Automated global delineation of human settlements from 40 years of Landsat satellite data archives

This paper presents the analysis of Earth Observation data records collected between 1975 and 2014 for assessing the extent and temporal evolution of the built-up surface in the frame of the Global Human Settlement Layer project.The scale of the information produced by the study enables the assessment of the whole continuum of human settlements from rural hamlets to megacities.The study applies enhanced processing methods as compared to the first production of the GHSL baseline data.The major improvements include the use of a more refined learning set on built-up areas derived from Sentinel-1 data which allowed testing the added-value of incremental learning in big data analytics.Herein,the new features of the GHSL built-up grids and the methods are described and compared with the previous ones using a reference set of building footprints for 277 areas of interest.The results show a gradual improvement in the accuracy measures with a gain of 3.6% in the balanced accuracy,between the first production of the GHSL baseline and the latest GHSL multitemporal built-up grids.A validation of the multitemporal component is also conducted at the global scale establishing the reliability of the built-up layer across time.

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.

The Generalised Settlement Area:mapping the Earth surface in the vicinity of built-up areas

Geo-information on settlements from Earth Observation offers a base for objective and scalable monitoring of the evolution of cities and settlements,including their location,extent and other attributes.In this work,we deploy the best available global knowledge on the presence of human settlements and built-up structures derived from Earth Observation to advance the understanding of the human presence on Earth.We start from a concept of Generalised Settlement Area to identify the Earth surface within which any built-up structure is present.We further characterise the resulted map by using an agreement map among the state of the art of remote sensing products mapping built-up areas or other strictly related semantic abstractions as urban areas or artificial surfaces.The agreement map is formed by a grid of 1 km2,where each cell is classified according to the number of EO-derived products reporting any positive occurrence of the abstractions related to the presence of built-up structures.The paper describes the characteristics of the Generalised Settlement Area,the differences in the agreement map across geographic regions of the world,and outlines the implications for potential users of the EO-derived products used in this study.