Human Settlement Mapping Research Articles

New Insights into Urbanization Based on Global Mapping and Analysis of Human Settlements in the Rural–Urban Continuum

The clear boundary between urban and rural areas is gradually disappearing, and urban and rural areas are two poles of a gradient with many continuous human settlements in between, which is a concept known as the rural–urban continuum. Little is known about the distribution and change trajectories of the various types in the rural–urban continuum across the globe. Therefore, using global land-cover data (FROM-GLC Plus) and global population data (Worldpop) based on the decision-making tree method, this study proposed a method and classification system for global rural–urban continuum mapping and produced the mapping results on a global scale in the Google Earth Engine platform. With the expansion of built-up areas and the increase in population, the global human settlements follow the pattern that develops from wildland to villages (isolated—sparse—dense), and then to towns (sparse—dense), and finally to urban areas (edge—center). From a regional perspective, there are some obvious differences: Africa is dominated by sparse villages; Asia has the highest proportion of densely clustered towns; the proportion of dense villages in Europe is high. Rural–urban continuum mapping and analysis provide a database and new insights into urbanization and differences between urban and rural areas around the world.

Convolutional neural networks for global human settlements mapping from Sentinel-2 satellite imagery

Spatially consistent and up-to-date maps of human settlements are crucial for addressing policies related to urbanization and sustainability, especially in the era of an increasingly urbanized world. The availability of open and free Sentinel-2 data of the Copernicus Earth Observation program offers a new opportunity for wall-to-wall mapping of human settlements at a global scale. This paper presents a deep-learning-based framework for a fully automated extraction of built-up areas at a spatial resolution of 10 m from a global composite of Sentinel-2 imagery. A multi-neuro modeling methodology building on a simple Convolution Neural Networks architecture for pixel-wise image classification of built-up areas is developed. The core features of the proposed model are the image patch of size 5 × 5 pixels adequate for describing built-up areas from Sentinel-2 imagery and the lightweight topology with a total number of 1,448,578 trainable parameters and 4 2D convolutional layers and 2 flattened layers. The deployment of the model on the global Sentinel-2 image composite provides the most detailed and complete map reporting about built-up areas for reference year 2018. The validation of the results with an independent reference dataset of building footprints covering 277 sites across the world establishes the reliability of the built-up layer produced by the proposed framework and the model robustness. The results of this study contribute to cutting-edge research in the field of automated built-up areas mapping from remote sensing data and establish a new reference layer for the analysis of the spatial distribution of human settlements across the rural–urban continuum.

The Politics of Cartographic Calculation and Coordination: State Mapping of Human Settlements in Lima

ABSTRACT This article demonstrates a way of analysing planning governance in relation to human settlements and exposes the micro-politics at play that precipitate particular forms of planning in Lima. Adopting a socio-material perspective, it focuses on mundane institutional practices in the production, use and circulation of cartography, to reveal conflicting and competing rationalities. It uncovers the multiple ways the politics of representation play out through omission, inclusion and partial visibility of low-income settlements, as well as the production and reproduction of cartographic palimpsests, giving way to an urban governance regime that works against the normative objectives of the state.

Domain-Adapted Convolutional Networks for Satellite Image Classification: A Large-Scale Interactive Learning Workflow

Satellite imagery often exhibits large spatial extent areas that encompass object classes with considerable variability. This often limits large-scale model generalization with machine learning algorithms. Notably, acquisition conditions, including dates, sensor position, lighting condition, and sensor types, often translate into class distribution shifts introducing complex nonlinear factors and hamper the potential impact of machine learning classifiers. This paper investigates the challenge of exploiting satellite images using convolutional neural networks (CNN) for settlement classification where the class distribution shifts are significant. We present a large-scale human settlement mapping workflow based-off multiple modules to adapt a pretrained CNN to address the negative impact of distribution shift on classification performance. To extend a locally trained classifier onto large spatial extents areas we introduce several submodules: First, a human-in-the-loop element for relabeling of misclassified target domain samples to generate representative examples for model adaptation; second, an efficient hashing module to minimize redundancy and noisy samples from the mass-selected examples; and third, a novel relevance ranking module to minimize the dominance of source example on the target domain. The workflow presents a novel and practical approach to achieve large-scale domain adaptation with binary classifiers that are based-off CNN features. Experimental evaluations are conducted on areas of interest that encompass various image characteristics, including multisensors, multitemporal, and multiangular conditions. Domain adaptation is assessed on source–target pairs through the transfer loss and transfer ratio metrics to illustrate the utility of the workflow.

