Centre de documentation
scientifique

Development of a novel hybrid multi-boosting neural network model for spatial prediction of urban flood / Amid Darabi in Geocarto international, vol 37 n° 19 ([15/09/2022])  

Public [article]  inGeocarto international > vol 37 n° 19 [15/09/2022] . - pp 5716 - 5741 Titre : Development of a novel hybrid multi-boosting neural network model for spatial prediction of urban flood Type de document : Article/Communication Auteurs : Amid Darabi, Auteur ; Omid Rahmati, Auteur ; Seyed Amir Naghibi, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 5716 - 5741 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie thématique [Termes IGN] aléa [Termes IGN] apprentissage automatique [Termes IGN] cartographie des risques [Termes IGN] classification et arbre de régression [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par Perceptron multicouche [Termes IGN] écoulement des eaux [Termes IGN] inondation [Termes IGN] Iran [Termes IGN] simulation spatiale [Termes IGN] zone urbaine Résumé : (auteur) In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models. Numéro de notice : A2022-708 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2021.1920629 Date de publication en ligne : 13/05/2021 En ligne : https://doi.org/10.1080/10106049.2021.1920629 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101578 [article]

Applicability of generalized additive model in groundwater potential modelling and comparison its performance by bivariate statistical methods / Fatemeh Falah in Geocarto international, vol 32 n° 10 (October 2017)  

Public [article]  inGeocarto international > vol 32 n° 10 (October 2017) . - pp 1069 - 1089 Titre : Applicability of generalized additive model in groundwater potential modelling and comparison its performance by bivariate statistical methods Type de document : Article/Communication Auteurs : Fatemeh Falah, Auteur ; Samira Ghorbani Nejad, Auteur ; Omid Rahmati, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 1069 - 1089 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] analyse bivariée [Termes IGN] ArcGIS [Termes IGN] eau souterraine [Termes IGN] géostatistique [Termes IGN] Iran [Termes IGN] modèle de simulation [Termes IGN] ressources en eau [Termes IGN] système d'information géographique Résumé : (Auteur) Groundwater is the most valuable natural resource in arid areas. Therefore, any attempt to investigate potential zones of groundwater for further management of water supply is necessary. Hence, many researchers have worked on this subject all around the world. On the other hand, the Generalized Additive Model (GAM) has been applied to environmental and ecological modelling, but its applicability to other kinds of predictive modelling such as groundwater potential mapping has not yet been investigated. Therefore, the main purpose of this study is to evaluate the performance of GAM model and then its comparison with three popular GIS-based bivariate statistical methods, namely Frequency Ratio (FR), Statistical Index (SI) and Weight-of-Evidence (WOE) for producing groundwater spring potential map (GSPM) in Lorestan Province Iran. To achieve this, out of 6439 existed springs, 4291 spring locations were selected for training phase and the remaining 2147 springs for model evaluation. Next, the thematic layers of 12 effective spring parameters including altitude, plan curvature, slope angle, slope aspect, drainage density, distance from rivers, topographic wetness index, fault density, distance from fault, lithology, soil and land use/land cover were mapped and integrated using the ArcGIS 10.2 software to generate a groundwater prospect map using mentioned approaches. The produced GSPMs were then classified into four distinct groundwater potential zones, namely low, moderate, high and very high classes. The results of the analysis were finally validated using the receiver operating characteristic (ROC) curve technique. The results indicated that out of four models, SI is superior (prediction accuracy of 85.4%) following by FR, GAM and WOE, respectively (prediction accuracy of 83.7, 77 and 76.3%). The result of groundwater spring potential map is helpful as a guide for engineers in water resources management and land use planning in order to select suitable areas to implement development schemes and also government entities. Numéro de notice : A2017-669 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.201 Date de publication en ligne : 07/06/2016 En ligne : https://doi.org/10.1080/10106049.2016.1188166 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=87144 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2017101	RAB	Revue	Centre de documentation	En réserve L003	Disponible