Centre dedocumentation
scientifique

A comparison of a gradient boosting decision tree, random forests, and artificial neural networks to model urban land use changes: the case of the Seoul metropolitan area / Myung-Jin Jun in International journal of geographical information science IJGIS, vol 35 n° 11 (November 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 11 (November 2021) . - pp 2149 - 2167 Titre : A comparison of a gradient boosting decision tree, random forests, and artificial neural networks to model urban land use changes: the case of the Seoul metropolitan area Type de document : Article/Communication Auteurs : Myung-Jin Jun, Auteur Année de publication : 2021 Article en page(s) : pp 2149 - 2167 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse comparative [Termes IGN] arbre de décision [Termes IGN] changement d'utilisation du sol [Termes IGN] classification par forêts aléatoires [Termes IGN] Extreme Gradient Machine [Termes IGN] modèle de simulation [Termes IGN] réseau neuronal artificiel [Termes IGN] Séoul [Termes IGN] zone urbaine Résumé : (auteur) This study compares the performance of gradient boosting decision tree (GBDT), artificial neural networks (ANNs), and random forests (RF) methods in LUC modeling in the Seoul metropolitan area. The results of this study showed that GBDT and RF have higher predictive power than ANN, indicating that tree-based ensemble methods are an effective technique for LUC prediction. Along with the outstanding predictive performance, the DT-based ensemble models provide insights for understanding which factors drive LUCs in complex urban dynamics with the relative importance and nonlinear marginal effects of predictor variables. The GBDT results indicate that distance to the existing residential site has the highest contribution to urban land use conversion (30.4% of the relative importance), while other significant predictor variables were proximity to industrial and public sites (combined 32.3% of relative importance). New residential development is likely to be adjacent to existing residential sites, but nonresidential development occurs at a distance (about 600 m) from such sites. The distance to the central business district (CBD) had increasing marginal effects on residential land use conversion, while no significant pattern was found for nonresidential land use conversion, indicating that Seoul has experienced more population suburbanization than employment decentralization. Numéro de notice : A2021-756 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2021.1887490 Date de publication en ligne : 01/03/2021 En ligne : https://doi.org/10.1080/13658816.2021.1887490 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98771 [article]

Spatial interpolation of mobile positioning data for population statistics / Anto Aasa in Journal of location-based services, vol 15 n° inconnu ([01/10/2021])  

Public [article]  inJournal of location-based services > vol 15 n° inconnu [01/10/2021] Titre : Spatial interpolation of mobile positioning data for population statistics Type de document : Article/Communication Auteurs : Anto Aasa, Auteur ; Pilleriine Kamenjuk, Auteur ; Erki Saluveer, Auteur ; et al., Auteur Année de publication : 2021 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] analyse comparative [Termes IGN] classification par forêts aléatoires [Termes IGN] données démographiques [Termes IGN] données GNSS [Termes IGN] interpolation spatiale [Termes IGN] mobilité [Termes IGN] traitement de données localisées Résumé : (auteur) Mobile positioning is recognised to be one of the most promising new sources of data for the production of fast and cost-effective statistics regarding population and mobility. Considerable interest has been shown by government institutions in their search for a way to use mobile positioning data to produce official statistics, although to date there are only few examples of successful projects. Apart from data access and sampling, the main challenges relate to the spatial interpolation of mobile positioning data and extrapolation of recorded data to the level of the entire population. This area of work has to date received relatively little attention in the academic discussion. In the current study, we compare five different methods of spatial interpolation of mobile positioning data. The best methods of describing population distribution and size in comparison with Census data are the adaptive Morton grid and the Random forest model (R2 > 0.9), while the more widely used point-in-polygon and areal-weighted methods produce results that are far less satisfactory (R2 = 0.42; R2 = 0.35). Careful selection of spatial interpolation methods is therefore of the utmost importance for producing reliable population statistics from mobile positioning data. Numéro de notice : A2021-727 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/17489725.2021.1917710 Date de publication en ligne : 10/05/2021 En ligne : https://doi.org/10.1080/17489725.2021.1917710 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98658 [article]

Using LiDAR and Random Forest to improve deer habitat models in a managed forest landscape / Colin S. Shanley in Forest ecology and management, vol 499 (1 November 2021)  

