Table of Contents
Urban growth mapping has emerged as one of the most critical applications of satellite technology in the 21st century, enabling researchers, city planners, and policymakers to understand and manage the rapid transformation of human settlements across the globe. In 2026, advances in sensors, open data, and AI have transformed satellite imagery into a universal tool used to monitor climate change, track conflicts, guide urban development, and support disaster response. This comprehensive approach to monitoring urban expansion provides unprecedented insights into how cities evolve, where populations concentrate, and how infrastructure must adapt to accommodate growing communities.
Understanding Urban Growth Through Satellite Technology
The application of satellite imagery to urban monitoring represents a fundamental shift in how we understand and plan for human settlement development. Satellite imagery for urban and land development can be used to gather strategic planning information pertaining to a district or an entire city. This bird’s-eye perspective offers advantages that ground-based surveys simply cannot match, including the ability to monitor vast areas simultaneously, track changes over time with consistent methodology, and access regions that may be difficult or dangerous to reach on foot.
Recent advances in big data computing and machine learning are allowing us to take advantage of growing catalogs of open-source imagery and to produce maps of the ever-changing urban environment at unprecedented scale, timeliness, and accuracy. These technological improvements have democratized access to urban monitoring capabilities, making sophisticated analysis tools available to researchers and planners worldwide, not just those in wealthy nations or well-funded institutions.
The Evolution of Satellite-Based Urban Monitoring
Satellite technology has undergone remarkable evolution since its early days. Modern satellites capture images with resolutions that were unimaginable just a few decades ago. The satellite sensors deliver 16-Bit 4-Band or 8-Band multispectral pixel resolutions from 1.2-meters to 5-meters, with pansharpened vegetation indices delivered with a resolution of 30cm, 40cm, or 50cm, providing great detail for vegetation and environmental analysis for urban planning and development.
The integration of multiple data sources has become standard practice in contemporary urban analysis. The World Settlement Footprint, a suite of map layers developed by the German Aerospace Center (DLR) in collaboration with the European Space Agency (ESA), the Google Earth Engine team, and the World Bank, combines multispectral and radar-based satellite imagery to help inform decisions for a myriad of operations, from understanding urbanization patterns over time.
The Science of Human Settlement Pattern Analysis
Understanding human settlement patterns goes far beyond simply identifying where buildings exist. Settlement patterns refer to the spatial distribution and arrangement of human settlements across a landscape, influenced by various factors such as environment, economic activities, transportation networks, cultural practices, and historical developments, reflecting how communities organize themselves in geographic space and interact with their environment and each other.
Types of Settlement Patterns
Settlement patterns can be classified into several distinct types, each revealing different aspects of how human communities organize themselves spatially. Settlement patterns describe the spatial distribution of human settlements or agricultural practices, with three main types: clustered, dispersed, and linear.
Clustered settlements are characterized by densely packed communities with minimal space between individual structures. These patterns typically emerge in areas where resources are concentrated, where defense was historically important, or where social and economic interactions benefit from proximity. Urban cores and traditional villages often exhibit clustered patterns.
Dispersed settlements feature significant spacing between individual dwellings and structures. This pattern is common in agricultural regions where families need access to larger land parcels, or in areas where resources are distributed across the landscape rather than concentrated in specific locations.
Linear settlements develop along transportation corridors, waterways, or other geographic features that create natural axes for development. Roads, rivers, coastlines, and valleys frequently serve as organizing features for linear settlement patterns.
Factors Influencing Settlement Distribution
Some of the processes driving the physical changes in human settlements are population and economic growth, rural-urban migration, and in-situ urban transformation that also includes the envelopment of small settlements by larger ones and land-expansive development. These forces interact in complex ways, creating unique settlement patterns in different regions and time periods.
Environmental factors play a crucial role in determining where and how settlements develop. Topography, water availability, climate, soil quality, and natural hazards all influence settlement location decisions. Influences of topographic factors (elevation, slope and aspect) on settlement locations were stronger across hilly regions. This demonstrates how physical geography continues to shape human settlement choices even in the modern era.
Economic considerations also drive settlement patterns. Access to employment opportunities, markets, transportation infrastructure, and natural resources creates economic incentives that attract population concentration in specific locations. The interplay between economic opportunity and settlement growth creates feedback loops where successful settlements attract more residents and investment, further reinforcing growth patterns.
