Dr. Tongshu Zheng earned his Bachelor’s degree in Environmental and Sustainable Development from The Hong Kong Polytechnic University, graduating with First Class Honours. In 2018, he completed his Master’s in Environmental Engineering at Duke University, followed by a Ph.D. in the same field in 2021, where he was recognized as the “Outstanding Scholar” in his department upon graduation.

His doctoral research focused on applying machine learning and deep learning to advance environmental monitoring. He developed approaches to calibrate low-cost air quality sensors network and to retrieve air pollutant concentrations from emerging microsatellite imagery. These approaches give accurate estimates of fine particulate concentrations at a neighborhood level, as well as identify hot-spot sources to target mitigation strategies. In recognition of his work, he received the Sloan Foundation Energy Data Analytics Ph.D. Fellowship and the Senol Utku Annual Award, and his research was featured on the cover story of the Sloan Foundation’s Annual Report Highlights.

To date, Dr. Zheng has published eight SCI-indexed journal papers (four as first author, two as second author), which have received 637 citations. His work has been cited by leading institutions including MIT, Harvard, and UC Berkeley, and top journals such as Science and PNAS. It has also received broad media coverage, and he has presented at major international conferences including the Air Sensors International Conference (ASIC) in 2018 and Planet Explore in 2021.

Professionally, he has worked at the California Air Resources Board (CARB) and environmental technology company Aclima, contributing to the modernization of air quality and greenhouse gas monitoring data infrastructures, large-scale mobile air quality sampling projects, and air quality predictive models development for government clients in California, New York, Washington, D.C., Illinois, and Mexico—supporting multi-million-dollar environmental initiatives.

His current research focuses on integrating data science and computer science techniques with low-cost air quality monitoring technologies:

• Using mobile monitoring platforms to create ultra-high-spatiotemporal-resolution urban air pollution exposure maps, identify disadvantaged and sensitive populations, and characterize previously unmeasurable and often overlooked VOC species and sources in urban areas.
• Using low-cost air quality sensors to investigate how building types, HVAC systems, human activities, and outdoor environmental conditions influence indoor air pollution.
• Developing ethane retrieval methods from hyperspectral satellite imagery and using TROPOMI satellite data with GEOS-Chem to estimate methane emissions from China’s oil and gas sector and evaluate their long-term trends.