Public [article]  inForest ecology and management > vol 499 (1 November 2021) . - n° 119580 Titre : Using LiDAR and Random Forest to improve deer habitat models in a managed forest landscape Type de document : Article/Communication Auteurs : Colin S. Shanley, Auteur ; Daniel R. Eacker, Auteur ; Connor P. Reynolds, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 119580 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] Alaska (Etats-Unis) [Termes IGN] Cervidae [Termes IGN] classification par forêts aléatoires [Termes IGN] coefficient de corrélation [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] géomorphométrie [Termes IGN] habitat animal [Termes IGN] habitat forestier [Termes IGN] paysage forestier [Termes IGN] semis de points Résumé : (auteur) Conservation strategies are hindered by a lack of accurate maps of important habitat for many wildlife species, but especially for species inhabiting managed forest landscapes. Prioritizing restoration efforts on Alaska’s Tongass National Forest from past extensive clearcut logging is extremely challenging given the difficulty in accurately mapping its remote, rugged temperate rainforest landscapes. We tested the application of airborne light detection and ranging (LiDAR) technology to build a winter habitat model for Sitka black-tailed deer (Odocoileus hemionus sitkensis), the primary herbivore in the coastal temperate rainforest. We analyzed the importance of geomorphometric and forest structure characteristics as predictors of deer winter habitat selection using Random Forest applied to a 3-year GPS relocation dataset collected from 40 adult female deer. The LiDAR-based habitat model had a predictive performance of 94% (Out-of-bag error = 6%), a 10% lower model error compared to air-photo interpreted polygons and modeled plot data. Random Forest also outperformed analogous resource selection function models based on a comprehensive k-fold cross-validation. Deer habitat selection patterns in the LiDAR-based model were nonlinear across geomorphometric and forest structure predictive variables, and generally supported existing studies of deer habitat selection. Besides improving deer conservation and management on the Tongass National Forest, our approach could greatly enhance the accuracy and resolution of habitat maps used for conservation and restoration planning across large managed forest landscapes. Numéro de notice : A2021-696 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.foreco.2021.119580 Date de publication en ligne : 26/08/2021 En ligne : https://doi.org/10.1016/j.foreco.2021.119580 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98529 [article]

Classification of tree species in a heterogeneous urban environment using object-based ensemble analysis and World View-2 satellite imagery / Simbarashe Jombo in Applied geomatics, vol 13 n° 3 (September 2021)  

Public [article]  inApplied geomatics > vol 13 n° 3 (September 2021) . - pp 373 - 387 Titre : Classification of tree species in a heterogeneous urban environment using object-based ensemble analysis and World View-2 satellite imagery Type de document : Article/Communication Auteurs : Simbarashe Jombo, Auteur ; Elhadi Adam, Auteur ; John Odindi, Auteur Année de publication : 2021 Article en page(s) : pp 373 - 387 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image orientée objet [Termes IGN] arbre urbain [Termes IGN] classification par forêts aléatoires [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] espèce végétale [Termes IGN] image à très haute résolution [Termes IGN] image multibande [Termes IGN] image Worldview [Termes IGN] indice de végétation [Termes IGN] Johannesbourg [Termes IGN] segmentation d'image Résumé : (auteur) Urban trees are valuable in, inter alia, ameliorating air pollution and mitigating the effects associated with urban heat islands. The dearth of tree cover maps is a major challenge for urban planners in the management of urban trees. This work adopts remote sensing approaches to provide urban tree cover maps which can strengthen urban landscape management. Whereas traditional pixel-based classification approaches have been commonly used in image classification, they are not well-suited for urban tree mapping due to their failure to fully explore the image’s spatial and spectral characteristics. Object-based classification techniques produce improved accuracies using additional variables. This study depicts the capability of object-based image analysis (OBIA) in mapping common urban trees using very high-resolution (VHR) WorldView-2 (WV-2) imagery. The study tests the utility of WV-2 bands and other feature variables in the object-based mapping of common urban trees and other land cover classes. Furthermore, the study compares the utility of Support Vector Machine (SVM) and Random Forest (RF) in the object-based mapping of common urban trees and other land cover classes. The results show that the Normalized Difference Vegetation Index (NDVI), NIR 1 and NIR 2 bands were important in the classification of common urban trees and other land cover classes. The RF classifier performed better than SVM, with an overall accuracy of 91.9% as compared to 87.3% for SVM. The results of this study offer insight to urban authorities with knowledge on the segmentation parameters, classification methods and feature variables for mapping urban trees, valuable in urban tree management. Numéro de notice : A2021-624 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1007/s12518-021-00358-3 Date de publication en ligne : 20/01/2021 En ligne : https://doi.org/10.1007/s12518-021-00358-3 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98248 [article]

