Search

The Population To Grid tool (POP2G) –version 1.0- is an information system developed in the framework of the Global Human Settlement Layer (GHSL) to produce geospatial grids of population counts at different spatial resolutions. The POP2G v1.0 is a flexible tool to produce geospatial population grids in GeoTIFF format from census data. The tool operationalises the workflow developed for the production of the Global Human Settlement Layer Population Grid layers (GHS-POP). The POP2G v1.0 tool allows the creation of population grids at 50 m, 250 m, and 1 km spatial resolutions, handling census data stored as point or polygon vector data (in latter case requires additional covariate as input for dasymetric disaggregation). The principal purpose of the tool is the production of the population grid used as input for the Degree of Urbanisation Grid (DUG) also produced in the GHSL framework. However the potential uses of the tool and population grids go far beyond this main application. The tool is a capacity enhancement asset in the framework of the multi-stakeholder effort to develop a people-based harmonised definition of cities and settlements that helps the assessment of the feasibility of applying a global definition of cities/urban areas in support of global monitoring of SDGs and the New Urban Agenda urban targets. The POP2G, as all GHSL tools, is issued with an end-user licence agreement, included in the download package, JRC.E.1-Disaster Risk Management

The Degree of Urbanisation Grid (GHS-DUG) Tool (– version 4) is an information system developed in the framework of the Global Human Settlement Layer (GHSL) to produce geospatial grids to map settlement classes and extract related statistics. The settlement classes are derived from the “Degree of Urbanisation” method and ported to the GHSL environment through the GHSL Settlement Mode (GHSL SMOD). The GHS-DUG 4 is designed as a scalable tool allowing the application of the GHSL Settlement Model to the input data available to the user or to data made available in the GHSL Data Package 2019. This document contains the description of the GHS-DUG Tool use, the rationale of the differentiation between settlement classes and the comprehensive description of the outputs. The tool is a capacity enhancement asset in the framework of the multi-stakeholder effort for the uptake of the Degree of Urbanisation, the people-based harmonised definition of cities and settlements recommended by the 51st Session of the United Nations Statistical Commission as the method to delineate cities and rural areas for international statistical comparison. The GHS-DUG, as all GHSL Tools, is issued with an end-user licence agreement, included in the download package., JRC.E.1-Disaster Risk Management

The Degree of Urbanisation Grid (DUG) Tool (– version 3.1) is an information system developed in the framework of the Global Human Settlement Layer (GHSL) to produce geospatial grids to map settlement classes and extract related statistics. The settlement classes are derived from the “Degree of Urbanisation” method and ported to the GHSL environment through the GHSL Settlement Mode (GHSL SMOD). The DUG 3.1 is designed as a scalable tool allowing the application of the GHSL Settlement Model to the input data available to the user or to data made available in the GHSL Data Package 2019. This document contains the description of the DUG Tool use, the rationale of the differentiation between settlement classes and the comprehensive description of the outputs. The tool is a capacity enhancement asset in the framework of the multi-stakeholder effort to develop a people-based harmonised definition of cities and settlements that helps the assessment of the feasibility of applying a global definition of cities/urban areas in support of global monitoring of SDGs and the New Urban Agenda urban targets. The DUG, as all GHSL Tools, is issued with an end-user licence agreement, included in the download package., JRC.E.1-Disaster Risk Management

The Degree of Urbanisation Territorial Units Classifier (GHS-DU-TUC) Tool (– version 1) is an information system developed in the framework of the Global Human Settlement Layer (GHSL) to produce the classification of territorial units based on the Degree of Urbanisation and extract related statistics. The tool classifies territorial units by Degree of Urbanisation at Level 1 (3 classes) and Level 2 (7 classes) based on population majority by settlement classes derived from the “Degree of Urbanisation” method and ported to the GHSL environment through the GHSL Settlement Model (GHSL SMOD). The GHS-DU-TUC 1 is designed as an operational tool to perform the second step required to apply the Degree of Urbanisation released as standalone tool and as ArcGIS Toolbox. Once the first step produces the settlement classification grid (i.e. with the GHS-DUG Tool), the user runs the GHS-DU-TUC that requires this settlement classification grid, the population grid used to produce the settlement classification grid (i.e. produced with the GHS-POP2G Tool) and a geometry of territorial units to be classified by Degree of Urbanisation. This tool is conceptualised to be deployed after the application of the GHSL tools GHS-POP2G and GHS-DUG but it accepts in input population grids produced by means of any other procedure respecting the described constrains. This document contains the description of the GHS-DU-TUC Tool use, the rationale for the second step to apply the Degree of Urbanisation (the classification of territorial units) and the comprehensive description of the outputs. The tool is a capacity enhancement asset in the framework of the multi-stakeholder effort for the uptake of the Degree of Urbanisation, the people-based harmonised definition of cities and settlements recommended by the 51st Session of the United Nations Statistical Commission as the method to delineate cities and rural areas for international statistical comparison. The GHS-DU-TUC, as all GHSL Tools, is issued with an end-user licence agreement, included in the download package., JRC.E.1-Disaster Risk Management

