Module 48: A review of mapping techniques of slums using machine learning, remote sensing, and volunteered geographic information

Faculty Contact: Krzysztof Janowicz

Research Areas:

Over the past two decades, urbanization has increased the population of individuals residing in cities. By proxy, individuals living in urban slums have similarly increased. Health provision to slum communities are limited by the informal planning of slum communities and the lack of navigational and cartographic information about these informal settlements. This review will describe the current techniques used to map informal settlements, specifically focusing on methodologies that utilize Big Data techniques to predict the underlying pathways of a slum area. Furthermore, it will justify how the MoveMap project can fill gaps in our understanding of slums and their internal network structure, where nodes are representations of locations of interest (latrines, health clinics, homes, etc.) and edges are the pathways that connect them. The MoveMap project aims to elucidate pathways within urban slums in developing cities by using a combination of machine learning, remote sensing, and volunteered geographic information from GPS-enabled mobile devices. Using either GPS-enabled mobile phones or personal GPS trackers, the daily movement patterns of a subset of residents in a given slum will be recorded and saved. These movement patterns will be merged and overlaid to create an overall map of the slum area. The eventual aim of MoveMap is to utilize a continuous stream of GPS-tracked movement pathways to create dynamic maps of areas undergoing continuous change.


Active Quarters:

  • Spring 2018: Vania Wang