Towards Sustainable Urban Systems with Human-Centered Big Data Mining

Songhua Hu

Postdoctoral Researcher, Senseable City Lab, Massachusetts Institute of Technology (MIT)

Abstract: Climate change and population growth pose unprecedented challenges to the urban and human systems. Meanwhile, the proliferation of crowdsensing techniques, such as mobile phones, vehicles, and cameras, has generated vast spatiotemporal data for understanding human activities and their interaction with the urban environment. Effectively managing such massive, multi-structured spatiotemporal data, extracting valuable information, and tailoring solutions to various urban challenges are more crucial than ever. In this talk, I will first delve into my research on using raw location data collected from millions of mobile phones to estimate and forecast individual human mobility patterns. Building on this foundation, I will demonstrate how it can support mobility decarbonization. Specifically, I will introduce a scalable framework that integrates ubiquitous, multi-structured mobility data to estimate citywide on-road vehicle emissions with high spatiotemporal resolution, followed by an evaluation of various city-scale decarbonization strategies, including vehicle electrification and sustainable travel demand management. Lastly, I will highlight opportunities for multidisciplinary collaboration in areas such as energy demand estimating, event response, and environmental exposure to drive broader and more lasting impacts.

Bio: Dr. Songhua Hu is a postdoctoral researcher at the MIT Senseable City Lab. He holds a Ph.D. in Civil Engineering from the University of Maryland, College Park. His research focuses on modeling human mobility and human-environment interactions using crowdsourced digital footprints collected from mobile phones, vehicles, social media, and cameras. His work has contributed to projects funded by the NSF, NIH, USDOT, and USDOE, resulting in 28 journal papers published in PNAS, Transportation Research Part A/C/D, and over 30 conference presentations. He is the recipient of the 2023 University of Maryland Best Doctoral Research Award and the 2023 COTA Best Dissertation Award.