The Population To Grid tool (GHS-POP2G) –version 2- is an information system developed in the framework of the Global Human Settlement Layer (GHSL) to produce geospatial grids of population counts at different spatial resolutions. The GHS-POP2G v2 is a flexible tool to produce geospatial population grids in GeoTIFF format from census data. The tool operationalises the workflow developed for the production of the Global Human Settlement Layer Population Grid layers (GHS-POP). The GHS-POP2G v2 tool allows the creation of population grids at 50 m, 100 m, 250 m, and 1 km spatial resolutions, handling census data stored as point or polygon vector data (in latter case requires additional covariate as input for dasymetric disaggregation). The principal purpose of the tool is the production of the population grid used as input for the Degree of Urbanisation Grid (GHS-DUG) also produced in the GHSL framework. However the potential uses of the tool and population grids go far beyond this main application. The tool is a capacity enhancement asset in the framework of the multi-stakeholder effort to develop a people-based harmonised definition of cities and settlements that helps the assessment of the feasibility of applying a global definition of cities/urban areas in support of global monitoring of SDGs and the New Urban Agenda urban targets. The GHS-POP2G, as all GHSL tools, is issued with an end-user licence agreement, included in the download package., JRC.E.1-Disaster Risk Management

The presence of green spaces within city centres has been recognized as a valuable component of the city landscape. Vegetation provides a variety of benefits including energy saving, improved air q...

The Global Human Settlement Layer (GHSL) produces new global spatial information, evidence-based analytics and knowledge describing the human presence on the planet Earth. The GHSL operates in a fully open and free data and methods access policy, building the knowledge supporting the definition, the public discussion and the implementation of European policies and the international frameworks as the 2030 Development Agenda and the related thematic agreements. The GHSL supports the GEO Human Planet Initiative (HPI) that is committed to developing a new generation of measurements and information products providing new scientific evidence and a comprehensive understanding of the human presence on the planet and that can support global policy processes with agreed, actionable and goal-driven metrics. The Human Planet Initiative relies on a core set of partners committed in coordinating the production of the global settlement spatial baseline data. One of the core partners is the European Commission, Directorate General Joint Research Centre, Global Human Settlement Layer project. The Global Human Settlement Layer project produces global spatial information, evidence-based analytics, and knowledge describing the human presence in the planet. This document describes the public release of the GHSL Data Package 2019 (GHS P2019)., JRC.E.1-Disaster Risk Management

The Global Human Settlement Layer Urban Centres Database (GHS-UCDB) is the most complete database on cities to date, publicly released as an open and free dataset - GHS STAT UCDB2015MT GLOBE R2019A V1.0. The database represents the global status on Urban Centres in 2015 by offering cities location, their extent (surface, shape), and describing each city with a set of geographical, socio-economic and environmental attributes, many of them going back 25 or even 40 years in time. Urban Centres are defined in a consistent way across geographical locations and over time, applying the “Global Definition of Cities and Settlements” developed by the European Union to the Global Human Settlement Layer Built-up (GHS-BUILT) areas and Population (GHS-POP) grids. This report contains the description of the dimensions and the derived attributes that characterise the Urban Centres in the database. The document includes notes about methodology and sources. The GHS-UCDB contains information for more than 10,000 Urban Centres and it is the baseline data of the analytical results presented in the Atlas of the Human Planet 2018., JRC.E.1-Disaster Risk Management

