Integration of urban growth modelling products with image-based urban change analysis

Urban change detection using remotely sensed data has been extensively studied. One current application of detection products is the formulation of calibration data for urban change prediction models. As multi-temporal scenes become available and urban growth prediction models increase in popularity and accuracy, it is natural to envisage a bi-directional relationship where, in addition to detection products assisting prediction models, the prediction information acts as ancillary input to enhance spectral-based change detection products. This closed feedback loop has the potential to significantly increase the accuracy of both detection and prediction efforts. Consequently, our objective is to evaluate the integration of prediction information with spectral data for urban change monitoring. A case study was carried out in the Denver, Colorado metropolitan area. Probabilities of urban change generated from two existing urban prediction models (based on decision trees and logistic regression) are combined as additional information content with a Landsat Thematic Mapper (TM) scene. Detailed assessments at the pixel and block scales are implemented to evaluate urban change classification accuracy using different input data and training sample sizes. Results show that in pixel-based assessments, the fusion of decision tree change probabilities and TM spectral bands with sufficient training samples leads to improvements. In terms of overall accuracies, the improvement is 2.0–2.4%, from 87.3% (spectral-only model) and 87.7% (prediction probability model) to 89.7% for the fused model. Similarly, the corresponding kappa coefficients show increases of 0.07–0.08, from 0.60 for the spectral model and 0.61 for the urban prediction model to 0.68 for the fused model. Accuracies aggregated at the block scale present an approximate 2.1–4.3% increase when the fusion-based model is employed compared with the exclusive use of either spectral or prediction probability data, namely 87.6% (fused) vs 83.4% (spectral) and 85.7% (prediction). It is also important to state that the standard deviation of accuracies between blocks is significantly reduced by more than 3% (11.5% vs 14.9% and 14.7%), suggesting higher consistency in classification performance. This is a desirable attribute for subsequent use of these products, for example by the urban planning community. Statistical tests at the block scale also demonstrate that such improvements are significant. It is also observed that to receive the integration benefits, the remote sensing classifier needs a large but reasonable training data set size, while the prediction model should be based on advanced modelling methods. Further assessments on block accuracy with respect to urbanization conditions (i.e. urban presence and change sizes) indicate the ability of the fusion to address spectral limitations, especially in blocks with high relative change. These initial results encourage the expansion of spectral/prediction data fusion to other sites, modelling techniques, and input data.

[1]  Jennifer A. Miller,et al.  Modeling the distribution of four vegetation alliances using generalized linear models and classification trees with spatial dependence , 2002 .

[2]  Giorgos Mountrakis,et al.  Enhancing and replacing spectral information with intermediate structural inputs: A case study on impervious surface detection , 2011 .

[3]  Zhiyong Hu,et al.  Modeling urban growth in Atlanta using logistic regression , 2007, Comput. Environ. Urban Syst..

[4]  Giorgos Mountrakis,et al.  Developing a multi-network urbanization model: A case study of urban growth in Denver, Colorado , 2011, Int. J. Geogr. Inf. Sci..

[5]  E Brown de Colstoun,et al.  National Park vegetation mapping using multitemporal Landsat 7 data and a decision tree classifier , 2003 .

[6]  S. E. Hampson,et al.  Linear function neurons: Structure and training , 1986, Biological Cybernetics.

[7]  Claude R. Duguay,et al.  A software package for integrating digital elevation models into the digital analysis of remote-sensing data , 1989 .

[8]  George Xian,et al.  Quantifying Multi-temporal Urban Development Characteristics in Las Vegas from Landsat and ASTER Data , 2008 .

[9]  Xuefei Hu,et al.  Estimating impervious surfaces from medium spatial resolution imagery using the self-organizing map and multi-layer perceptron neural networks. , 2009 .

[10]  Mark A. Friedl,et al.  Using prior probabilities in decision-tree classification of remotely sensed data , 2002 .

[11]  P. Treitz,et al.  Integrating spectral, spatial, and terrain variables for forest ecosystem classification , 2000 .

[12]  R. Reynolds,et al.  A non-parametric, supervised classification of vegetation types on the Kaibab National Forest using decision trees , 2003 .

[13]  Fabio Dell'Acqua,et al.  Rapid Damage Detection in the Bam Area Using Multitemporal SAR and Exploiting Ancillary Data , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[14]  R. G. Oderwald,et al.  Assessing Landsat classification accuracy using discrete multivariate analysis statistical techniques. , 1983 .

[15]  Usama M. Fayyad,et al.  On the Handling of Continuous-Valued Attributes in Decision Tree Generation , 1992, Machine Learning.

[16]  Qihao Weng,et al.  Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends , 2012 .

[17]  Christiane Weber,et al.  Urbanization pressure and modeling of urban growth: example of the Tunis Metropolitan Area , 2003 .

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

[19]  Karen C. Seto,et al.  Using the ART-MMAP neural network to model and predict urban growth : a spatiotemporal data mining approach , 2008 .

[20]  J. Townshend,et al.  Global land cover classi(cid:142) cation at 1 km spatial resolution using a classi(cid:142) cation tree approach , 2004 .

