Centre de documentation
scientifique

Dépouillements

Approximating prediction uncertainty for random forest regression models / John W. Coulston in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 3 (March 2016)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 82 n° 3 (March 2016) . - pp 189 - 197 Titre : Approximating prediction uncertainty for random forest regression models Type de document : Article/Communication Auteurs : John W. Coulston, Auteur ; Christine E. Blinn, Auteur ; Valerie A. Thomas, Auteur ; Randolph H. Wynne, Auteur Année de publication : 2016 Article en page(s) : pp 189 - 197 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] incertitude des données [Termes IGN] méthode de Monte-Carlo [Termes IGN] modèle de régression [Termes IGN] prédiction [Termes IGN] variable Résumé : (auteur) Machine learning approaches such as random forest have increased for the spatial modeling and mapping of continuous variables. Random forest is a non-parametric ensemble approach, and unlike traditional regression approaches there is no direct quantification of prediction error. Understanding prediction uncertainty is important when using model-based continuous maps as inputs to other modeling applications such as fire modeling. Here we use a Monte Carlo approach to quantify prediction uncertainty for random forest regression models. We test the approach by simulating maps of dependent and independent variables with known characteristics and comparing actual errors with prediction errors. Our approach produced conservative prediction intervals across most of the range of predicted values. However, because the Monte Carlo approach was data driven, prediction intervals were either too wide or too narrow in sparse parts of the prediction distribution. Overall, our approach provides reasonable estimates of prediction uncertainty for random forest regression models. Numéro de notice : A2016-176 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.82.3.189 En ligne : https://doi.org/10.14358/PERS.82.3.189 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80506 [article]

Comparison of three Landsat TM compositing methods: A case study using modeled tree canopy cover / Bonnie Ruefenacht in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 3 (March 2016)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 82 n° 3 (March 2016) . - pp 199 - 211 Titre : Comparison of three Landsat TM compositing methods: A case study using modeled tree canopy cover Type de document : Article/Communication Auteurs : Bonnie Ruefenacht, Auteur Année de publication : 2016 Article en page(s) : pp 199 - 211 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] canopée [Termes IGN] image Landsat-TM [Termes IGN] modèle de régression [Termes IGN] mosaïquage d'images [Termes IGN] Normalized Difference Vegetation Index Résumé : (auteur) Landsat imagery mosaics developed using model II regression have been shown to successfully model percent tree-canopy cover (PTCC). Creating model II regression mosaics, however, is a time-consuming, manual process. The objective of this study is to evaluate the effectiveness of using more easily automated image composites techniques, such as median Landsat-5 image composites or maximum NDVI Landsat-5 image composites, as alternatives to model II regression mosaics for the modeling of PTCC. This study found all composite types were effective in modeling PTCC, but the maximum NDVI composites included anomalies, clouds, shadows, and tended to be pixelated, whereas the median composites and the model II regression mosaics had none of these issues. The median composite procedure is automated and was found to be an effective approach to statistically reduce a much larger ensemble of images on a pixel basis to create images suitable for vegetation modeling. Numéro de notice : A2016-177 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.82.3.189 En ligne : https://doi.org/10.14358/PERS.82.3.189 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80515 [article]

A feature selection approach for segmentation of very high-resolution satellite images / Ahmad Izadipour in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 3 (March 2016)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 82 n° 3 (March 2016) . - pp 213 - 222 Titre : A feature selection approach for segmentation of very high-resolution satellite images Type de document : Article/Communication Auteurs : Ahmad Izadipour, Auteur ; Behzad Akbari, Auteur ; Barat Mojaradi, Auteur Année de publication : 2016 Article en page(s) : pp 213 - 222 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] extraction de traits caractéristiques [Termes IGN] image Geoeye [Termes IGN] image Quickbird [Termes IGN] résolution globale (imagerie) [Termes IGN] segmentation d'image Résumé : (auteur) Most of the feature selection (FS) methods in the literature determine features that are appropriate only for a given dataset. In contrast, in this paper a FS method that is not dependent to a specific dataset is proposed. In this regard, the effective feature types based on reasonable facts are predefined and appropriate candidate features for each feature type are selected. In proposed method, the features selected from a single labeled image can be used in segmentation of images captured by different satellites with similar spatial resolution. The selected feature types contain spatial and spectral features. The selected features are applied for segmentation of the images captured by QuickBird and GeoEye satellites and obtained results of proposed method are compared with well-known FS methods. Using different evaluation measures, our comparison shows the efficiency of the proposed method in providing better segmentation compared to other FS methods that are presented in this paper. Numéro de notice : A2016-178 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.82.3.213 En ligne : https://doi.org/10.14358/PERS.82.3.213 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80519 [article]