The Atlas of the Human Planet 2019 presents key human settlements and urbanisation statistics for 239 countries based on the progress made towards the development of a people-based global harmonised definition of cities and rural areas. Figures and statistics presented in the Atlas 2019 are the result of massive automatic big data processing carried out at the European Commission Directorate General Joint Research Centre in the framework of the Global Human Settlement Layer (GHSL) combining satellite imagery and census information to map settlements, understand their characteristics, and report about their changes over 40 years’ time (1975 – 2015). The Atlas explains the fundamentals of the GHSL, and the service it provides to upscale to the globe the Degree of Urbanisation method (currently adopted as European Union Regulation). Based on the global application of the method the Atlas presents a global urbanisation brief, a commented series of highlights on global human settlement development trajectories, supported by 239 urbanisation briefs, which form the knowledge base for the next generation of urban and territorial policy, development and cooperation action, and global reporting on progress made towards meeting the Sustainable Development Goals and the 2030 Development Agenda as a whole., JRC.E.1-Disaster Risk Management

The combination of Earth Observation and population data produces new information that describes inequalities across the globe in an original, objective and spatially distinct way.The new information contributes to a better understanding of the spatial distribution of wealth and poverty around the globe.The approach has potential for the monitoring and detection of changes in spatial patterns of inequality., JRC.E.1-Disaster Risk Management

This document presents the contributions presented at the first internal workshop on Artificial Intelligence (AI), organized by the Joint Research Centre (JRC) of the European Commission. This workshop was held on 23rd May at the premises of the JRC in Ispra (Italy), with video-conference to all JRC's sites. The workshop aimed to gather JRC specialists on AI to share their experience, to identify opportunities for meeting the EC demands on AI, and explore synergies among different JRC's working groups on AI. The full-day session workshop was organized around three main topical strands entitled Policy support, New Initiatives and Technology Development. Contributions covered a wide range of areas, including applications of AI to Cybersecurity, Transport, Environment, Health and other specific issues. This report is structured according to those main topics of study. According to the JRC Director General Vladimír Šucha: "The workshop was very stimulating and interesting presenting a broad spectrum of activities and competencies across JRC. It gave a great opportunity to build a strong and hopefully useful position in the field of AI/ML". While the first part of the workshop was mainly informative, in the second part we collectively discussed about JRC priorities and the set-up of a Community of Practice (now available at https://webgate.ec.europa.eu/connected/groups/community-of-practice-ai-and-big-data) dealing with AI and Big Data. Finally, the preliminary results of the online survey were presented. All colleagues were excellent in communicating their scientific activity in a flash and efficient way., JRC.B.6-Digital Economy

Urban transformation is an emerging topic in recent years and its socio-economical and environmental impacts have become increasingly evident to scientists and policymakers. The ability to analyse and understand this process was limited by the lack of comprehensive datasets and formalised methodologies. The Global Human Settlement Layer (GHSL) suite accommodates this need by providing worldwide, multi-epoch information on human settlements. In particular, the GHSL suite includes three main layers that map built-up density (GHS-BUILT), population density (GHS-POP) and human settlements (GHS-SMOD). These grid-based layers are produced in a consistent and harmonised way for four epochs (1975-1990-2000-2015) allowing the comparison between different periods. In this technical report, we present a formalised methodology (workflow) to characterise and analyse the dynamics of settlements. This workflow proposes a taxonomy of all possible GHS-SMOD classification combinations between two epochs; it quantifies and analyses changes of built-up surface and population density in each taxonomical class. We show the workflow capability by using the region of New York (United States of America) as a case study. The presented workflow has a direct application to characterise urban dynamics using the GHSL. Such approach supports the assessment of urbanization processes, by monitoring urban expansion, contraction and rural-urban transitions, and by measuring sustainable urban development metrics. The application of this workflow allows taking into account, both and separately, the net and the gross change in built-up surface and population density within a urban settlement evolution. Moreover, the application of this workflow to the GHSL suite benefits of the full ranges of GHSL features (global coverage, data consistency and open and free data format)., JRC.E.1-Disaster Risk Management