Two hidden layer neural network-based rotation forest ensemble for hyperspectral image classification / Laxmi Narayana Eeti in Geocarto international, vol 36 n° 16 ([17/08/2021])  

Public [article]  inGeocarto international > vol 36 n° 16 [17/08/2021] . - pp 1820 - 1837 Titre : Two hidden layer neural network-based rotation forest ensemble for hyperspectral image classification Type de document : Article/Communication Auteurs : Laxmi Narayana Eeti, Auteur ; Krishna Mohan Buddhiraju, Auteur Année de publication : 2021 Article en page(s) : pp 1820 - 1837 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] arbre de décision [Termes IGN] bagging [Termes IGN] classification par forêts aléatoires [Termes IGN] image AVIRIS [Termes IGN] image EO1-Hyperion [Termes IGN] image hyperspectrale [Termes IGN] image ROSIS [Termes IGN] Perceptron multicouche [Termes IGN] précision de la classification [Termes IGN] réseau neuronal profond [Termes IGN] Rotation Forest classification Résumé : (auteur) Decision tree-based Rotation Forest could generate satisfactory but lower classification accuracy for a given training sample set and image data, owing to the inherent disadvantages in decision trees, namely myopic, replication and fragmentation problem. To improve performance of Rotation Forest technique, we propose to utilize two-hidden-layered-feedforward neural network as base classifier instead of decision tree. We examine the classification performance of proposed model under two situations, namely when free network parameters are maintained the same across all ensemble components and otherwise. The proposed model, where each component is initialized with different pair of initial weights and bias, performs better than decision tree-based Rotation Forest on three different Hyperspectral sensor datasets – AVIRIS, ROSIS and Hyperion. Improvements in classification accuracy are above 2% and up to 3% depending upon dataset. Also, the proposed model achieves improvement in accuracy over Random Forest in the range 4.2–8.8%. Numéro de notice : A2021-581 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1678680 Date de publication en ligne : 21/10/2019 En ligne : https://doi.org/10.1080/10106049.2019.1678680 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98193 [article]

Unsupervised band selection of hyperspectral data based on mutual information derived from weighted cluster entropy for snow classification / Divyesh Varade in Geocarto international, Vol 36 n° 15 ([10/08/2021])  

Permalink

Investigating the application of artificial intelligence for earthquake prediction in Terengganu / Suzlyana Marhain in Natural Hazards, vol 108 n° 1 (August 2021)  

Permalink

Measuring shallow-water bathymetric signal strength in lidar point attribute data using machine learning / Kim Lowell in International journal of geographical information science IJGIS, vol 35 n° 8 (August 2021)  

Permalink

Random forests with bagging and genetic algorithms coupled with least trimmed squares regression for soil moisture deficit using SMOS satellite soil moisture / Pashrant K. Srivastava in ISPRS International journal of geo-information, vol 10 n° 8 (August 2021)  

Permalink

Surface modelling of forest aboveground biomass based on remote sensing and forest inventory data / Xiaofang Sun in Geocarto international, vol 36 n° 14 ([01/08/2021])  

Permalink

DEM- and GIS-based analysis of soil erosion depth using machine learning / Kieu Anh Nguyen in ISPRS International journal of geo-information, vol 10 n° 7 (July 2021)  

Permalink

Extracting Shallow-Water Bathymetry from Lidar point clouds using pulse attribute data: Merging density-based and machine learning approaches / Kim Lowell in Marine geodesy, vol 44 n° 4 (July 2021)  

Permalink

Implementing a mass valuation application on interoperable land valuation data model designed as an extension of the national GDI / Arif Cagdas Aydinoglu in Survey review, Vol 53 n° 379 (July 2021)  

Permalink

Machine learning for inference: using gradient boosting decision tree to assess non-linear effects of bus rapid transit on house prices / Linchuan Yang in Annals of GIS, vol 27 n° 3 (July 2021)  

Permalink

Using machine learning to map Western Australian landscapes for mineral exploration / Thomas Albrecht in ISPRS International journal of geo-information, vol 10 n° 7 (July 2021)  

Permalink