Urban land cover thematic disaggregation, employing datasets from multiple sources and RandomForests modeling

Abstract Urban land cover mapping has lately attracted a vast amount of attention as it closely relates to a broad scope of scientific and management applications. Late methodological and technological advancements facilitate the development of datasets with improved accuracy. However, thematic resolution of urban land cover has received much less attention so far, a fact that hampers the produced datasets utility. This paper seeks to provide insights towards the improvement of thematic resolution of urban land cover classification. We integrate existing, readily available and with acceptable accuracies datasets from multiple sources, with remote sensing techniques. The study site is Greece and the urban land cover is classified nationwide into five classes, using the RandomForests algorithm. Results allowed us to quantify, for the first time with a good accuracy, the proportion that is occupied by each different urban land cover class. The total area covered by urban land cover is 2280 km 2 (1.76% of total terrestrial area), the dominant class is discontinuous dense urban fabric (50.71% of urban land cover) and the least occurring class is discontinuous very low density urban fabric (2.06% of urban land cover).

[1]  F. J. Gallego,et al.  A population density grid of the European Union , 2010 .

[2]  Gerald Mills,et al.  Cities as agents of global change , 2007 .

[3]  V. Rodriguez-Galiano,et al.  Land cover change analysis of a Mediterranean area in Spain using different sources of data: Multi-seasonal Landsat images, land surface temperature, digital terrain models and texture , 2012 .

[4]  Dimitrios Gounaridis,et al.  Land cover of Greece, 2010: a semi-automated classification using random forests , 2016 .

[5]  C. Fanelli,et al.  European Environment Agency. The european Environment. State and Outlook 2005 , 2006 .

[6]  George N. Zaimes,et al.  Quantifying spatio-temporal patterns of forest fragmentation in Hymettus Mountain, Greece , 2014, Comput. Environ. Urban Syst..

[7]  F. Ramm,et al.  OpenStreetMap: Using and Enhancing the Free Map of the World , 2010 .

[8]  V. Mesev.  The use of census data in urban image classification , 1998 .

[9]  P. Sutton,et al.  Paving the planet: impervious surface as proxy measure of the human ecological footprint , 2009 .

[10]  Hanqiu Xu.  Extraction of Urban Built-up Land Features from Landsat Imagery Using a Thematicoriented Index Combination Technique , 2007 .

[11]  Jianguo Wu,et al.  Effects of thematic resolution on landscape pattern analysis , 2007, Landscape Ecology.

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  T. M. Conway,et al.  The impact of class resolution in land use change models , 2009, Comput. Environ. Urban Syst..

[14]  Didier Tanré,et al.  Second Simulation of the Satellite Signal in the Solar Spectrum, 6S: an overview , 1997, IEEE Trans. Geosci. Remote. Sens..

[15]  Volker C. Radeloff,et al.  Road Density and Landscape Pattern in Relation to Housing Density, and Ownership, Land Cover, and Soils , 2005, Landscape Ecology.

[16]  Robert Costanza,et al.  Ecosystem Appropriation by Cities , 1996 .

[17]  Joseph Tzanopoulos,et al.  Historical analysis of landscape change using remote sensing techniques: An explanatory tool for agricultural transformation in Greek rural areas , 2008 .

[18]  P. Teillet,et al.  On the Slope-Aspect Correction of Multispectral Scanner Data , 1982 .

[19]  Atsuyuki Okabe,et al.  A kernel density estimation method for networks, its computational method and a GIS‐based tool , 2009, Int. J. Geogr. Inf. Sci..

[20]  Jonathan Cheung-Wai Chan,et al.  Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery , 2008 .

[21]  Chandra P. Giri,et al.  Next generation of global land cover characterization, mapping, and monitoring , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[22]  Hankui K. Zhang,et al.  Meta-discoveries from a synthesis of satellite-based land-cover mapping research , 2014 .

[23]  J McGlade,et al.  The European Environment: State and Outlook 2005 , 2005 .

[24]  R. DeFries,et al.  Deforestation driven by urban population growth and agricultural trade in the twenty-first century , 2010 .

[25]  M. Friedl,et al.  Mapping global urban areas using MODIS 500-m data: new methods and datasets based on 'urban ecoregions'. , 2010 .

[26]  D. Bailey,et al.  Thematic resolution matters: Indicators of landscape pattern for European agro-ecosystems , 2007 .

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

[28]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[29]  P. Atkinson,et al.  Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture , 2012 .

[30]  R. Nemani,et al.  Global Distribution and Density of Constructed Impervious Surfaces , 2007, Sensors.

[31]  D. Civco,et al.  Mapping urban areas on a global scale: which of the eight maps now available is more accurate? , 2009 .

[32]  Robert Gilmore Pontius,et al.  Effect of Category Aggregation on Map Comparison , 2004, GIScience.

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

[34]  Jamal Jokar Arsanjani,et al.  The emergence and evolution of OpenStreetMap: a cellular automata approach , 2015, Int. J. Digit. Earth.

[35]  N. Grimm,et al.  Global Change and the Ecology of Cities , 2008, Science.

[36]  A. S. Belward,et al.  Who launched what, when and why; trends in global land-cover observation capacity from civilian earth observation satellites , 2015 .

[37]  A. Gibon,et al.  Agricultural abandonment in mountain areas of Europe: Environmental consequences and policy response , 2000 .

[38]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[39]  A. Andreades.  The Greek Census , 1909 .

[40]  D. Lu,et al.  Urban classification using full spectral information of landsat ETM+ imagery in Marion County, Indiana , 2005 .

[41]  Apostolos G. Papadopoulos,et al.  Migrants in rural Greece , 2003 .

[42]  Dimitris Skuras,et al.  Agriculture and the Greek Rural Environment , 1997 .

[43]  I. Wayan Nuarsa,et al.  Enhanced Built-Up and Bareness Index (EBBI) for Mapping Built-Up and Bare Land in an Urban Area , 2012, Remote. Sens..

[44]  Russell G. Congalton,et al.  Global Land Cover Mapping: A Review and Uncertainty Analysis , 2014, Remote. Sens..

[45]  Changshan Wu,et al.  Normalized spectral mixture analysis for monitoring urban composition using ETM+ imagery , 2004 .

[46]  Jay Gao,et al.  Use of normalized difference built-up index in automatically mapping urban areas from TM imagery , 2003 .

[47]  Rajiv Ranjan,et al.  Semantic analysis and retrieval of spatial data based on the uncertain ontology model in Digital Earth , 2015, Int. J. Digit. Earth.

[48]  D. Lu,et al.  Use of impervious surface in urban land-use classification , 2006 .

[49]  K. McGarigal,et al.  Fine-scale remotely-sensed cover mapping of coastal dune and salt marsh ecosystems at Cape Cod National Seashore using Random Forests , 2012 .