Centre de documentation
scientifique

Spatio-temporal urban landscape change analysis using the Markov chain model and a modified genetic algorithm / J. Tang in International Journal of Remote Sensing IJRS, vol 28 n°15-16 (August 2007)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 28 n°15-16 (August 2007) . - pp 3255 - 3271 Titre : Spatio-temporal urban landscape change analysis using the Markov chain model and a modified genetic algorithm Type de document : Article/Communication Auteurs : J. Tang, Auteur ; L. Wang, Auteur ; Z. Yao, Auteur Année de publication : 2007 Article en page(s) : pp 3255 - 3271 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme génétique [Termes IGN] analyse spatio-temporelle [Termes IGN] chaîne de Markov [Termes IGN] Chine [Termes IGN] image Landsat [Termes IGN] modèle de Markov [Termes IGN] prévision [Termes IGN] urbanisation Résumé : (Auteur) The landscape pattern of Daqing City, China, has undergone a significant change over the past 20 years, as a result of the rapid urbanization process. To understand how urbanization has influenced the landscape in Daqing City, the largest base of the petrochemical industry in China, we conducted a series of spatial analyses with landscape pattern maps obtained from Landsat images in 1979, 1990 and 2000. Results indicate that a substantial urban area has been extended during the past two decades, along with the shrinking of wetland and woodland. Spatio-temporal optimization is not a trivial task in developing landscape models. In previous studies, the optimization of spatial and temporal factors was achieved separately, because of the difficulty in formulating them together in a single model. In this study, we adapted the traditional Markov model by obtaining model parameters and neighbourhood rules from a modified genetic algorithm (GA). Model performance was evaluated between the empirical landscape map from the Landsat image and the simulated landscape map from the models. Over three simulation runs, the global deviation (GD) for the three models was 1.37, 1.10 and 1.15, respectively. This result shows that the Markov model and the GA together are able to effectively capture the spatio-temporal trend in the landscape pattern associated with urbanization for this region. The future landscape distribution in 2010, 2030 and 2050 was derived using a spatial Markov model (SMM) for further urban change and planning research. Copyright Taylor & Francis Numéro de notice : A2007-357 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160600962749 En ligne : https://doi.org/10.1080/01431160600962749 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28720 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-07091	RAB	Revue	Centre de documentation	En réserve L003	Disponible