Advanced Techniques for Satellite Image Analysis
Modern urban growth mapping relies on sophisticated analytical techniques that extract meaningful information from satellite imagery. These methods have evolved significantly with the advent of artificial intelligence and machine learning, enabling automated analysis of vast datasets that would be impossible to process manually.
Image Classification Methods
Image classification forms the foundation of satellite-based urban analysis. This process involves categorizing each pixel or group of pixels in an image according to what type of land cover or land use it represents. Classification algorithms can distinguish between built-up areas, vegetation, water bodies, bare soil, and other land cover types based on their spectral signatures—the unique patterns of light reflection and absorption that different materials exhibit.
Supervised classification requires training data where analysts identify examples of each land cover type, which the algorithm then uses to classify the rest of the image. Unsupervised classification allows algorithms to identify natural groupings in the data without pre-defined categories, which can reveal unexpected patterns or land cover types.
Daylight satellite imagery used in conjunction with deep-learning methodologies enables a standardized, fine-grained measurement of urban density and functional growth across space and time, with deep learning offering a more scalable and transferable alternative that learns patterns directly from imagery and captures spatial patterns through convolutions, enabling retrospective analysis of urban patterns using historical satellite archives.
Change Detection Algorithms
Change detection represents one of the most valuable applications of satellite imagery for urban growth monitoring. By comparing images of the same area captured at different times, analysts can identify where urban expansion has occurred, where vegetation has been cleared, or where infrastructure has been developed.
Timely and accurate urban change detection is vital for sustainable urban development, infrastructure management, and disaster response, with three-dimensional change detection frameworks integrating high-resolution optical imagery and Digital Surface Models from two time points to capture both horizontal and vertical transformations. This three-dimensional approach represents a significant advancement over traditional two-dimensional methods, as it can detect not just the expansion of urban areas but also the vertical growth represented by taller buildings.
Recent advances in deep learning, particularly Convolutional Neural Networks, have demonstrated remarkable potential for automatic feature extraction and pattern recognition in remote sensing, with encoder-decoder architectures such as UNet and its variants showing strong performance in semantic segmentation tasks, enabling models to learn both local and contextual information.
Building Footprint Extraction
The extraction of individual building footprints from satellite imagery has become increasingly automated and accurate. Increasing availability of very high resolution imagery (<1 m spatial resolution) and computing power is enabling complete sets of settlement data in the form of building footprints to be extracted from imagery. These detailed building datasets provide granular information about urban structure and density.
The open-data GlobalBuildingAtlas is the first high-resolution 3D map of 2.75 billion buildings worldwide, derived from satellite imagery by researchers at the Technical University of Munich, opening up new possibilities for understanding how cities grow, how infrastructure is shaped, and how risks unfold, providing a powerful new basis for climate research and for tracking progress towards the UN Sustainable Development Goals.
Building footprint data enables sophisticated analysis of urban morphology—the physical form and structure of cities. While spatially detailed, extracted building footprints typically lack other information that identify building types or can be used to differentiate intra-urban land uses or neighbourhood types, but work demonstrates an approach to classifying settlement types through multi-scale spatial patterns of urban morphology visible in building footprint data.
Geographic Information Systems in Urban Analysis
Geographic Information Systems (GIS) serve as the essential platform for integrating, analyzing, and visualizing satellite imagery alongside other spatial datasets. High-resolution satellite imagery and LiDAR incorporated into a GIS map and CAD has gained popularity among planners, developers, and engineers for large-scale mapping of any region for most urban and land development applications.
Spatial Data Integration
The power of GIS lies in its ability to combine multiple layers of information. Satellite imagery forms one layer, but GIS platforms can integrate this with census data, infrastructure maps, environmental datasets, socioeconomic information, and many other data types. This integration enables analysts to examine relationships between different variables and understand the complex factors driving urban growth.
Information from satellite images when combined with GIS maps is used for analysis in evaluating construction costs as well as environmental impact of alternative routes for utility and transport corridors for land cover and land use classification, and identifying population groups at risk where human intervention is most needed to limit and prevent hazards during development stages.
Spatial data and mapping techniques from Geographic Information Systems are often employed to analyze settlement patterns, allowing researchers to visualize and interpret the underlying factors influencing how and where settlements develop. This visualization capability makes complex spatial relationships comprehensible to decision-makers and stakeholders who may not have technical expertise in spatial analysis.
