Objectives
General objectives of this research
- Improve our understanding of the relationships between urban deprivation and exposure to temperature variations and extremes
- Develop methods combining advancements in EO and Citizen Science
- Produce evidence of climate vulnerabilities of the urban poor, for setting priorities (most vulnerable first)
- Stimulate awareness and support advocacy with data
- Promote dialogue on low-cost local adaptation measures aimed at improving quality of life
More specifically
- Investigate the spatial variations of air temperature within settlements through machine-learning (ML) modelling, using EO-based covariates and sparse temperature measurements recorded with low-cost sensors (loggers) in a citizen-science approach.
- Capture the high-resolution spatial patterns of thermal susceptibility within settlements through ML modelling, using EO-based covariates, open geospatial data, and sparse micro-survey data collected in collaboration with settlement residents.
- Model the variations of population density within settlements harnessing the power of deep learning modelling using EO imagery and sparse micro-survey data.
- Combine the outputs to highlight areas where high exposure and high susceptibility intersect, and quantify their population.
