2018/08/14 by Mohamed R. Ibrahim, Helena Titheridge, Ibrahim, Mohamed R. +6
Economics, Econometrics and Finance · Environmental Science · Social Sciences · #Computers and Society (cs.CY) #FOS: Computer and information sciences #Impact of Light on Environment and Health #Land Use and Ecosystem Services #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Spatial and Panel Data Analysis #Urban Transport and Accessibility
paper · pdf · doi:10.48550/arxiv.1808.06470
openalex publication_date 2018/08/14 · openalex created_date 2022/08/04 · openalex updated_date 2026/07/28
Identifying current and future informal regions within cities remains a\ncrucial issue for policymakers and governments in developing countries. The\ndelineation process of identifying such regions in cities requires a lot of\nresources. While there are various studies that identify informal settlements\nbased on satellite image classification, relying on both supervised or\nunsupervised machine learning approaches, these models either require multiple\ninput data to function or need further development with regards to precision.\nIn this paper, we introduce a novel method for identifying and predicting\ninformal settlements using only street intersections data, regardless of the\nvariation of urban form, number of floors, materials used for construction or\nstreet width. With such minimal input data, we attempt to provide planners and\npolicy-makers with a pragmatic tool that can aid in identifying informal zones\nin cities. The algorithm of the model is based on spatial statistics and a\nmachine learning approach, using Multinomial Logistic Regression (MNL) and\nArtificial Neural Networks (ANN). The proposed model relies on defining\ninformal settlements based on two ubiquitous characteristics that these regions\ntend to be filled in with smaller subdivided lots of housing relative to the\nformal areas within the local context, and the paucity of services and\ninfrastructure within the boundary of these settlements that require relatively\nbigger lots. We applied the model in five major cities in Egypt and India that\nhave spatial structures in which informality is present. These cities are\nGreater Cairo, Alexandria, Hurghada and Minya in Egypt, and Mumbai in India.\nThe predictSLUMS model shows high validity and accuracy for identifying and\npredicting informality within the same city the model was trained on or in\ndifferent ones of a similar context.\n