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

ABSTRACT 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.

[1]  C. Woodcock,et al.  Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4–7, 8, and Sentinel 2 images , 2015 .

[2]  Frederick E. Petry,et al.  Principles and Applications , 1997 .

[3]  Martino Pesaresi,et al.  Estimation of Land Use Efficiency from the Global Human Settlement Layer (GHSL) , 2018 .

[4]  Catherine Linard,et al.  Modelling spatial patterns of urban growth in Africa. , 2013, Applied geography.

[5]  Pierre Soille,et al.  A versatile data-intensive computing platform for information retrieval from big geospatial data , 2018, Future Gener. Comput. Syst..

[6]  J. E. Dobson,et al.  LandScan: Locating People is What Matters , 2002 .

[7]  M. Friedl,et al.  A new map of global urban extent from MODIS satellite data , 2009 .

[8]  Martino Pesaresi,et al.  Comparison of built‐up area maps produced within the global human settlement framework , 2018, Trans. GIS.

[9]  Catherine Linard,et al.  High-resolution gridded population datasets for Latin America and the Caribbean in 2010, 2015, and 2020 , 2015, Scientific Data.

[10]  G. Chander,et al.  Assessment of the NASA–USGS Global Land Survey (GLS) datasets , 2013 .

[11]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[12]  Martino Pesaresi,et al.  Principles and Applications of the Global Human Settlement Layer as Baseline for the Land Use Efficiency Indicator - SDG 11.3.1 , 2018, ISPRS Int. J. Geo Inf..

[13]  Hankui K. Zhang,et al.  Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data , 2013 .

[14]  Soille Pierre,et al.  A Global Mosaic from Copernicus Sentinel-1 Data , 2017 .

[15]  Catherine Doldirina,et al.  Open Data and Earth Observations The Case of Opening Up Access to and Use of Earth Observation Data Through the Global Earth Observation System of Systems , 2015 .

[16]  Pesaresi Martino,et al.  Benchmarking of the Symbolic Machine Learning classifier with state of the art image classification methods - application to remote sensing imagery , 2015 .

[17]  Soille Pierre,et al.  MASS PROCESSING OF SENTINEL-1 AND LANDSAT DATA FOR MAPPING HUMAN SETTLEMENTS AT GLOBAL LEVEL , 2017 .

[18]  T. Esch,et al.  Breaking new ground in mapping human settlements from space – The Global Urban Footprint , 2017, 1706.04862.

[19]  Pesaresi Martino,et al.  Atlas of the Human Planet 2018 , 2018 .

[20]  Pesaresi Martino,et al.  Development of new open and free multi-temporal global population grids at 250 m resolution , 2016 .

[21]  J. E. Dobson,et al.  LandScan: A Global Population Database for Estimating Populations at Risk , 2000 .

[22]  M. Pesaresi,et al.  GHS built-up grid, derived from Sentinel-1 (2016), R2018A , 2018 .

[23]  J. Pekel,et al.  High-resolution mapping of global surface water and its long-term changes , 2016, Nature.

[24]  A. Thomson,et al.  A global map of urban extent from nightlights , 2015 .

[25]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[26]  G. Lemoine,et al.  Enhanced automatic detection of human settlements using Sentinel-1 interferometric coherence , 2018 .

[27]  Huadong Guo,et al.  A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[28]  Julea Andreea Maria,et al.  Operating procedure for the production of the Global Human Settlement Layer from Landsat data of the epochs 1975, 1990, 2000, and 2014 , 2016 .

[29]  L. Lin,et al.  A concordance correlation coefficient to evaluate reproducibility. , 1989, Biometrics.

[30]  Sérgio Freire,et al.  Introducing mapping standards in the quality assessment of buildings extracted from very high resolution satellite imagery , 2014 .

[31]  Jin Chen,et al.  Global land cover mapping at 30 m resolution: A POK-based operational approach , 2015 .

[32]  Martino Pesaresi,et al.  A New Method for Earth Observation Data Analytics Based on Symbolic Machine Learning , 2016, Remote. Sens..

[33]  K. Thomas,et al.  Atlas of the Human Planet - Mapping Human Presence on Earth with the Global Human Settlement Layer , 2016 .

[34]  Carsten Brockmann,et al.  Consistent Global Land Cover Maps For Climate Modelling Communities: Current Achievements Of The ESA' Land Cover CCI , 2013 .

[35]  Martino Pesaresi,et al.  A Robust Built-Up Area Presence Index by Anisotropic Rotation-Invariant Textural Measure , 2008, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[36]  Kirk H. Stone.  The Development of A Focus for the Geography of Settlement , 1965 .

[37]  Sérgio Freire,et al.  GHS built-up grid, derived from Landsat, multitemporal (1975, 1990, 2000, 2014) , 2015 .

[38]  L. Dijkstra,et al.  Big earth data analytics on Sentinel-1 and Landsat imagery in support to global human settlements mapping , 2017 .

[39]  Sérgio Freire,et al.  Unveiling 25 Years of Planetary Urbanization with Remote Sensing: Perspectives from the Global Human Settlement Layer , 2018, Remote. Sens..

[40]  Joachim M. Buhmann,et al.  The Balanced Accuracy and Its Posterior Distribution , 2010, 2010 20th International Conference on Pattern Recognition.

[41]  Siragusa Alice,et al.  Atlas of the Human Planet 2017: Global Exposure to Natural Hazards , 2017 .

[42]  Xiaoping Liu,et al.  High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine Platform , 2018 .

[43]  F. H. Newell,et al.  United States Geological Survey , 1900, Nature.