users need them, when they need them. This project will develop software tools for data visualization and exploration, automated processes and database structures for data ingestion, storage, and retrieval, and geospatial machine learning models and approaches for predictive analytics to guide operational efforts.
Research Areas: graph analysis, big data, machine learning, visualization
Data types: geospatial, demographic