Big Data

The Big Data group applies deep learning methods to various big data sources, especially high resolution satellite data and street imagery, to characterise urban environmental features and exposures, including housing, the social environment, air quality, noise and the transportation environment (mode, street safety, etc.) and to evaluate how urban land use and service delivery policies could impact health.  The group also advances methodologies for the use of big data, such as how best to combine satellite and street level images, transferability of prediction models trained in one city to others, and the use of images to evaluate temporal change.


Related Publications

10 entries « 1 of 2 »

Suel E, Bhatt S, Brauer M, Flaxman S, Ezzati M

Multimodal deep learning from satellite and street-level imagery for measuring income, overcrowding, and environmental deprivation in urban areas

Remote Sensing of Environment, 257 , pp. 112339, 2021.

()

Suel E, Sorek-Hamer M, Moise I, von Pohle M, Sahasrabhojanee A, Asanjan A, Deardorff E, Lingenfelter V, Oza N, Ezzati M, Brauer M

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) 2020.

()

Li F, Li F, Li S, Long Y

Deciphering the recreational use of urban parks: Experiments using multi-source big data for all Chinese cities

Science of the Total Environment, 701 (1), pp. 134896, 2020.

()

Zhang ZX, Long Y

Application of Wearable Cameras in Studying Individual Behaviors in Built Environments

Landscape Architecture Frontiers, 7 (2), pp. 22-37, 2019.

()

Suel E, Polak JW, Bennett JE, Ezzati M

Measuring social, environmental and health inequalities using deep learning and street imagery

Scientific Reports, 9 , pp. 6229, 2019.

()

10 entries « 1 of 2 »