Esra's research is focused on the use of emerging sources of digital data for characterising urban environmental features and exposures. She is mainly interested in regular monitoring of socio-economic status, housing quality, and transport characteristics in urban areas at high spatial resolution.
She works with street level images, high resolution sattelite data, and mobile phone data. Methodologically, she is interested in integrating data-driven, a.k.a. machine learning, and hypothesis-driven models to leverage strengths of both the new digital (e.g. large scale continuous, low-cost) and traditional (e.g. semantically rich) data sources.
et al., 2022, What you see is what you breathe? Estimating air pollution spatial variation using street level imagery, Remote Sensing, Vol:14, ISSN:2072-4292
et al., 2022, Street-view greenspace exposure and objective sleep characteristics among children, Environmental Research, Vol:214, ISSN:0013-9351
et al., 2022, A deep learning approach for meter-scale air quality estimation in urban environments using very high-spatial-resolution satellite imagery, Atmosphere, Vol:13, ISSN:2073-4433, Pages:1-16
Casacuberta S, Suel E, Flaxman S, 2021, PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretability, Responsible Ai and Deepspatial Workshops at the 27th Sigkdd Conference on Knowledge Discovery and Data Mining (kdd 2021)