The GEO Human Planet Initiative is committed to developing a new generation of measurements and information products that provide new scientific evidence and a comprehensive understanding of the human presence on the planet and that can support global policy processes with agreed, actionable and goal-driven metrics. The Human Planet Initiative relies on a core set of partners committed in coordinating the production of the global settlement spatial baseline data, and an enlarged community of partners developing experimental activities on using the new baseline data for derived post-2015 indicators. One of the core partners is the European Commission, Directorate General Joint Research Centre, Global Human Settlement Layer project. The Global Human Settlement Layer project produces global spatial information, evidence-based analytics, and knowledge describing the human presence in the planet. This document describes the Community pre-Release of the GHSL Data Package 2018 - GHS CR2018 - created for the members of the GEO Human Planet Initiative. The data in this data package have the purpose to gather feedbacks from the GEO Human Planet Initiative community, in preparation for the public release of these data. Disclaimer: the data included in the Community Pre-Release of the GHSL Data Package 2018 should be considered preliminary and not yet validated. It may differ substantially with the data that will be included in the public final Release 2018. The JRC data are provided "as is" and "as available" in conformity with the JRC Data Policy1 and the Commission Decision on reuse of Commission documents (2011/833/EU). Although the JRC guarantees its best effort in assuring quality when publishing these data, it provides them without any warranty of warranty of any kind, either express or implied, including, but not limited to, any implied warranty against infringement of third parties' property rights, or merchantability, integration, satisfactory quality and fitness for a particular purpose. The JRC has no obligation to provide technical support or remedies for the data. The JRC does not represent or warrant that the data will be error free or uninterrupted, or that all non-conformities can or will be corrected, or that any data are accurate or complete, or that they are of a satisfactory technical or scientific quality. The JRC or as the case may be the European Commission shall not be held liable for any direct or indirect, incidental, consequential or other damages, including but not limited to the loss of data, loss of profits, or any other financial loss arising from the use of the JRC data, or inability to use them, even if the JRC is notified of the possibility of such damages., JRC.E.1-Disaster Risk Management

Spatial inequalities across the globe are not easy to detect and satellite data have shown to be of use in this task. Earth Observation (EO) data combined with other information sources can provide complementary information to those derived from traditional methods. This research shows patterns of inequalities emerging by combining global night lights measured from Earth Observation, population density and built-up in 2015. The focus of the paper is to describe the spatial patterns that emerge by combing the three variables. This work focuses on processing EO data to derive information products, and in combining built-up- and population density with nighttime emission. The built-up surface was derived entirely from remote sensing archives using artificial intelligence and pattern recognition techniques. The built-up was combined with population census data to derive population density. Also the nighttime emission data were available from EO satellite sensors. The three layers are subsequently combined as three colour compositions based on the three primary colours (i.e. red green and blue) to display the “human settlement spatial pattern” maps. These GHSL nightlights provide insights in inequalities across the globe. Many patterns seem to be associated with countries income. Typically, high income countries are very well lit at night, low income countries are poorly lit at night. All larger cities of the world are lit at night, those in low-income countries are often less well lit than cites in high-income countries. There are also important differences in nightlights emission in conflict areas, or along borders of countries. This report provides a selected number of patterns that are described at the regional, national and local scale. However, in depth analysis would be required to assess more precisely that relation between wealth access to energy and countries GDP, for example. This work also addresses regional inequality in GHSL nightlights in Slovakia. The country was selected to address the deprivation of the Roma minority community. The work aims to relate the information from the GHSL nightlights with that collected from field survey and census information conducted at the national level. Socio-economic data available at subnational level was correlated with nightlight. The analysis shows that despite the potential of GHSL nightlights in identifying deprived areas, the measurement scale of satellite derived nightlights at 375 x 375 m and 750 x 750 m pixel size is too coarse to capture the inequalities of deprived communities that occur at finer scale. In addition, in the European context the gradient of inequality is not strong enough to produce strong evidence. Although there is a specific pattern of GHSL nightlights in settlements with high Roma presence, this cannot be used to identify such areas among the others. This work is part of the exploratory data analysis conducted within the GHSL team. The exploratory analysis will be followed by more quantitative assessments that will be available in future work., JRC.E.1-Disaster Risk Management

The Atlas of the Human Planet 2018 describes the Urban Centre Database, which was produced in the framework of the Global Human Settlement Layer (GHSL) project by applying a global definition of cities and settlements to the GHSL data. The Atlas presents the key findings of the analysis of geographic, environmental and socio-economic variables that were gathered from free and open sources for each urban centre in the world., JRC.E.1-Disaster Risk Management

People, planet, prosperity and peace are four priorities shared by Africa and Europe, and areas where opportunities for beneficial cooperation abound. Over the past three decades, the European Commission’s Joint Research Centre (JRC) has worked with many organisations and institutions across Africa. This report and its accompanying interactive online service ‘Africa StoryMaps’ present the key findings from this collaboration, and set out options the decision-making, research and education communities may consider. The report focuses on the African dimension of the partnership. It explores the opportunities and challenges arising from the fact that Africa has over twice the population of the European Union (EU), is the world’s most youthful continent, has an economy that is growing faster than that of the EU, is almost seven times larger geographically, yet is vulnerable to diverse internal and external stresses. Tell us what you think about this report. Please fill out and return our feedback form (PDF) at https://ec.europa.eu/jrc/en/file/document/africa-report-feedback-form., JRC.D.6-Knowledge for Sustainable Development and Food Security