Spatial Analysis Techniques
GIS platforms provide numerous analytical tools specifically designed for understanding spatial patterns. Proximity analysis can identify areas within certain distances of infrastructure or services. Density analysis reveals concentrations of population or development. Network analysis can model transportation systems and accessibility. Terrain analysis examines how topography influences development patterns.
Point pattern analysis techniques help researchers understand whether settlements are randomly distributed, clustered, or regularly spaced. Ripley’s K function and the Monte Carlo method describe the characteristics of settlement point patterns and formally test them against a CSR hypothesis, while regression identifies the effects of topographic factors on the spatial structure of settlement patterns.
Applications in Urban Planning and Policy
The insights gained from satellite-based urban growth mapping have direct applications in planning and policy decisions that affect millions of people. Understanding where and how cities are growing enables more effective and equitable urban development.
Infrastructure Planning
Satellite imagery helps planners identify where infrastructure investments are most needed. By mapping population distribution and growth patterns, authorities can prioritize the construction of roads, water systems, electrical grids, schools, hospitals, and other essential services in areas where they will serve the most people or where growth is expected to occur.
Products such as the World Settlement Footprint augment analytical and diagnostic products such as Climate Change Development Reports and City Scans by helping visualize settlement expansion over time, showing where the most recent growth is happening, allowing identification and tracking of informal versus formally approved expansion, and identifying geographical barriers that limit the smart expansion of settlements.
The 3D building data from GlobalBuildingAtlas enables cities to plan additional housing or public facilities such as schools and health centres in densely populated, disadvantaged neighbourhoods, while the data plays a crucial role in climate adaptation, improving models on topics such as energy demand and carbon emissions, and supporting the planning of green infrastructure.
Monitoring Informal Settlements
One particularly important application of satellite-based urban monitoring is the detection and mapping of informal settlements, which house a significant portion of urban populations in many developing countries. The method improves the detection of small and fragmented structures, including emerging informal settlements that global datasets frequently miss.
Understanding the location, extent, and growth of informal settlements is crucial for providing services to these communities and improving living conditions. Satellite imagery can identify these areas even when they lack formal addresses or appear in official records, ensuring that planning efforts account for all residents.
Sustainable Development Monitoring
Satellite imagery provides objective, consistent data for tracking progress toward sustainable development goals. In some parts of the world, particularly the global South, urbanization occurs at rates that generate unprecedented city sizes, and with increasing city size comes unprecedented challenges including air pollution, uncontrolled and unplanned urban growth, and the need for improved efficiency in the transport sector as well as in fuel and energy consumption.
Monitoring urban green spaces represents another important sustainability application. The rapid development and growth of urban areas are putting increased pressure on the environment including green spaces and urban parks, with green spaces including street landscapes, lawns, public park areas, gardens, crops, and forests needed to improve the urban areas and to provide a quality of life to the population.
Remote Sensing Technologies and Data Sources
Multiple satellite systems and remote sensing technologies contribute to urban growth mapping, each offering different capabilities and advantages. Understanding these various data sources helps analysts select the most appropriate imagery for specific applications.
Optical Satellite Imagery
Optical satellites capture images using visible light and nearby wavelengths, similar to how cameras work. These systems provide intuitive, photo-like images that are easy to interpret. Different spectral bands capture different wavelengths of light, revealing information about vegetation health, water content, built materials, and other surface characteristics.
The use of medium resolution satellite imagery such as Landsat, Sentinel-2, and SPOT proved to benefit in the analysis of changes in the vegetation and environment from different years or time periods during the same season which helps to analyze the change that occurred in the past to making the decision on moving forward with planning and development of urban areas. These freely available datasets provide consistent, long-term records that enable historical analysis of urban growth.
High-resolution stereo satellite sensors, such as GeoEye-1, WorldView-2, WorldView-3, WorldView-4, and the Pleiades Neo satellite constellation can provide a variety of geospatial data for analysis of vegetation and green spaces for the development of sustainable urban areas. These commercial satellites offer the highest resolution imagery available, enabling detailed analysis of individual buildings and small-scale features.
