Centre de documentation
scientifique

Estimation of some stand parameters from textural features from WorldView-2 satellite image using the artificial neural network and multiple regression methods: a case study from Turkey / Alkan Günlü in Geocarto international, vol 36 n° 8 ([01/05/2021])  

Public [article]  inGeocarto international > vol 36 n° 8 [01/05/2021] . - pp 918 - 935 Titre : Estimation of some stand parameters from textural features from WorldView-2 satellite image using the artificial neural network and multiple regression methods: a case study from Turkey Type de document : Article/Communication Auteurs : Alkan Günlü, Auteur ; İlker Ercanlı, Auteur ; Muammer Şenyurt, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 918 - 935 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] biomasse aérienne [Termes IGN] classification par Perceptron multicouche [Termes IGN] échantillonnage [Termes IGN] fonction de base radiale [Termes IGN] gestion forestière [Termes IGN] image proche infrarouge [Termes IGN] image Worldview [Termes IGN] matrice de co-occurrence [Termes IGN] peuplement forestier [Termes IGN] Pinus nigra [Termes IGN] régression multiple [Termes IGN] réseau neuronal artificiel [Termes IGN] texture d'image [Termes IGN] Turquie Résumé : (auteur) The aim of this research is to assess some stand parameters such as stand volume (SV), basal area (BA), number of trees (NT) and aboveground biomass (AGB) of pure Crimean pine forest stands in Turkey by using ground measurements and remote sensing techniques. For this purpose, 86 sample plots were collected from pure Crimean pine stands of Yenice Forest Management Planning Unit in Ilgaz Forest Management Enterprise, Turkey. The stand parameters of each sample area were estimated using the data obtained from the sample plots. Subsequently, we calculated the values of contrast (CON), correlation (COR), dissimilarity (DIS), entropy (ENT), homogeneity (HOM), mean (M), second moment (SM) and variance (VAR) from WorldView-2 imagery using a grey-level co-occurrence matrix method. Eight textural features and twelve different window sizes ranging from 3 × 3 to 25 × 25 were generated from blue, green, red and near-infrared bands of the WorldView-2 satellite image. For predicting the relationships between WorldView-2 textural features and stand parameters of each sample plot, regression models were developed by using multiple linear regression (MLR) analysis. Additionally, artificial neural networks (ANNs) based on the multilayer perceptron (MLP) and the radial basis function (RBF) architectures were trained by comparing various numbers of neurons and activation functions in their network types. The results showed that the MLR models had low the coefficient of determination (R2) values (0.32 for SV, 0.35 for BA, 0.33 for NT and 0.34 for AGB), and the most of the ANNs models (MLP and RBF) were better than the regression models for estimating stand parameters. The ANNs model containing MLP and RBF for SV (R2 = 0.40; R2 = 0.56), for BA (R2 = 0.34; R2 = 0.51), for NT (R2 = 0.34; R2 = 0.37) and for AGB (R2 = 0.34, R2 = 0.57) were found the best results, respectively. Our results revealed that the ANNs models developed with WorldView-2 satellite image were beneficial to estimate stand parameters better than the MLR model in pure Crimean pine stands. Numéro de notice : A2021-484 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1629644 Date de publication en ligne : 25/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1629644 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97443 [article]

Artificial neural network models by ALOS PALSAR data for aboveground stand carbon predictions of pure beech stands: a case study from northern of Turkey / Alkan Günlü in Geocarto international, Vol 35 n° 1 ([02/01/2020])  

Public [article]  inGeocarto international > Vol 35 n° 1 [02/01/2020] . - pp 17 - 28 Titre : Artificial neural network models by ALOS PALSAR data for aboveground stand carbon predictions of pure beech stands: a case study from northern of Turkey Type de document : Article/Communication Auteurs : Alkan Günlü, Auteur ; Ilker Erkanli, Auteur Année de publication : 2020 Article en page(s) : pp 17 - 28 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] biomasse aérienne [Termes IGN] Fagus (genre) [Termes IGN] image ALOS-PALSAR [Termes IGN] peuplement forestier [Termes IGN] puits de carbone [Termes IGN] régression multiple [Termes IGN] réseau neuronal artificiel [Termes IGN] Turquie Résumé : (auteur) The goal of this study was to estimate aboveground stand carbon (AGSC) of pure beech stands in Turkey with ground measurements as well as topographic information and remote sensing data. For this purpose, 153 sample plots were collected from pure beech stands in study area. The AGSC of each sample plot was computed. Eight texture images (variance, dissimilarity, homogeneity, entropy, contrast, mean, second moment and correlation) with five window sizes (3 × 3, 5 × 5, 7 × 7, 9 × 9 and 11 × 11) generated from ALOS PALSAR L-band satellite image. The AGSC models predicting the relationships between ALOS PALSAR texture values and topographic information, and sample plot AGSC were developed by using multiple linear regressions (MLR). Also, artificial neural networks (ANNs) architectures were trained by comparing various numbers of neurons and activation functions in its network types. Our results revealed the ability of ANNs was better than MLR models to predict AGSC values. Numéro de notice : A2020-017 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2018.1499817 Date de publication en ligne : 20/09/2018 En ligne : https://doi.org/10.1080/10106049.2018.1499817 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94410 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2020011	RAB	Livre	Centre de documentation	En réserve L003	Disponible