Urban vegetation classification: Benefits of multitemporal RapidEye satellite data

Global climate change and sustained urban growth have increased the necessity of assessing the role that urban vegetation plays in urban dwellers' lives, as well as in urban ecosystem services. Urban environmental studies, however, still lack methods to characterize urban vegetation with adequate detail and across large areas. To remedy this gap, we apply a Support-Vector-Machine approach to classify eight frequent tree genera in the capital city of Berlin, Germany. We investigate different spectral and temporal band combinations of five RapidEye images acquired during the 2009 phenological season, and use ancillary surface and terrain models for orthorectification and improved tree masking. Results show that intra-annual time-series of RapidEye data can be used for high-precision tree genera classification in an urban environment. Differences within RapidEye time-series correlate well with empirical phenological studies of different tree genera, and RapidEye's red-edge band supports class separability. Further assessment is needed on the individual tree level and mixed stands regarding the quality of mapping urban individual trees, as our sampling approach mainly focused on larger stands with only a single tree genus. Urban applications will benefit from multitemporal RapidEye data, which offers area-wide monitoring and allows in-depth vegetation analysis to augment existing assessments. Such information is indispensable for assessing differences in urban ecosystem services related to carbon storage, cooling or air filtering, all of which differ between tree species. Therefore, the importance of in-depth analyses of urban vegetation cannot be underestimated in today's context of climate change.

[1]  R. Hill,et al.  Mapping tree species in temperate deciduous woodland using time‐series multi‐spectral data , 2010 .

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  F. Siegert,et al.  Assessment of grassland use intensity by remote sensing to support conservation schemes , 2012 .

[4]  Eric C. Turnblom,et al.  Tree Species Detection Accuracies Using Discrete Point Lidar and Airborne Waveform Lidar , 2012, Remote. Sens..

[5]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[6]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[7]  Mark D. Schwartz,et al.  Surface phenology and satellite sensor-derived onset of greenness: an initial comparison , 1999 .

[8]  Jan‐Åke Nilsson,et al.  Leafing phenology and timing of egg laying in great tits Parus major and blue tits P-caeruleus , 2006 .

[9]  Liang Liang,et al.  Validating satellite phenology through intensive ground observation and landscape scaling in a mixed seasonal forest , 2011 .

[10]  Baoxin Hu,et al.  Individual Urban Tree Species Classification Using Very High Spatial Resolution Airborne Multi-Spectral Imagery Using Longitudinal Profiles , 2012, Remote. Sens..

[11]  Barbara Koch,et al.  Airborne laser data for stand delineation and information extraction , 2009 .

[12]  A. Gitelson,et al.  Quantitative estimation of chlorophyll-a using reflectance spectra : experiments with autumn chestnut and maple leaves , 1994 .

[13]  Taskin Kavzoglu,et al.  A kernel functions analysis for support vector machines for land cover classification , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[14]  Qihao Weng,et al.  Remote Sensing Sensors and Applications in Environmental Resources Mapping and Modelling , 2007, Sensors.

[15]  Geoffrey J. Hay,et al.  Development of a pit filling algorithm for LiDAR canopy height models , 2009, Comput. Geosci..

[16]  W. Wagner,et al.  3D vegetation mapping using small‐footprint full‐waveform airborne laser scanners , 2008 .

[17]  P. Bolund,et al.  Ecosystem services in urban areas , 1999 .

[18]  Helmi Zulhaidi Mohd Shafri,et al.  yperspectral discrimination of tree species with different classifications using ingle-and multiple-endmember , 2013 .

[19]  M. Lefsky,et al.  Urban forest biomass estimates: is it important to use allometric relationships developed specifically for urban trees? , 2009, Urban Ecosystems.

[20]  A. Troy,et al.  Urban ecological systems: scientific foundations and a decade of progress. , 2011, Journal of environmental management.

[21]  Patrick Hostert,et al.  Simplifying Support Vector Machines for classification of hyperspectral imagery and selection of relevant features , 2010, 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[22]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[23]  Kevin J. Gaston,et al.  Mapping an urban ecosystem service: quantifying above‐ground carbon storage at a city‐wide scale , 2011 .

[24]  R. Pu,et al.  Segmented canonical discriminant analysis of in situ hyperspectral data for identifying 13 urban tree species , 2011 .

[25]  C. N. Hewitt,et al.  Quantifying the effect of urban tree planting on concentrations and depositions of PM10 in two UK conurbations , 2007 .

[26]  L. Bruzzone,et al.  Tree species classification in the Southern Alps based on the fusion of very high geometrical resolution multispectral/hyperspectral images and LiDAR data , 2012 .

[27]  J. Hyyppä,et al.  Tree species classification using airborne LiDAR - effects of stand and tree parameters, downsizing of training set, intensity normalization, and sensor type , 2010 .

[28]  A. Arnfield.  Two decades of urban climate research: a review of turbulence, exchanges of energy and water, and the urban heat island , 2003 .

