Comparing support vector machines with logistic regression for calibrating cellular automata land use change models

ABSTRACT Land use change models enable the exploration of the drivers and consequences of land use dynamics. A broad array of modeling approaches are available and each type has certain advantages and disadvantages depending on the objective of the research. This paper presents an approach combining cellular automata (CA) model and support vector machines (SVMs) for modeling urban land use change in Wallonia (Belgium) between 2000 and 2010. The main objective of this study is to compare the accuracy of allocating new land use transitions based on CA-SVMs approach with conventional coupled logistic regression method (logit) and CA (CA-logit). Both approaches are used to calibrate the CA transition rules. Various geophysical and proximity factors are considered as urban expansion driving forces. Relative operating characteristic and a fuzzy map comparison are employed to evaluate the performance of the model. The evaluation processes highlight that the allocation ability of CA-SVMs slightly outperforms CA-logit approach. The result also reveals that the major urban expansion determinant is urban road infrastructure.

[1]  Andrés Manuel García,et al.  An analysis of the effect of the stochastic component of urban cellular automata models , 2011, Comput. Environ. Urban Syst..

[2]  Bart Baesens,et al.  Comprehensible Credit Scoring Models Using Rule Extraction from Support Vector Machines , 2007, Eur. J. Oper. Res..

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

[4]  A. Rompaey,et al.  Urban growth of Kampala, Uganda: Pattern analysis and scenario development , 2012 .

[5]  Perver K. Baran,et al.  Suburban change: A time series approach to measuring form and spatial configuration , 2013 .

[6]  Xia Li,et al.  Cellular automata for simulating land use changes based on support vector machines , 2008, Comput. Geosci..

[7]  Mario Cools,et al.  Understanding urban development types and drivers in Wallonia: a multi-density approach , 2017, Int. J. Bus. Intell. Data Min..

[8]  Melvin Alexander.  Applied Statistics and Probability for Engineers , 1995 .

[9]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[10]  Yan Liu,et al.  Modeling dynamic urban growth using cellular automata and particle swarm optimization rules , 2011 .

[11]  A. Troisi,et al.  AN URBAN GROWTH MODEL BASED ON A CELLULAR AUTOMATA PHENOMENOLOGICAL FRAMEWORK , 2011 .

[12]  Johan A. K. Suykens,et al.  Financial time series prediction using least squares support vector machines within the evidence framework , 2001, IEEE Trans. Neural Networks.

[13]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[14]  Filip De Turck,et al.  Bmc Medical Informatics and Decision Making Support Vector Machine versus Logistic Regression Modeling for Prediction of Hospital Mortality in Critically Ill Patients with Haematological Malignancies , 2008 .

[15]  A. Rompaey,et al.  Detecting and modelling spatial patterns of urban sprawl in highly fragmented areas: A case study in the Flanders–Brussels region , 2009 .

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

[17]  A. Achmad,et al.  Modeling of urban growth in tsunami-prone city using logistic regression: Analysis of Banda Aceh, Indonesia , 2015 .

[18]  Mario Cools,et al.  Measuring the Effect of Stochastic Perturbation Component in Cellular Automata Urban Growth Model , 2014 .

[19]  Roger White,et al.  Hierarchical fuzzy pattern matching for the regional comparison of land use maps , 2001, Int. J. Geogr. Inf. Sci..

[20]  Bogdan Zagajewski,et al.  Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images , 2017 .

[21]  Xiaoping Liu,et al.  Modeling urban land-use dynamics in a fast developing city using the modified logistic cellular automaton with a patch-based simulation strategy , 2014, Int. J. Geogr. Inf. Sci..

[22]  Mario Cools,et al.  Addressing the determinants of built-up expansion and densification processes at the regional scale , 2018 .

[23]  A. Troisi,et al.  Can CA describe collective effects of polluting agents , 2015 .

[24]  P. Waddell.  UrbanSim: Modeling Urban Development for Land Use, Transportation, and Environmental Planning , 2002 .

[25]  Lien Poelmans,et al.  Complexity and performance of urban expansion models , 2010, Comput. Environ. Urban Syst..

[26]  Graham K. Rand,et al.  Quantitative Applications in the Social Sciences , 1983 .

[27]  Ikechukwu Maduako,et al.  Spatio-temporal urban growth dynamics of Lagos Metropolitan Region of Nigeria based on Hybrid methods for LULC modeling and prediction , 2018 .

[28]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[29]  F. Meza,et al.  Assessing spatial dynamics of urban growth using an integrated land use model. Application in Santiago Metropolitan Area, 2010-2045 , 2014 .

