Settlement classification from multi-scale spatial patterns using georeferenced administrative data on buildings in low and middle-income countries

点击翻译按钮获取中文摘要

Model-based population estimates continue to improve with more refined input datasets and moresophisticated modelling techniques to better reflect population distributions. Urban environments,however, remain a challenge for population models. The heterogeneous landscape of cities, from highrisesto industrial estates, and mixed use buildings makes population predictions difficult. Mostpopulation data from a census or survey reflect the residential population, or a "nighttime" populationwhen people are at home, yet for many cities, accurate classifications identifying where these residentialareas are remain lacking.During the day, we know that city population swell with workers, students, shoppers, and othercommuters, yet these populations are generally not accounted for in population estimates. Therefore,improved settlement classification models and building usage are a critical input for improvingpopulation estimates. Accurate urban population models are more important than ever as the majority ofglobal population and population growth are occurring in urban areas.This research is to improve on the existing modelling technique of settlement classification using buildingfootprint and other building characteristics e.g. use, height etc. with a focus on low and middle incomesettings which typically have growing urban centres and often lack up-to-date information on settlementtypes or neighbourhoods. This has been identified as very helpful in identifying slums and informalsettlements, areas of potential health risk, and population density. Also, as urban settlements continue togrow, understanding their morphology, both within and between cities, becomes key for planning,delivering, and monitoring projects in support of sustainable development.