This user guide accompanies the MASADA tool which is a public tool for the detection of built-up areas from remote sensing data. MASADA stands for Massive Spatial Automatic Data Analytics. It has been developed in the frame of the “Global Human Settlement Layer” (GHSL) project of the European Commission’s Joint Research Centre, with the overall objective to support the production of settlement layers at regional scale, by processing high and very high resolution satellite imagery. The tool builds on the Symbolic Machine Learning (SML) classifier; a supervised classification method of remotely sensed data which allows extracting built-up information using a coarse resolution settlement map or a land cover information for learning the classifier. The image classification workflow incorporates radiometric, textural and morphological features as inputs for information extraction. Though being originally developed for built-up areas extraction, the SML classifier is a multi-purpose classifier that can be used for general land cover mapping provided there is an appropriate training data set. The tool supports several types of multispectral optical imagery. It includes ready-to-use workflows for specific sensors, but at the same time, it allows the parametrization and customization of the workflow by the user. Currently it includes predefined workflows for SPOT-5, SPOT-6/7, RapidEye and CBERS-4, but it was also tested with various high and very high resolution1 sensors like GeoEye-1, WorldView-2/3, Pléiades and Quickbird., JRC.E.1-Disaster Risk Management

LUE tool stands for Land Use Efficiency tool and it is a tool developed by the Global Human Settlement Layer (GHSL) Team. This tool, developed in Python language, allows user calculating easily and quickly some indicators on the change of land in an area of interest. The tool is designed to be use with GHS Layers on Built-up area and population, but it can be easily adapted also to other input data. This guide provides instructions about installing and using the LUE tool in the open source software QGIS and provides suggestions for the output interpretation., JRC.E.1-Disaster Risk Management

This user guide accompanies the DUG tool which is a public tool for applying the “Degree of urbanisation” (DEGURBA) model at one kilometer grid. DUG stands for Degree of Urbanisation Grid. It has been developed in the frame of the “Global Human Settlement Layer” (GHSL) project of the European Commission’s Joint Research Centre, with the overall objective to support the DEGURBA activities. The tool builds on the GHS SMOD model that implements settlement model classifier at 1 km grid. The tool uses population and built-up grids as input data, and optionally a water mask. It has been developed and tested using GHS P2016 datasets ; however other grids can be used on user responsibility. This user guide is a comprehensive guide to all aspects of using the DUG tool. It includes instructions for the set-up of the software, the use of the tool and the manipulation of the data. It presents briefly the basic principles and background information on the methodology and its implementation. Some guidelines on the parametrization are also provided., JRC.E.1-Disaster Risk Management

AAXY stands for Associative Analysis between X and Y, it’s a special analytic method developed in the frame of the Global Human Settlement Layer (GHSL) project and it’s being used for extraction of information from satellite images. This software allows user to extract information (Evidence-based Normalized Differential Index or ENDI measure) from satellite data and it’s been used for the production of the GHSL products such as GHSL BUILT and GHSL POP in the different epochs 1975, 1990, 2000, and 2014. This guide provides instructions about installing and using the AAXY command line tool on a Windows computer., JRC.E.1-Disaster Risk Management

The JRC’s Global Human Settlement Layer (GHSL) and the derived population data were integrated with night-time satellite imagery to assess the humanitarian impact of the Syrian conflict. The results demonstrate that the methodology allows estimating in a timely and consistent manner the number of affected people during crisis. Estimates of affected people that match with the official figures including registered refugees and IDPs were obtained with this method. The approach has a potential in estimating in an objective and timely way the impacts of humanitarian crisis. Prospective studies can make use of the temporal and spatial advantages of open-access geospatial data (night-time satellite imagery and GHSL derived products) in the field of disaster risk management to investigate the role of social dynamics over space and time in the occurrences of disasters and provide evidence-based knowledge to support disaster risk reduction plans and actions., JRC.E.1-Disaster Risk Management

The Atlas of the Human Planet presents the key findings of the analysis of the Global Human Settlement Layer (GHSL). This data set reports about the growth of built-up and population in the last 40 years (1975-2015) at an unprecedented level of detail. The information supports the international frameworks of the Agenda 2030., JRC.E.1-Disaster Risk Management