[30]  I. Thomas,et al.  The morphology of built-up landscapes in Wallonia (Belgium): A classification using fractal indices , 2008 .

[31]  Jason Weston,et al.  A user's guide to support vector machines. , 2010, Methods in molecular biology.

[32]  S. Gottwald,et al.  Fuzzy sets, fuzzy logic, fuzzy methods with applications , 1995 .

[33]  S. Goetz,et al.  Using the Sleuth Urban Growth Model to Simulate the Impacts of Future Policy Scenarios on Urban Land Use in the Baltimore-Washington Metropolitan Area , 2004 .

[34]  Ton C M de Nijs,et al.  Determinants of Land-Use Change Patterns in the Netherlands , 2004 .

[35]  Andrés Manuel García,et al.  Cellular automata models for the simulation of real-world urban processes: A review and analysis , 2010 .

[36]  Xijun Yu,et al.  Modelling urban expansion using a multi agent-based model in the city of Changsha , 2010 .

[37]  A. Troisi,et al.  CA-PRI, A CELLULAR AUTOMATA PHENOMENOLOGICAL RESEARCH INVESTIGATION: SIMULATION RESULTS , 2013 .

[38]  Alain Bonnafous,et al.  Urban simulation with alternative road pricing scenarios , 2015 .

[39]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[40]  Mario Cools,et al.  Coupling agent-based, cellular automata and logistic regression into a hybrid urban expansion model (HUEM) , 2017 .

[41]  Alex Hagen,et al.  Fuzzy set approach to assessing similarity of categorical maps , 2003, Int. J. Geogr. Inf. Sci..

[42]  Adrian E. Raftery,et al.  Assessing Uncertainty in Urban Simulations Using Bayesian Melding , 2007 .

[43]  Xia Li,et al.  Simulating complex urban development using kernel-based non-linear cellular automata , 2008 .

[44]  M. Batty,et al.  Modeling urban dynamics through GIS-based cellular automata , 1999 .

[45]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[46]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[47]  Robert V. Brill,et al.  Applied Statistics and Probability for Engineers , 2004, Technometrics.

[48]  Mark Brussel,et al.  Logistic regression and cellular automata-based modelling of retail, commercial and residential development in the city of Ahmedabad, India , 2014 .

[49]  Andreas Rienow,et al.  Supporting SLEUTH - Enhancing a cellular automaton with support vector machines for urban growth modeling , 2015, Comput. Environ. Urban Syst..

[50]  Xingjian Liu,et al.  Simulating urban expansion using a cloud-based cellular automata model: A case study of Jiangxia, Wuhan, China , 2013 .

[51]  Richard Tay,et al.  Support vector machines for urban growth modeling , 2010, GeoInformatica.

[52]  Isabelle Thomas,et al.  Defining and characterizing urban boundaries: A fractal analysis of theoretical cities and Belgian cities , 2013, Comput. Environ. Urban Syst..

[53]  Fulong Wu,et al.  Calibration of stochastic cellular automata: the application to rural-urban land conversions , 2002, Int. J. Geogr. Inf. Sci..

[54]  I. Masser,et al.  Urban growth pattern modeling: a case study of Wuhan city, PR China , 2003 .

[55]  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..

[56]  Roger White,et al.  Cellular Automata and Fractal Urban Form: A Cellular Modelling Approach to the Evolution of Urban Land-Use Patterns , 1993 .

[57]  Mario Cools,et al.  Modelling built-up expansion and densification with multinomial logistic regression, cellular automata and genetic algorithm , 2018, Comput. Environ. Urban Syst..

[58]  Yuek Ming Ho,et al.  The simulation and prediction of spatio-temporal urban growth trends using cellular automata models: A review , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[59]  Bernhard Schölkopf,et al.  Incorporating Invariances in Support Vector Learning Machines , 1996, ICANN.

[60]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[61]  Keith C. Clarke,et al.  Cellular automata modeling approaches to forecast urban growth for adana, Turkey: A comparative approach , 2016 .

[62]  Jamal Jokar Arsanjani,et al.  ntegration of logistic regression , Markov chain and cellular automata odels to simulate urban expansion amal , 2012 .

[63]  R. Kelley Pace,et al.  Semiparametric Maximum Likelihood Estimates of Spatial Dependence , 2002 .

[64]  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.

[65]  Fernando De la Torre,et al.  Optimal feature selection for support vector machines , 2010, Pattern Recognit..