Abstract:The body of scientific literature on slum mapping employing remote sensing methods has increased since the availability of more very-high-resolution (VHR) sensors. This improves the ability to produce information for pro-poor policy development and to build methods capable of supporting systematic global slum monitoring required for international policy development such as the Sustainable Development Goals. This review provides an overview of slum mapping-related remote sensing publications over the period of 2000-2015 regarding four dimensions: contextual factors, physical slum characteristics, data and requirements, and slum extraction methods. The review has shown the following results. First, our contextual knowledge on the diversity of slums across the globe is limited, and slum dynamics are not well captured. Second, a more systematic exploration of physical slum characteristics is required for the development of robust image-based proxies. Third, although the latest commercial sensor technologies provide image data of less than 0.5 m spatial resolution, thereby improving object recognition in slums, the complex and diverse morphology of slums makes extraction through standard methods difficult. Fourth, successful approaches show diversity in terms of extracted information levels (area or object based), implemented indicator sets (single or large sets) and methods employed (e.g., object-based image analysis (OBIA) or machine learning). In the context of a global slum inventory, texture-based methods show good robustness across cities and imagery. Machine-learning algorithms have the highest reported accuracies and allow working with large indicator sets in a computationally efficient manner, while the upscaling of pixel-level information requires further research. For local slum mapping, OBIA approaches show good capabilities of extracting both area-and object-based information. Ultimately, establishing a more systematic relationship between higher-level image elements and slum characteristics is essential to train algorithms able to analyze variations in slum morphologies to facilitate global slum monitoring.Keywords: slums; informal areas; urban remote sensing; Global South; VHR imagery Global Urbanization and Slum Dynamics: The ContextCurrently, about one-quarter of the world's urban population lives in slums, which are defined by UN-Habitat as informal settlements [1] or areas deprived of access to safe water, acceptable sanitation, and durable housing; in addition to being areas that are overcrowded and lack land tenure security [2]. Over the last 15 years, there has been renewed interest in slum improvement and eradication by local and international organizations dealing with development issues. During this period, slums became a more prominent subject of remote sensing (RS) image analysis. Supported by increased availability of very-high-resolution (VHR) data and methodological advances, many RS studies [3][4][5][6][7][8] aimed to produce information on the geography and dynamics of slums. ...

Many cities in the global South are facing the emergence and growth of highly dynamic slum areas, but often lack detailed information on these developments. Available statistical data are commonly aggregated to large, heterogeneous administrative units that are geographically meaningless for informing effective pro-poor policies. General base information neither allows spatially disaggregated analysis of deprived areas nor monitoring of rapidly changing settlement dynamics, which characterize slums. This paper explores the utility of the gray-level co-occurrence matrix (GLCM) variance to distinguish between slums and formal built-up (formal) areas in very high spatial and spectral resolution satellite imagery such as WorldView-2, OrbView, Quickbird, and Resourcesat. Three geographically different cities are selected for this investigation: Mumbai and Ahmedabad, India and Kigali, Rwanda. The exploration of the utility and transferability of the GLCM shows that the variance of the GLCM combined with the normalized difference vegetation index (NDVI) is able to separate slums and formal areas. The overall accuracy achieved is 84% in Kigali, 87% in Mumbai, and 88% in Ahmedabad. Furthermore, combining spectral information with the GLCM variance within a random forest classifier results in a pixel-based classification accuracy of 90%. The final slum map, aggregated to homogenous urban patches (HUPs), shows an accuracy of 88%-95% for slum locations depending on the scale parameter.

Information about unplanned settlements in cities in developing countries is often unavailable or incomplete, mainly due to a combination of their informal development and capacity constraints of planning authorities. Despite the extent of unplanned areas in many countries, which at times can dominate residential land-use, very few tools exist for their identification and monitoring. Therefore, there is a clear need for such tools to support timely updating of spatial databases. The present research aims to contribute to the development of such tools, by using spatial metrics to characterise the morphology of unplanned urban settlements in VHR images. The methodology was tested in two case study areas: Dar es Salaam (Tanzania) and New Delhi (India). The research methodology is built on using image segmentation and on the assumption that segments representing homogenous urban patches are different in planned and unplanned areas. Homogenous urban patches were extracted using multi-resolution image segmentation. The morphological aspects (size, density and layout pattern) of planned and unplanned patches were then analysed using spatial metrics. A set of metrics that reflected morphological characteristics of unplanned settlements was identified. This final set was used to build an 'unplanned settlement index' (USI) using spatial multi-criteria evaluation methods. Comparison between results and available land use data showed that the index can assist in the identification of unplanned settlements, with an accuracy of 73% for five selected parts of New Delhi and 75% for Dar es Salaam%.