Big earth data analytics on Sentinel-1 and Landsat imagery in support to global human settlements mapping

Continuous global-scale mapping of human settlements in the service of international agreements calls for massive volume of multi-source, multi-temporal, and multi-scale earth observation data. In this paper, the latest developments in terms of processing big earth observation data for the purpose of improving the Global Human Settlement Layer (GHSL) data are presented. Two experiments with Sentinel-1 and Landsat data collections were run leveraging on the Joint Research Centre Earth Observation Data and Processing Platform. A comparative analysis of the results of built-up areas extraction from different remote sensing data and processing workflows shows how the information production supported by data-intensive computing infrastructure for optimization and multiple testing can improve the output information reliability and consistency within the GHSL scope. The paper presents the processing workflows and the results of the two main experiments, giving insights into the enhanced mapping capabilities gained by analyzing Sentinel-1 and Landsat data-sets, and the lessons learnt in terms of handling and processing big earth observation data.

Graph-based semi-supervised classification on very high resolution remote sensing images

Classification of very high resolution (VHR) remote sensing imagery is a rapidly emerging discipline but faces several challenges owing to the huge scale of the pixel data involved, indiscernibility in the traditionally used features to represent various regions, and the lack of available ground truth data. This paper provides a framework which elegantly overcomes these hurdles by providing a novel semi-supervised learning approach which employs multiscale superpixel tessellation representations of VHR imagery. Superpixels are homogeneous and irregularly shaped regions which form the backbone of our approach and are used to derive novel features by learning a decision tree. Our semi-supervised learning approach works on a superpixel graph and seamlessly combines the large margin capability of a support vector machine (SVM) with a graph-based Laplacian label propagation approach to obtain a novel objective function. Further we also provide a self-contained and easily parallelisable linear iterative optimisation approach based on the principle of majorisation-minimisation. We evaluate this approach on four different geographic settings with varying neighbourhood types and draw comparisons with the popular and widely used Gaussian multiple instance learning algorithm. Our results showcase several advantages in accuracy and efficiency, which coupled with the ease of model building and inherently parallelisable optimisation make our framework a great choice for deployment in large scale applications like global human settlement mapping and population distribution, and change detection.

Graph-based semi-supervised classification on very high resolution remote sensing images

Classification of very high resolution (VHR) remote sensing imagery is a rapidly emerging discipline but faces several challenges owing to the huge scale of the pixel data involved, indiscernibility in the traditionally used features to represent various regions, and the lack of available ground truth data. This paper provides a framework which elegantly overcomes these hurdles by providing a novel semi-supervised learning approach which employs multiscale superpixel tessellation representations of VHR imagery. Superpixels are homogeneous and irregularly shaped regions which form the backbone of our approach and are used to derive novel features by learning a decision tree. Our semi-supervised learning approach works on a superpixel graph and seamlessly combines the large margin capability of a support vector machine (SVM) with a graph-based Laplacian label propagation approach to obtain a novel objective function. Further we also provide a self-contained and easily parallelisable linear iterative optimisation approach based on the principle of majorisation-minimisation. We evaluate this approach on four different geographic settings with varying neighbourhood types and draw comparisons with the popular and widely used Gaussian multiple instance learning algorithm. Our results showcase several advantages in accuracy and efficiency, which coupled with the ease of model building and inherently parallelisable optimisation make our framework a great choice for deployment in large scale applications like global human settlement mapping and population distribution, and change detection.

DEVELOPMENT OF TIME-SERIES HUMAN SETTLEMENT MAPPING SYSTEM USING HISTORICAL LANDSAT ARCHIVE

Methodology of automated human settlement mapping is highly needed for utilization of historical satellite data archives for urgent issues of urban growth in global scale, such as disaster risk management, public health, food security, and urban management. As development of global data with spatial resolution of 10-100 m was achieved by some initiatives using ASTER, Landsat, and TerraSAR-X, next goal has targeted to development of time-series data which can contribute to studies urban development with background context of socioeconomy, disaster risk management, public health, transport and other development issues. We developed an automated algorithm to detect human settlement by classification of built-up and non-built-up in time-series Landsat images. A machine learning algorithm, Local and Global Consistency (LLGC), was applied with improvements for remote sensing data. The algorithm enables to use MCD12Q1, a MODIS-based global land cover map with 500-m resolution, as training data so that any manual process is not required for preparation of training data. In addition, we designed the method to composite multiple results of LLGC into a single output to reduce uncertainty. The LLGC results has a confidence value ranging 0.0 to 1.0 representing probability of built-up and non-built-up. The median value of the confidence for a certain period around a target time was expected to be a robust output of confidence to identify built-up or non-built-up areas against uncertainties in satellite data quality, such as cloud and haze contamination. Four scenes of Landsat data for each target years, 1990, 2000, 2005, and 2010, were chosen among the Landsat archive data with cloud contamination less than 20%.We developed a system with the algorithms on the Data Integration and Analysis System (DIAS) in the University of Tokyo and processed 5200 scenes of Landsat data for cities with more than one million people worldwide.

