Centre de documentation
scientifique

Performance evaluation of land change simulation models using landscape metrics / Sadeq Dezhkam in Geocarto international, vol 32 n° 6 (June 2017)  

Public [article]  inGeocarto international > vol 32 n° 6 (June 2017) . - pp 655 - 677 Titre : Performance evaluation of land change simulation models using landscape metrics Type de document : Article/Communication Auteurs : Sadeq Dezhkam, Auteur ; Bahman Jabbarian Amiri, Auteur ; Ali Asghar Darvishsefat, Auteur ; Yousef Sakieh, Auteur Année de publication : 2017 Article en page(s) : pp 655 - 677 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse diachronique [Termes IGN] champ aléatoire de Markov [Termes IGN] changement d'occupation du sol [Termes IGN] changement d'utilisation du sol [Termes IGN] géovisualisation [Termes IGN] Iran [Termes IGN] modèle de simulation [Termes IGN] simulation spatiale [Termes IGN] test de performance Résumé : (Auteur) This study proposes a landscape metrics-based method for model performance evaluation of land change simulation models. To quantify model performance at both landscape and class levels, a set of composition- and configuration-based metrics including number of patches, class area, landscape shape index, mean patch area and mean Euclidean nearest neighbour distance were employed. These landscape metrics provided detailed information on simulation success of a cellular automata-Markov chain (CA-Markov) model standpoint of spatial arrangement of the simulated map versus the corresponding reference layer. As a measure of model simulation success, mean relative error (MRE) of the metrics was calculated. At both landscape and class levels, the MRE values were accounted for 22.73 and 10.2%, respectively, which are further categorised into qualitative measurements of model simulation performance for simple and quick comparison of the results. Findings of the present study depict a hierarchical and multi spatial level assessment of model performance. Numéro de notice : A2017-276 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2016.1167967 Date de publication en ligne : 08/04/2016 En ligne : http://dx.doi.org/10.1080/10106049.2016.1167967 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85305 [article]