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., 2021, Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas, Remote Sensing of Environment: an Interdisciplinary Journal, Vol:257, ISSN:0034-4257
et al., 2020, Predicting fine particulate matter (PM2.5) in the Greater London area: an ensemble approach using machine learning methods, Remote Sensing, Vol:12, ISSN:2072-4292, Pages:1-18
et al., 2019, Measuring social, environmental and health inequalities using deep learning and street imagery, Scientific Reports, Vol:9, ISSN:2045-2322
Suel E, Polak J, 2018, Incorporating online shopping into travel demand modelling: challenges, progress, and opportunities, Transport Reviews, Vol:38, ISSN:0144-1647, Pages:576-601
et al., 2020, Predicting air pollution spatial variation with street-level imagery, Machine Learning in Public Health (MLPH) Workshop, 34th Conference on Neural Information Processing Systems (NeurIPS 2020), NeurIPS