DEVELOPMENT OF TIME-SERIES HUMAN SETTLEMENT MAPPING SYSTEM USING HISTORICAL LANDSAT ARCHIVE

Abstract. Methodology of automated human settlement mapping is highly needed for utilization of historical satellite data archives for urgent issues of urban growth in global scale, such as disaster risk management, public health, food security, and urban management. As development of global data with spatial resolution of 10-100 m was achieved by some initiatives using ASTER, Landsat, and TerraSAR-X, next goal has targeted to development of time-series data which can contribute to studies urban development with background context of socioeconomy, disaster risk management, public health, transport and other development issues. We developed an automated algorithm to detect human settlement by classification of built-up and non-built-up in time-series Landsat images. A machine learning algorithm, Local and Global Consistency (LLGC), was applied with improvements for remote sensing data. The algorithm enables to use MCD12Q1, a MODIS-based global land cover map with 500-m resolution, as training data so that any manual process is not required for preparation of training data. In addition, we designed the method to composite multiple results of LLGC into a single output to reduce uncertainty. The LLGC results has a confidence value ranging 0.0 to 1.0 representing probability of built-up and non-built-up. The median value of the confidence for a certain period around a target time was expected to be a robust output of confidence to identify built-up or non-built-up areas against uncertainties in satellite data quality, such as cloud and haze contamination. Four scenes of Landsat data for each target years, 1990, 2000, 2005, and 2010, were chosen among the Landsat archive data with cloud contamination less than 20%.We developed a system with the algorithms on the Data Integration and Analysis System (DIAS) in the University of Tokyo and processed 5200 scenes of Landsat data for cities with more than one million people worldwide.

Assessment of the Added-Value of Sentinel-2 for Detecting Built-up Areas

Monitoring of the human-induced changes and the availability of reliable and methodologically consistent urban area maps are essential to support sustainable urban development on a global scale. The Global Human Settlement Layer (GHSL) is a project funded by the European Commission, Joint Research Centre, which aims at providing scientific methods and systems for reliable and automatic mapping of built-up areas from remote sensing data. In the frame of the GHSL, the opportunities offered by the recent availability of Sentinel-2 data are being explored using a novel image classification method, called Symbolic Machine Learning (SML), for detailed urban land cover mapping. In this paper, a preliminary test was implemented with the purpose of: (i) assessing the applicability of the SML classifier on Sentinel-2 imagery; (ii) evaluating the complementarity of Sentinel-1 and Sentinel-2; and (iii) understanding the added-value of Sentinel-2 with respect to Landsat for improving global high-resolution human settlement mapping. The overall objective is to explore areas of improvement, including the possibility of synergistic use of the different sensors. The results showed that noticeable improvement of the quality of the classification could be gained from the increased spatial detail and from the thematic contents of Sentinel-2 compared to the Landsat derived product as well as from the complementarity between Sentinel-1 and Sentinel-2 images.

Urban Footprint Processor—Fully Automated Processing Chain Generating Settlement Masks From Global Data of the TanDEM-X Mission

The German TerraSAR-X add-on for Digital Elevation Measurement (TanDEM-X) mission (TDM) collects two global data sets of very high resolution (VHR) synthetic aperture radar (SAR) images between 2011 and 2013. Such imagery provides a unique information source for the identification of built-up areas in a so far unique spatial detail. This letter presents the novel implementation of a fully automated processing system for the delineation of human settlements worldwide based on the SAR data acquired in the context of the TDM. The proposed Urban Footprint Processor (UFP) includes three main processing stages dedicated to: i) the extraction of texture information suitable for highlighting regions characterized by highly structured and heterogeneous built-up areas; ii) the generation of a binary settlement layer (built-up, non-built-up) based on an unsupervised classification scheme accounting for both the original backscattering amplitude and the extracted texture; and iii) a final post-editing and mosaicking phase aimed at providing the final Urban Footprint (UF) product for arbitrary geographical regions. Experimental results assess the high potential of the TDM data and the proposed UFP to provide highly accurate geo-data for an improved global mapping of human settlements.

Fast and Efficient Urban Extent Extraction Using ASAR Wide Swath Mode Data

This paper aims at introducing a fast and efficient approach able to extract human settlement extents using ASAR Wide Swath Mode data. The proposed approach exploits the spatial features characterizing human settlements in SAR data at a spatial resolution around 100 m, i.e., long term coherence and large backscattered power values. The joint use of multi-temporal filtering and averaging and the homogeneously high SAR return from built-up structures is the key to extract quickly and robustly human settlement extents. Although prone to commission errors in mountainous areas, the procedure proposed in this paper proved to be able to extract consistently more accurate results than existing global data sets including Globcover 2009. This was assessed by running a series of tests in different geographical areas and comparing the new and the existing products with independently extracted “urban” and “non-urban” points. The results show that ASAR data have no fewer potential than optical ones for global mapping of human settlements. Properly processed, instead, SAR data are able to provide an effective solution to the need of a global map of human settlement, useful for risk computations, climate change model inputs and population mapping, among other applications.

Regional mapping of human settlements in southeastern China with multisensor remotely sensed data

Mapping human settlements from remotely sensed data at regional and global scales has attracted increasingly attention but remains a challenge. The thresholding technique is a common approach for settlement mapping based on the DMSP-OLS data. However, this approach often omits the areas with small proportional settlements such as towns and villages and overestimates urban extents, resulting in information loss of spatial patterns. This paper explored an integrated approach based on a combined use of multiple remotely sensed data to map settlements in southeastern China. Human settlements for selected sites were mapped from Landsat ETM+ images with a hybrid approach and they were used as reference data. The DMSP-OLS and Terra MODIS NDVI data were combined to develop a settlement index image. This index image was used to map a pixel-based settlement image with expert rules. A regression model was established to estimate fractional settlements at the regional scale, which the DMSP-OLS and MODIS NDVI data were used as independent variables and the settlement data derived from ETM+ images were used as a dependent variable. This research indicated that a combination of DMSP-OLS and NDVI variables provided a better estimation performance than single DMSP-OLS or NDVI variable, and the integrated approach for settlement mapping at the regional scale was promising. Compared to the results from the traditional thresholding technique, the estimated fractional settlement image in this paper greatly improved the spatial patterns of settlement distribution and accuracy of settlement areas. This paper provided a rapid and accurate approach to estimate fractional settlements from coarse spatial resolution images at the regional scale by combining a limited number of medium spatial resolution images. This research is especially valuable for timely updating settlement databases at regional and global scales with limited time, labor, and cost.

A new method for minimizing topographic effects on RADARSAT-1 images: an application in mapping human settlements in the mountainous Three Gorges Area, China

In this paper, a new method is proposed for minimizing topographic effects on RADARSAT-1 synthetic aperture radar (SAR) images in a mountainous region. Vegetation classes in terrain-affected areas (layover and foreshortening) and the human settlement class in non-affected areas on SAR images often appear with almost the same brightness and cannot be separated. As such, SAR application to land use/land cover mapping in mountainous areas is hindered. The suggested procedures include terrain effect simulation, normalization, and slope correction for SAR images. The possibility of using RADARSAT-1 images to detect human settlements in the mountainous Three Gorges Area, China, is investigated. The performance of various radiometric correction methods are compared and evaluated. In this case study, the separability between vegetation in terrain-affected areas and human settlements was successfully improved using the proposed method. Among all the images corrected using different methods, the one corrected by the proposed method for topographic correction produced the best result for mapping human settlements and other land use and land cover classes. The producer accuracy of human settlement mapping from the SAR image increased from 16.1% before correction to 46.4% after correction, the user accuracy increased from 20.9% to 39.4%, and kappa increased from 0.13 to 0.33.

Mapping of settlements in high-resolution satellite imagery using high performance computing

Classifying urban land cover from high-resolution satellite imagery is challenging, and those challenges are compounded when the imagery databases are very large. Accurate land cover data is a crucial component of the population distribution modeling efforts of the Oak Ridge National Laboratory’s (ORNL) LandScan Program. Currently, LandScan Program imagery analysts manually interpret high-resolution (1–5 m) imagery to augment existing satellite-derived medium (30 m) and coarse (1 km) resolution land cover datasets. For LandScan, the high-resolution image archives that require interpretation are on the order of terabytes. The goal of this research is to automate human settlement mapping by utilizing ORNL’s high performance computing capabilities. Our algorithm employs gray-level and local edge-pattern co-occurrence matrices to generate texture and edge patterns. Areas of urban land cover correlate with statistical features derived from these texture and edge patterns. We have parallelized our algorithms for implementation on a 64-node system using a single instruction multiple data programming model (SIMD) with Message Passing Interface (MPI) as the communication mode. Our parallel-configured classifier performs 30–40 times faster than stand-alone alternatives. We have tested our system on IKONOS imagery. The early results are promising, pointing towards future large-scale classification of human settlements at high-resolution.