No abstract

Despite an estimated one billion people around the world living in slums, most surveys of health and well-being do not distinguish between slum and non-slum urban residents. Identifying people who live in slums is important for research purposes and also to enable policymakers, programme managers, donors and non-governmental organisations to better target investments and services to areas of greatest deprivation. However, there is no consensus on what a slum is let alone how slums can be distinguished from non-slum urban precincts. Nor has attention been given to a more fine-grained classification of urban spaces that might go beyond a simple slum/non-slum dichotomy. The purpose of this paper is to provide a conceptual framework to help tackle the related issues of slum definition and classification of the urban landscape. We discuss:The concept of space as an epidemiological variable that results in ‘neighbourhood effects’.The problems of slum area definition when there is no ‘gold standard’.A long-list of variables from which a selection must be made in defining or classifying urban slum spaces.Methods to combine any set of identified variables in an operational slum area definition.Two basic approaches to spatial slum area definitions—top-down (starting with a predefined area which is then classified according to features present in that area) and bottom-up (defining the areal unit based on its features).Different requirements of a slum area definition according to its intended use.Implications for research and future development.

The continuous increase in deprived living conditions in many cities of the Global South contradicts efforts to make cities inclusive, safe, resilient, and sustainable places. Using examples of Asian, African, and Latin American cities, this study shows the scope and limits of earth observation (EO)-based mapping of deprived living conditions in support of providing consistent global information for the SDG indicator 11.1.1 “proportion of urban population living in slums, informal settlements or inadequate housing”. At the technical level, we compare several EO-based methods and imagery for mapping deprived living conditions, discussing their ability to map such areas including differences in terms of accuracy and performance at the city scale. At the operational level, we compare available municipal maps showing identified deprived areas with the spatial extent of morphological mapped areas of deprived living conditions (using EO) at the city scale, discussing the reasons for inconsistencies between municipal and EO-based maps. We provide an outlook on how EO-based mapping of deprived living conditions could contribute to a global spatial information base to support targeting of deprived living conditions in support of the SDG Goal 11.1.1 indicator, when uncertainties and ethical considerations on data provision are well addressed.

In the cities of the Global South, slum settlements are growing in size and number, but their locations and characteristics are often missing in official statistics and maps. Although several studies have focused on detecting slums from satellite images, only a few captured their variations. This study addresses this gap using an integrated approach that can identify a slums’ degree of deprivation in terms of socio-economic variability in Bangalore, India using image features derived from very high resolution (VHR) satellite images. To characterize deprivation, we use multiple correspondence analysis (MCA) and quantify deprivation with a data-driven index of multiple deprivation (DIMD). We take advantage of spatial features learned by a convolutional neural network (CNN) from VHR satellite images to predict the DIMD. To deal with a small training dataset of only 121 samples with known DIMD values, insufficient to train a deep CNN, we conduct a two-step transfer learning approach using 1461 delineated slum boundaries as follows. First, a CNN is trained using these samples to classify slums and formal areas. The trained network is then fine-tuned using the 121 samples to directly predict the DIMD. The best prediction is obtained by using an ensemble non-linear regression model, combining the results of the CNN and models based on hand-crafted and geographic information system (GIS) features, with R2 of 0.75. Our findings show that using the proposed two-step transfer learning approach, a deep CNN can be trained with a limited number of samples to predict the slums’ degree of deprivation. This demonstrates that the CNN-based approach can capture variations of deprivation in VHR images, providing a comprehensive understanding of the socio-economic situation of slums in Bangalore.

The survey-based slum mapping (SBSM) program conducted by the Indonesian government to reach the national target of “cities without slums” by 2019 shows mapping inconsistencies due to several reasons, e.g., the dependency on the surveyor’s experiences and the complexity of the slum indicators set. By relying on such inconsistent maps, it will be difficult to monitor the national slum upgrading program’s progress. Remote sensing imagery combined with machine learning algorithms could support the reduction of these inconsistencies. This study evaluates the performance of two machine learning algorithms, i.e., support vector machine (SVM) and random forest (RF), for slum mapping in support of the slum mapping campaign in Bandung, Indonesia. Recognizing the complexity in differentiating slum and formal areas in Indonesia, the study used a combination of spectral, contextual, and morphological features. In addition, sequential feature selection (SFS) combined with the Hilbert–Schmidt independence criterion (HSIC) was used to select significant features for classifying slums. Overall, the highest accuracy (88.5%) was achieved by the SVM with SFS using contextual, morphological, and spectral features, which is higher than the estimated accuracy of the SBSM. To evaluate the potential of machine learning-based slum mapping (MLBSM) in support of slum upgrading programs, interviews were conducted with several local and national stakeholders. Results show that local acceptance for a remote sensing-based slum mapping approach varies among stakeholder groups. Therefore, a locally adapted framework is required to combine ground surveys with robust and consistent machine learning methods, for being able to deal with big data, and to allow the rapid extraction of consistent information on the dynamics of slums at a large scale.