Skip to main content

Overview


I study how cities are warming in a changing climate, and how we can design better tools to keep them livable. My research develops new statistical and machine learning methods to turn messy environmental data—such as satellite imagery, crowdsourced weather stations, and sensor networks—into reliable, neighborhood-level maps of heat exposure. By rigorously accounting for uncertainty and bias, I uncover patterns of vulnerability that would otherwise remain hidden. This work not only advances methods for analyzing complex environmental data, but also provides actionable insights for climate adaptation, from evaluating reflective surfaces and shading structures to guiding investments in urban greenery and cooling infrastructure. Ultimately, I aim to build the data-driven foundation for resilient, equitable, and climate-adaptive cities.

Current Duke Appointments & Affiliations


Recent News Items


Published September 1, 2023
Pratt School of Engineering
Combating the Climate Crisis at Duke

View All News Items

Recent Scholarly Works


Probabilistic interpolation of crowdsourced meteorological data for higher-resolution gridded estimates of surface air temperature

Journal article Urban Climate · June 1, 2026 Crowdsourced air temperature data from networks like Weather Underground offer dense spatial coverage and are increasingly used to study the canopy urban heat island (CUHI) effect. However, these observations are noisy: siting conditions, environmental int ... Full text Cite

Neighborhood Environmental and Contextual Factors Improve Prediction of Childhood Body Mass Index: An Application of Novel Graph Neural Networks.

Journal article AJE Adv · September 24, 2025 Childhood obesity is a major risk factor for adult cardiovascular disease. Current obesity-prediction models were not developed in diverse populations and do not include heterogeneous social, environmental, and climate factors that may impact body mass ind ... Full text Link to item Cite

Big, noisy data: how scalable Gaussian processes can leverage personal weather stations to improve spatiotemporal coverage of urban climate networks

Other · May 21, 2025 Urban temperature varies dramatically across space and time, yet capturing this variability requires a dense, reliable sensor network—something that is rarely available in practice. Spatiotemporal gaps in data coverage make it difficult to connect ... Full text Cite
View All Scholarly Works

External Links


Personal Website