Radar and LiDAR Systems
Radar satellites use microwave energy rather than visible light, allowing them to capture images regardless of cloud cover or darkness. This capability is particularly valuable in tropical regions where persistent cloud cover often obscures optical imagery. Radar can also penetrate vegetation to some degree and is sensitive to surface texture and moisture.
LiDAR offers a high-quality three-dimensional mapping, but it is very costly to be used on a large scale and with repeated time observations per spatial unit, while traditional machine learning methods can help estimating building heights from widely available optical and radar images, but they typically need to rely on expert-driven feature engineering, which limits the transferability of their pipeline to other settings.
Nighttime Light Data
Satellite sensors that capture nighttime lights provide unique insights into human activity and energy consumption. The intensity and spatial distribution of artificial lighting correlates with population density, economic activity, and development levels. Changes in nighttime lights over time can indicate economic growth or decline, electrification of previously dark areas, or shifts in activity patterns.
By capturing patterns in building density and the presence of vegetation, the World Settlement Footprint datasets can assess the intensity of urban heat islands, while urban density and building height can be used to approximate energy demand, air quality, and many more aspects of cities.
Challenges and Limitations
Despite the tremendous capabilities of satellite-based urban growth mapping, several challenges and limitations must be acknowledged and addressed to ensure accurate and useful results.
Data Quality and Availability
Cloud cover represents a persistent challenge for optical satellite imagery, particularly in tropical and coastal regions where clouds are frequent. While radar systems can overcome this limitation, they produce images that are more difficult to interpret and may not capture all the information needed for comprehensive urban analysis.
Temporal resolution—how frequently satellites revisit the same location—affects the ability to capture rapid changes. While some satellites provide daily coverage, high-resolution commercial satellites may only image a specific location every few weeks or months unless specifically tasked to do so, which can be expensive.
Access to high-resolution commercial imagery remains limited by cost for many researchers and planning agencies, particularly in developing countries where urban growth is most rapid and monitoring is most needed. While free and open data sources like Landsat and Sentinel have democratized access to satellite imagery, their moderate resolution may not capture all the details needed for local-scale planning.
Technical and Methodological Challenges
Accurately classifying land cover and detecting changes requires sophisticated algorithms and expertise. Different urban materials can have similar spectral signatures, making it difficult to distinguish between them. Shadows from tall buildings can obscure features and complicate classification. Seasonal variations in vegetation can be mistaken for land cover changes if not properly accounted for.
Traditional two-dimensional approaches often overlook vertical and structural variations in dense urban areas, and while traditional 2D change detection methods such as image differencing, principal component analysis, and change vector analysis primarily rely on spectral information and can identify surface-level changes, they often fail to capture vertical modifications such as building height variations that are common in dense urban environments.
Validation and Accuracy Assessment
Ensuring that satellite-derived maps accurately represent conditions on the ground requires validation through field surveys or comparison with other authoritative data sources. This validation process can be time-consuming and expensive, particularly for large areas. Without proper validation, errors in classification or change detection may go unnoticed and lead to poor planning decisions.
Emerging Trends and Future Directions
The field of satellite-based urban growth mapping continues to evolve rapidly, with new technologies and approaches constantly emerging. Understanding these trends helps anticipate future capabilities and applications.
Artificial Intelligence and Machine Learning
AI and machine learning are transforming satellite image analysis, enabling automated processing of vast datasets and detection of subtle patterns that human analysts might miss. The use of AI/ML algorithms and a CV or GIS managements system can provide a cost effective to obtain satellite imagery to monitor and automatically identify green spaces, improving urban environments, and plays an important role to life all around us.
Deep learning models can now extract building footprints, classify land use types, detect changes, and even predict future growth patterns with increasing accuracy. These capabilities are making sophisticated analysis accessible to users without extensive technical expertise in remote sensing.
Integration of Multiple Data Sources
The Global Human Settlement Layer framework produces global spatial information about the human presence on the planet over time, using heterogeneous data including global archives of fine-scale satellite imagery, census data, and volunteered geographic information, with data processed fully automatically and generating analytics and knowledge reporting objectively and systematically about the presence of population and built-up infrastructures.
The integration of satellite imagery with social media data, mobile phone records, crowdsourced mapping, and other novel data sources provides richer, more comprehensive understanding of urban dynamics. These diverse data streams complement each other, with satellite imagery providing consistent spatial coverage while other sources add temporal detail and information about human behavior and activities.