[21]  T. Esch,et al.  Large-area assessment of impervious surface based on integrated analysis of single-date Landsat-7 images and geospatial vector data , 2009 .

[22]  Robert Gilmore Pontius,et al.  Comparison of the structure and accuracy of two land change models , 2005, Int. J. Geogr. Inf. Sci..

[23]  Paul E. Gessler,et al.  Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments , 2008 .

[24]  D. Roberts,et al.  Sub-pixel mapping of urban land cover using multiple endmember spectral mixture analysis: Manaus, Brazil , 2007 .

[25]  Giorgos Mountrakis,et al.  Integrating intermediate inputs from partially classified images within a hybrid classification framework: An impervious surface estimation example , 2010 .

[26]  Xiaohu Zhang,et al.  Parallel cellular automata for large-scale urban simulation using load-balancing techniques , 2010, Int. J. Geogr. Inf. Sci..

[27]  Alexandra D. Syphard,et al.  Using a cellular automaton model to forecast the effects of urban growth on habitat pattern in southern California , 2005 .

[28]  Alan H. Strahler,et al.  FOCIS: A forest classification and inventory system using LANDSAT and digital terrain data , 1981 .

[29]  Jennifer A. Miller,et al.  Land-Cover Change Monitoring with Classification Trees Using Landsat TM and Ancillary Data , 2003 .

[30]  Evaristo Ricchetti,et al.  Multispectral Satellite Image and Ancillary Data Integration for Geological Classification , 2000 .

[31]  J. Chan,et al.  Detecting the nature of change in an urban environment : A comparison of machine learning algorithms , 2001 .

[32]  R. DeFries,et al.  Classification trees: an alternative to traditional land cover classifiers , 1996 .

[33]  Keith C. Clarke,et al.  Loose-Coupling a Cellular Automaton Model and GIS: Long-Term Urban Growth Prediction for San Francisco and Washington/Baltimore , 1998, Int. J. Geogr. Inf. Sci..

[34]  Li Zhang,et al.  Spatiotemporal analysis of rural–urban land conversion , 2009, Int. J. Geogr. Inf. Sci..

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

[36]  Steven E. Franklin,et al.  Spatial and spectral classification of remote-sensing imagery , 1991 .

[37]  Roger White,et al.  The Use of Constrained Cellular Automata for High-Resolution Modelling of Urban Land-Use Dynamics , 1997 .

[38]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

[39]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .

[40]  Xuefei Hu,et al.  Estimating impervious surfaces using linear spectral mixture analysis with multitemporal ASTER images , 2009 .

[41]  M. Ramsey,et al.  Monitoring urban land cover change: An expert system approach to land cover classification of semiarid to arid urban centers , 2001 .

[42]  Bryan C. Pijanowski,et al.  Calibrating a neural network‐based urban change model for two metropolitan areas of the Upper Midwest of the United States , 2005, Int. J. Geogr. Inf. Sci..

[43]  S. Ventura,et al.  THE INTEGRATION OF GEOGRAPHIC DATA WITH REMOTELY SENSED IMAGERY TO IMPROVE CLASSIFICATION IN AN URBAN AREA , 1995 .

[44]  Alan T. Murray,et al.  Estimating impervious surface distribution by spectral mixture analysis , 2003 .

[45]  J. Franklin Predictive vegetation mapping: geographic modelling of biospatial patterns in relation to environmental gradients , 1995 .

[46]  Ioannis Kanellopoulos,et al.  Global Elevation Ancillary Data for Land-use Classification Using Granular Neural Networks , 2008 .

[47]  M. Bauer,et al.  Estimating and Mapping Impervious Surface Area by Regression Analysis of Landsat Imagery , 2007 .

[48]  Paul M. Mather,et al.  An assessment of the effectiveness of decision tree methods for land cover classification , 2003 .

[49]  Brigitte Poulin,et al.  Wetland monitoring using classification trees and SPOT-5 seasonal time series , 2010 .

[50]  D. Roberts,et al.  Hierarchical Multiple Endmember Spectral Mixture Analysis (MESMA) of hyperspectral imagery for urban environments , 2009 .

[51]  Xiaojun Yang,et al.  Estimating landscape imperviousness index from satellite imagery , 2006, IEEE Geosci. Remote. Sens. Lett..

[52]  Giorgos Mountrakis,et al.  A Spatially Heterogeneous Expert Based (SHEB) Urban Growth Model using Model Regionalization , 2011, J. Geogr. Inf. Syst..

[53]  J. Townshend,et al.  Global land cover classifications at 8 km spatial resolution: The use of training data derived from Landsat imagery in decision tree classifiers , 1998 .

[54]  N. Coops,et al.  Extracting urban vegetation characteristics using spectral mixture analysis and decision tree classifications. , 2009 .

[55]  Geneva G. Belford,et al.  Instability of decision tree classification algorithms , 2001, KDD.

[56]  John R. Jensen,et al.  A change detection model based on neighborhood correlation image analysis and decision tree classification , 2005 .

[57]  K. Seto,et al.  Modeling the Drivers of Urban Land Use Change in the Pearl River Delta, China: Integrating Remote Sensing with Socioeconomic Data , 2003, Land Economics.

[58]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..