This document describes the assessment of global terrain data and a procedure to combine terrain data with newly available human settlement data. The aim is to quantify settlements in low-lying coastal zones and in topographically rugged terrain. For terrain data we use the Shuttle Radar Topographic Mission Digital Elevation Model made available at 90m (3 arc sec), for settlement data we use the Global Human Settlement Layer (GHSL) data set released in 2016 composed of built-up area (GHS-BU), population (GHS-POP) and settlement model (GHS-SMOD) grids and available for 4 epochs, 1975, 1990, 2000 and 2015. We show that SRTM at 90m and GHSL can be combined in a meaningful way. However, we could not generate accuracy assessment on the resulting figures as both datasets do not come with accuracy assessment. In addition, as the data extend only up to 60degrees north, the analysis is not completely global even if it covers the large part of the populated land masses. Preliminary results show that it is possible to derive quantitative measures related to the increase of population in coastal zones, and in steep terrain that may be considered prone to natural hazards. Preliminary analysis indicates that the rate of population growth for the four epochs in the low-lying coastal areas is higher than the global population growth rate. In addition, we show that we are able to measure the spatial expansion of settlements over steep slopes especially in the large cities in developing countries (i.e. Lima), but also in coastal settlements of developed countries (e.g., Italy and France)., JRC.E.1-Disaster Risk Management

A new method for satellite data classification is presented. The method is based on symbolic machine learning (SML) techniques and is designed for working in complex and information-abundant environments, where it is important to assess relationships between different data layers in model-free and computational-effective modalities. In particular, the method is tailored for operating in earth observation data scenarios connoted by the following characteristics: i) they are made by a large number of data granules (scenes), ii) they are made by heterogeneous sensors and iii) they are mapping a large variety of different geographical areas in different data collection conditions. The volume, variety and partially unstructured nature of these scenarios can be associated with the characteristics of Big Data. The results of an experiment observing the behavior of the SML classifier by injecting increasing levels of noise in the training set are discussed. Spatial generalization, random thematic noise and spatial displacement noise are tested. Seven supervised classification algorithms have been considered for comparison: Maximum Likelihood, Logistic Regression, Linear Discriminant Analysis, Naive Bayes, Decision Tree, Random Forest and Support Vector Machine. According to the results of the experiment, the SML classifier performed very well providing outputs with comparable or better quality than the other classifiers. Furthermore, the better performances were released with a much less expensive computational cost. Consequently, the SML classifier was evaluated as the best available solution in the specific data scenario under consideration. Few applicative examples of the new SML classifier using Spot5, Sentinel1, and Sentinel2 data inputs are provided., JRC.G.2-Global security and crisis management

This report describes a pilot study that is carried out jointly by the European Commission’s Joint Research Centre (JRC) and the South African National Space Agency (SANSA). The pilot study aims at develop a robust methodology for the automated mapping of settlements, formal and informal, in the entire territory of South Africa. It relies on the methodology for automated settlement mapping, also known as Global Human Settlement Layer (GHSL), developed by the JRC and the high resolution satellite data holdings of SANSA. Amongst other uses it aims a supporting the National Department of Human Settlement (NDHS) in its implementation of the Upgrading Informal Settlements Programme (UISP) with the objective of eventually upgrading all informal settlements in the country. The pilot study focusses on the Gauteng area, the cities of Durban and Rustenburg as well as a rural area in the Limpopo province. Once stabilised the workflow will be extended to the full country to generate a multi-temporal wall-to wall data set of the settlements of South Africa., JRC.G.2-Global security and crisis management

In the context of disaster risk management, there is a need for detailed, updated and consistent data on the exposure of people and their settlements. Drawing from the latest generation of satellite imagery, a new approach allows to automatically produce, in an effective way, detailed geodatasets quantifying built-up areas and population distribution. This approach is multi-sensor, multi-scale, multi-use, and focuses on automatic retrieval of quantitative information from the imagery. In parallel with large-scale image processing, global reference datasets were developed which improve the representation of smaller settlements and low-density areas, compared to previously-available maps. These outputs are useful at any stage of the disaster management cycle, by improving the spatial assessment of exposure to hazards and thus contributing to advancing global risk and impact analyses. Coupled with sound decision-making, this ultimately contributes to disaster mitigation efforts., JRC.G.2-Global security and crisis management