Real-Time Monitoring and Rapid Response
Advances in satellite technology and data processing are enabling near-real-time monitoring of urban areas. Real-time monitoring of wildfires, floods, and droughts using AI-enabled change detection demonstrates capabilities that are increasingly being applied to urban monitoring as well. This rapid analysis supports emergency response, disaster management, and timely decision-making.
Three-Dimensional Urban Modeling
The shift from two-dimensional to three-dimensional urban analysis represents a significant advancement. Three-dimensional models visualize not only the footprint but also the volume of each building, enabling far more precise insights into urbanization, living conditions and poverty than traditional 2D maps.
Three-dimensional models support more sophisticated analysis of urban density, energy consumption, climate impacts, and many other factors that depend on building volume and height, not just footprint area. These models are becoming increasingly detailed and accessible as data sources and processing capabilities improve.
Case Studies and Real-World Applications
Examining specific examples of satellite-based urban growth mapping in action illustrates the practical value and diverse applications of these technologies.
Mapping Urban Expansion in Developing Cities
A study introduces a practical method that combines satellite imagery with partially labeled information and targeted manual refinement to identify new built-up areas in Metropolitan Lima from 2016 to 2025, with results showing that Metropolitan Lima expanded by approximately 76 km2 during the study period. This type of detailed expansion monitoring helps city authorities understand growth patterns and plan infrastructure accordingly.
Building Function Classification in China
SinoBF-1, a national building functional map of China, delineates 110 million buildings across 109 major cities using 1-meter multi-modal satellite data, using nine indicators spanning urbanization intensity, facility accessibility, and infrastructure sufficiency to quantify disparities across city tiers, geographic regions, and intra-city zones, revealing that accessibility and amenity diversity decline sharply from top- to low-tier cities, while mid tiers show more equitable housing allocation.
This comprehensive mapping effort demonstrates how satellite imagery combined with advanced analysis can reveal patterns of inequality and inform policies to promote more equitable urban development.
Global Settlement Monitoring
The HPI aims to measure and monitor human presence on planet Earth and to improve the understanding of human activities and societal processes in settlements and their hinterlands, through the integration of global information layers and through modelling, with the final aim to disseminate information to a community of users and decision makers at all levels, also through the development of human settlement indicators.
These global initiatives provide consistent, comparable data across countries and regions, enabling international organizations to track urbanization trends, monitor progress toward development goals, and identify areas requiring intervention or support.
Best Practices for Urban Growth Mapping
Successful implementation of satellite-based urban growth mapping requires attention to methodological rigor, data quality, and appropriate application of results. Following established best practices helps ensure that analysis produces reliable, actionable insights.
Data Selection and Preprocessing
Selecting appropriate satellite imagery requires considering the specific objectives of the analysis, the scale of features being mapped, the required temporal frequency, and budget constraints. Free and open data sources should be evaluated first, with commercial high-resolution imagery acquired only when necessary for the specific application.
Proper preprocessing of satellite imagery is essential for accurate analysis. This includes geometric correction to ensure images align properly with maps and other data sources, atmospheric correction to remove the effects of haze and atmospheric scattering, and radiometric calibration to enable comparison between images from different dates or sensors.
Validation and Accuracy Assessment
All satellite-derived maps and analyses should include rigorous accuracy assessment. This typically involves comparing classified images or detected changes against reference data from field surveys, high-resolution imagery, or other authoritative sources. Accuracy metrics should be clearly reported, including overall accuracy, user’s accuracy, producer’s accuracy, and kappa statistics where appropriate.
Understanding the limitations and potential errors in satellite-derived products is crucial for appropriate application. Maps should include metadata documenting the data sources, methods, accuracy assessment results, and appropriate uses of the products.
Stakeholder Engagement
Effective urban growth mapping involves collaboration between remote sensing specialists, urban planners, policymakers, and community stakeholders. Technical experts must communicate results in accessible ways that non-specialists can understand and use. Planners and policymakers should be involved early in the process to ensure that analysis addresses their specific needs and questions.
Community engagement helps validate results, provides local knowledge that improves interpretation, and builds support for planning decisions based on satellite-derived information. Participatory mapping approaches that combine satellite imagery with local knowledge can be particularly effective.
Resources and Tools for Urban Growth Mapping
Numerous resources and tools are available to support satellite-based urban growth mapping, ranging from free and open-source options to commercial platforms offering advanced capabilities.
