Research Interests:
Urban planning policy making using urban big data, urban science computation, and machine learning methods

Researcher Spotlight (first published 2019): Growing up in Tianjin, just southeast of Beijing, ChengHe Guan watched his world grow rapidly. “I was amazed by how China was changing at the time. There were different types of buildings coming up on the ground every day,” says Guan. “That's probably the very reason why I wanted to be an architect.”

The goal, though, was not just to be any architect—but to win the Pritzker Prize, architecture's highest honor. ChengHe started working at a Japanese architecture firm after earning a bachelor’s and master’s in the field, but grew frustrated after a few big projects stalled. “That's one of the many reasons I started thinking, ‘I can do something else—I can look at the bigger picture instead of just doing architectural design,’” he says. “I also figured I probably wasn’t going to become a Pritzker laureate, anyway,” he says with a laugh.

When ChengHe arrived at Harvard GSD to begin graduate studies in 2010, he started working on simulations—specifically a model concept called cellular automata, which uses scientific algorithms to help researchers project how cities and regions might grow. Today, he’s using this methodology to understand how to plan the low-carbon cities and regions of tomorrow. “When we consider the components and how we operate and construct the city, we can actually reduce the energy cost and promote healthier, better living for the people,” says ChengHe.

He began working with the Harvard-China Project two years ago as a postdoctoral fellow, initially brought on by Executive Director Chris Nielsen as part of a project that tracked changes in travel activity and personal health in 40 neighborhoods in Chengdu between 2005 and 2016. “We used this data to understand how urban form can promote people’s health,” says ChengHe. Access to this kind of data is one of the benefits of collaboration between GSD and the Harvard-China Project, he notes. Researchers who are focused on greenhouse gas emissions, for instance, can match their results to his data on urbanization to generate new research questions. “And then those can merge into some much bigger policy questions: How to reduce carbon emissions, how to build low-carbon cities, how to guide future planning,” says ChengHe.

In the short term, he hopes his work can impact city-level decisions about the development of arable, agricultural land to urban land in China. The long term, he says, offers even more exciting applications. “If we want to reduce carbon emissions to a certain level, keep the rise in global average surface temperatures to under 2 degrees Celsius, and maintain sea levels while also supporting economic growth, you will want to have wise policies in place,” says ChengHe. “So it’s important to use these predictions and the power of big data analysis to determine the outcomes of each of those policies and manage future city growth in an environmentally sound way—in China, or even beyond China’s borders.”

(Written by Dan Morrell)

Recent Publications:

[1] Tan, J., Guan, C.* (2021) Are people happier in locations of high property value? Spatial temporal analytics of activity frequency, public sentiment and housing price using Twitter data. Applied Geography 132, 102474 (SSCI) https://doi.org/10.1016/j.apgeog.2021.102474

[2] Yao, Z., Yang, J., Liu, J., Keith, M., Guan, C.* (2021) Comparing Tweet sentiment in megacities using machine learning techniques: In the midst of COVID-19. Cities 116, 103273. (SSCI) https://doi.org/10.1016/j.cities.2021.103273
 

[3] Guan, C., Song, J., Keith, M., Zhang, B., Akiyama Y., Da, L., Shibasaki R., Sato, T. (2021) Seasonal variations of park visitor volume and park service area in Tokyo: A mixed-method approach combining big data and field observations. Urban Forestry & Urban Greening, 58, 126973 (SCIE & SSCI) https://doi.org/10.1016/j.ufug.2020.126973

[4] Guan, C.*, Rowe, P. (2021) China’s urban block structures: A comparative study in three cities across different territories. Socio-Ecological Practice Research 3, 37-53. (CNKI) https://doi.org/10.1007/s42532-021-00074-7

[5] Gómez, J., Guan, C.*, Tripathy, P., Duque, J., Passos, S., Keith, M., Liu, J. (2021) Analyzing the spatiotemporal uncertainty in urbanization predictions. Remote Sensing, 13(3), 512 (SCIE) https://doi.org/10.3390/rs13030512

[6] Zhang, Y., Guan, C.^#, Chen, B., Zeng, L., Zhang, B. (2021) Tracking embodied water uses and GHG emissions along Chinese supply chains. Journal of Cleaner Production. (SCIE) https://doi.org/10.1016/j.jclepro.2020.125590

[7] Altinkaya-Genel O., Guan C.* (2021) Assessing urbanization dynamics in Turkey’s Marmara Region using CORINE data between 2006 and 2018. In a special issue - CORINE Land Cover System: Limits and Challenges for Territorial Studies and Planning. Remote Sensing. 13(4), 664 (SCIE) https://doi.org/10.3390/rs13040664

[8] Zhang, Y., Wu, X., Guan, C., Zhang, B. (2021) Methane emissions of major economies in 2014: A household-consumption-based perspective. Ranking: 3, h5-index (131), IF: 6.551. Science of the Total Environmental, 768, 144523. (SCIE) https://doi.org/10.1016/j.scitotenv.2020.144523