[29]  F. Kraas,et al.  Megacities and global change: key priorities , 2007 .

[30]  T. Noland,et al.  Classification of tree species based on structural features derived from high density LiDAR data , 2013 .

[31]  B. Kleinschmit,et al.  Testing the red edge channel for improving land-use classifications based on high-resolution multi-spectral satellite data , 2012 .

[32]  Åsa Persson,et al.  Species identification of individual trees by combining high resolution LiDAR data with multi‐spectral images , 2008 .

[33]  Jon Atli Benediktsson,et al.  Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Francesco Pirotti,et al.  Analysis of full-waveform LiDAR data for forestry applications: a review of investigations and methods , 2011 .

[35]  W. Cohen,et al.  The Role of Remote Sensing in LTER Projects , 2010 .

[36]  P. Curran,et al.  A new technique for interpolating the reflectance red edge position , 1998 .

[37]  Tobia Lakes,et al.  The urban environmental indicator “Biotope Area Ratio”—An enhanced approach to assess and manage the urban ecosystem services using high resolution remote-sensing , 2012 .

[38]  Alexandre Carleer,et al.  Exploitation of Very High Resolution Satellite Data for Tree Species Identification , 2004 .

[39]  Leaf duration and the sequence of leaf development and abscission in northeastern urban hardwood trees , 1986 .

[40]  James Barber,et al.  Red edge measurements for remotely sensing plant chlorophyll content , 1983 .

[41]  J. Hyyppä,et al.  Review of methods of small‐footprint airborne laser scanning for extracting forest inventory data in boreal forests , 2008 .

[42]  Alexander Marx.  Detection and Classification of Bark Beetle Infestation in Pure Norway Spruce Stands with Multi-temporal RapidEye Imagery and Data Mining Techniques , 2010 .

[43]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[44]  Xiaoma Li,et al.  Carbon storage and sequestration by urban forests in Shenyang, China , 2012 .

[45]  Alan A. Ager,et al.  Broadband, red-edge information from satellites improves early stress detection in a New Mexico conifer woodland , 2011 .

[46]  Andrew D. Richardson,et al.  Phenology of a northern hardwood forest canopy , 2006 .

[47]  Qihao Weng,et al.  Remote sensing of urban environments: Special issue , 2012 .

[48]  Barbara Koch,et al.  Exploring full-waveform LiDAR parameters for tree species classification , 2011, Int. J. Appl. Earth Obs. Geoinformation.

[49]  Richard B Primack,et al.  Leaf-out phenology of temperate woody plants: from trees to ecosystems. , 2011, The New phytologist.

[50]  D. Sims,et al.  Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages , 2002 .

[51]  Limor Shashua-Bar,et al.  Quantitative evaluation of passive cooling of the UCL microclimate in hot regions in summer, case study: urban streets and courtyards with trees , 2004 .

[52]  Randolph H. Wynne,et al.  Estimating Biophysical Parameters of Individual Trees in an Urban Environment Using Small Footprint Discrete-Return Imaging Lidar , 2012, Remote. Sens..

[53]  Isabelle Chuine,et al.  Leaf phenology in 22 North American tree species during the 21st century , 2009 .

[54]  K. Omasa,et al.  3D lidar imaging for detecting and understanding plant responses and canopy structure. , 2006, Journal of experimental botany.

[55]  M. Lechowicz,et al.  Why Do Temperate Deciduous Trees Leaf Out at Different Times? Adaptation and Ecology of Forest Communities , 1984, The American Naturalist.

[56]  Patrick Hostert,et al.  Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines , 2007 .

[57]  T. Wesol̸owski,et al.  Timing of bud burst and tree-leaf development in a multispecies temperate forest , 2006 .

[58]  G. Percival,et al.  The impact of horse chestnut leaf miner (Cameraria ohridella Deschka and Dimic; HCLM) on vitality, growth and reproduction of Aesculus hippocastanum L. , 2011 .

[59]  S. Pickett,et al.  Integrative approaches to investigating human-natural systems: the Baltimore ecosystem study , 2006 .

[60]  D. Nowak,et al.  Carbon storage and sequestration by urban trees in the USA. , 2002, Environmental pollution.

[61]  Gregory A. Keoleian,et al.  Carbon stored in human settlements: the conterminous United States , 2010 .

[62]  A Primer Karen C. Seto.  Global Urban Issues , 2009 .

[63]  Mary Ann Fajvan,et al.  A Comparison of Multispectral and Multitemporal Information in High Spatial Resolution Imagery for Classification of Individual Tree Species in a Temperate Hardwood Forest , 2001 .

[64]  D. Laband,et al.  Energy savings from tree shade. , 2010 .

[65]  R. Pu,et al.  A comparative analysis of high spatial resolution IKONOS and WorldView-2 imagery for mapping urban tree species , 2012 .

[66]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[67]  Clement Atzberger,et al.  Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data , 2012, Remote. Sens..