Free Satellite Data Sources
The Landsat program, jointly operated by NASA and the U.S. Geological Survey, provides the longest continuous record of Earth observation data, with imagery dating back to 1972. This historical archive enables analysis of urban growth over decades. Landsat imagery is freely available with moderate spatial resolution (30 meters for most bands) and 16-day revisit frequency.
The European Space Agency’s Copernicus program provides Sentinel satellite data free of charge. Sentinel-2 offers 10-meter resolution multispectral imagery with 5-day revisit frequency, making it excellent for monitoring urban areas. Sentinel-1 provides radar imagery that can see through clouds, valuable for tropical regions.
NASA’s Earth Observing System includes multiple satellites providing various types of data useful for urban monitoring. MODIS provides daily global coverage at moderate resolution, useful for large-scale monitoring. More specialized sensors provide data on temperature, vegetation, and other parameters relevant to urban environments.
Software and Analysis Platforms
Google Earth Engine provides a cloud-based platform for planetary-scale geospatial analysis, with access to petabytes of satellite imagery and the computing power to process it. The platform is free for research and educational use, making sophisticated analysis accessible to users worldwide.
QGIS is a free and open-source GIS platform with extensive capabilities for satellite image analysis. Numerous plugins extend its functionality for specific remote sensing applications. Commercial GIS platforms like ArcGIS offer additional capabilities and support, though at significant cost.
Specialized remote sensing software packages like ENVI, ERDAS IMAGINE, and eCognition provide advanced tools for image classification, change detection, and feature extraction. Open-source alternatives like SNAP (Sentinel Application Platform) and Orfeo Toolbox offer many similar capabilities without licensing costs.
Training and Capacity Building
Numerous online courses, tutorials, and training materials are available for learning satellite image analysis and GIS. Organizations like NASA, ESA, and the World Bank offer free training resources. Universities worldwide offer courses and degree programs in remote sensing and geospatial analysis.
Professional organizations like the American Society for Photogrammetry and Remote Sensing (ASPRS) and the International Society for Photogrammetry and Remote Sensing (ISPRS) provide networking opportunities, conferences, and publications that support professional development in the field.
The Future of Urban Growth Mapping
As satellite technology continues to advance and urban populations continue to grow, the importance of satellite-based urban growth mapping will only increase. As sensors improve and more satellites enter orbit, the accuracy, frequency, and value of this data will only continue to grow.
The convergence of satellite imagery with artificial intelligence, big data analytics, and other emerging technologies promises even more powerful capabilities for understanding and managing urban growth. Real-time monitoring, predictive modeling, and automated analysis will become increasingly sophisticated and accessible.
Perhaps most importantly, satellite-based urban growth mapping is becoming more democratic and participatory. What was once limited to governments is now accessible to researchers, journalists, and developers around the globe. This democratization of access to urban monitoring capabilities empowers communities to understand and advocate for their own development needs.
The challenges facing rapidly urbanizing regions—providing adequate housing, infrastructure, and services while protecting the environment and promoting equity—require the best possible information for decision-making. Satellite imagery provides an objective, consistent, and comprehensive view of urban growth that is essential for addressing these challenges effectively.
For urban planners, policymakers, researchers, and community advocates, understanding how to access and apply satellite-based urban growth mapping represents an increasingly essential skill. The tools and data are available; the challenge lies in building the capacity to use them effectively and ensuring that the insights they provide translate into better outcomes for the billions of people living in cities worldwide.
As we look to the future, the integration of satellite imagery with other data sources, the application of artificial intelligence to extract insights, and the engagement of diverse stakeholders in interpreting and applying results will shape how cities grow and evolve. The technology provides unprecedented capabilities for understanding urban dynamics; realizing the full potential of these capabilities requires commitment to rigorous analysis, inclusive planning processes, and evidence-based decision-making.
For those interested in learning more about satellite imagery applications in urban planning, the World Bank’s Urban Development resources provide extensive information and case studies. The Google Earth Engine platform offers powerful tools for satellite image analysis. The USGS Landsat program provides free access to decades of satellite imagery. The European Space Agency’s Copernicus program offers additional free satellite data sources. Finally, the Global Human Settlement Layer provides comprehensive global datasets on human settlements derived from satellite imagery.