TITLE

OPTIMUM PREDICTIVE MODEL FOR URBAN GROWTH PREDICTION

AUTHOR(S)
Ongsomwang, Suwit; Saravisutra, Apiradee
PUB. DATE
April 2011
SOURCE
Suranaree Journal of Science & Technology;Apr-Jun2011, Vol. 18 Issue 2, p141
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
This study aims to establish a framework to identify an optimum predictive model for simulation of urban dynamics in Nakhon Ratchasima province, Thailand. This study focuses on 2 different tochastic algorithms including the Cellular Automata Markov and logistic regression models. The core input data from interpreted land use in 1986 and 1994 were used to predict land use in 2002. The results are then compared with interpreted land use in 2002 to identify an optimum predictive model for urban growth. Results showed that the CA-Markov model provided higher overall accuracy and kappa hat coefficient of agreement for urban growth prediction in 2002 than the logistic regression model. Therefore, the CA-Markov model was chosen as an optimum predictive model for urban growth in 2010 and 2018. It was found that the urban and built-up area increased by about 36.32 sq. km (4.8% of the study area) between 2002 and 2010 while it increased by about 70.87 sq. km (9.4 % of the study area) between 2002 and 2018.
ACCESSION #
70020775

 

Related Articles

  • Langevin-Type Models II: Self-Targeting Candidates for MCMC Algorithms. Stramer, O.; Tweedie, R. L. // Methodology & Computing in Applied Probability;Oct1999, Vol. 1 Issue 3, p307 

    The Metropolis-Hastings algorithm for estimating a distribution π is based on choosing a candidate Markov chain and then accepting or rejecting moves of the candidate to produce a chain known to have π as the invariant measure. The tradiiional methods use candidates essentially...

  • Nonparametric interpolation of the Markov sequence. Dobrovidov, A. // Automation & Remote Control;Jan2008, Vol. 69 Issue 1, p52 

    Consideration was given to the problem of interpolation (smoothing) of the nonobservable component of the composite Markov process within the framework of the conditional Markov scheme. In the case of the dynamic observation models such as autoregression, equations were derived for the a...

  • Estimation of Sparse Binary Pairwise Markov Networks using Pseudo-likelihoods. Höfling, Holger; Tibshirani, Robert // Journal of Machine Learning Research;4/1/2009, Vol. 10 Issue 4, p883 

    We consider the problems of estimating the parameters as well as the structure of binary-valued Markov networks. For maximizing the penalized log-likelihood, we implement an approximate procedure based on the pseudo-likelihood of Besag (1975) and generalize it to a fast exact algorithm. The...

  • Bayesian power-law regression with a location parameter, with applications for construction of discharge rating curves. Reitan, Trond; Petersen-Øverleir, Asgeir // Stochastic Environmental Research & Risk Assessment;Apr2008, Vol. 22 Issue 3, p351 

    This paper presents a Bayesian approach for fitting the standard power-law rating curve model to a set of stage-discharge measurements. Methods for eliciting both regional and at-site prior information, and issues concerning the determination of prior forms, are discussed. An efficient MCMC...

  • Bayesian multilocus association mapping on ordinal and censored traits and its application to the analysis of genetic variation among Oryza sativa L. germplasms. Iwata, Hiroyoshi; Ebana, Kaworu; Fukuoka, Shuichi; Jannink, Jean-Luc; Hayashi, Takeshi // Theoretical & Applied Genetics;Mar2009, Vol. 118 Issue 5, p865 

    Association mapping can be a powerful tool for detecting quantitative trait loci (QTLs) without requiring line-crossing experiments. We previously proposed a Bayesian approach for simultaneously mapping multiple QTLs by a regression method that directly incorporates estimates of the population...

  • Multi-Task Learning for Classification with Dirichlet Process Priors. Ya Xue; Xuejun Liao; Carin, Lawrence; Krishnapuram, Balaji // Journal of Machine Learning Research;1/1/2007, Vol. 8 Issue 1, p35 

    Consider the problem of learning logistic-regression models for multiple classification tasks, where the training data set for each task is not drawn from the same statistical distribution. In such a multi-task learning (MTL) scenario, it is necessary to identify groups of similar tasks that...

  • Electricity Consumption Prediction Based on Improved WMC-GA-CV-SVR. Zheng Zhang; Shanlin Yang // Journal of Convergence Information Technology;Jan2013, Vol. 8 Issue 1, p214 

    Support Vector Regression model with Genetic Algorithm and Cross Validation (GA-CV) is proposed to predict the electricity consumption of Jiangsu province at first. The indicators such as temperature, retail sales of consumer goods, CPI, imports and exports are used by SVR model. In addition,...

  • Markov counting models for correlated binary responses. CRAWFORD, FORREST W.; ZELTERMAN, DANIEL // Biostatistics;Jul2015, Vol. 16 Issue 3, p427 

    We propose a class of continuous-time Markov counting processes for analyzing correlated binary data and establish a correspondence between these models and sums of exchangeable Bernoulli random variables. Our approach generalizes many previous models for correlated outcomes, admits easily...

  • Modelling the distribution of plant species using the autologistic regression model. HULIN WU; F RED W. HUFFER // Environmental & Ecological Statistics;Jan1997, Vol. 4 Issue 1, p31 

    The article deals with the problem of plant species distribution modeling in terms of climate variables including temperatures and rainfall. It proposes the use of autologistic regression model for the modelling of spatial binary data. It describes estimation methods which include coding method...

Share

Read the Article

Courtesy of VIRGINIA BEACH PUBLIC LIBRARY AND SYSTEM

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics