Centre dedocumentation
scientifique

Optimizing local geoid undulation model using GPS/levelling measurements and heuristic regression approaches / Mosbeh R. Kaloop in Survey review, vol 52 n° 375 (November 2020)  

Public [article]  inSurvey review > vol 52 n° 375 (November 2020) . - pp 544 - 554 Titre : Optimizing local geoid undulation model using GPS/levelling measurements and heuristic regression approaches Type de document : Article/Communication Auteurs : Mosbeh R. Kaloop, Auteur ; Ahmed Zaki, Auteur ; Hamad Al-Ajami, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 544 - 554 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie physique [Termes descripteurs IGN] anomalie de pesanteur [Termes descripteurs IGN] géoïde local [Termes descripteurs IGN] Koweit [Termes descripteurs IGN] méthode fondée sur le noyau [Termes descripteurs IGN] méthode heuristique [Termes descripteurs IGN] modèle de géopotentiel [Termes descripteurs IGN] nivellement avec assistance GPS [Termes descripteurs IGN] processus gaussien [Termes descripteurs IGN] régression [Termes descripteurs IGN] régression multivariée par spline adaptative Résumé : (auteur) This study investigates to use GPS/Levelling measurements of Kuwait and four heuristic regression methods including Least Square Support Vector Regression (LSSVR), Gaussian Process Regression (GPR), Kernel Ridge Regression (KRR), and Multivariate Adaptive Regression Splines (MARS) for modelling local geoid undulation. The accuracy of the models was compared by geoid undulation of gravitational observations and Global Geopotential Models (GGMs). The results show that the KRR model is suitable for Kuwait geoid model, its error of percentage is 0.018 and 0.124% relative to gravity and GPS/Levelling geoid undulation models, respectively. Furthermore, the comparison of KRR model with GGMs models signifies its accuracy. Numéro de notice : A2020-688 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2019.1665615 date de publication en ligne : 16/09/2019 En ligne : https://doi.org/10.1080/00396265.2019.1665615 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96221 [article]

The extension of the parametrization of the radio source coordinates in geodetic VLBI and its impact on the time series analysis / Maria Karbon in Journal of geodesy, vol 91 n° 7 (July 2017)  

Public [article]  inJournal of geodesy > vol 91 n° 7 (July 2017) . - pp 755 - 765 Titre : The extension of the parametrization of the radio source coordinates in geodetic VLBI and its impact on the time series analysis Type de document : Article/Communication Auteurs : Maria Karbon, Auteur ; Robert Heinkelmann, Auteur ; Julian Mora-Diaz, Auteur ; Minghui Xu, Auteur ; Tobias Nilsson, Auteur ; Harald Schuh, Auteur Année de publication : 2017 Article en page(s) : pp 755 - 765 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale [Termes descripteurs IGN] données ITGB [Termes descripteurs IGN] fonction spline [Termes descripteurs IGN] interférométrie à très grande base [Termes descripteurs IGN] paramètres d'orientation de la Terre [Termes descripteurs IGN] régression multivariée par spline adaptative [Termes descripteurs IGN] repère de référence céleste [Termes descripteurs IGN] série temporelle Résumé : (Auteur) The radio sources within the most recent celestial reference frame (CRF) catalog ICRF2 are represented by a single, time-invariant coordinate pair. The datum sources were chosen mainly according to certain statistical properties of their position time series. Yet, such statistics are not applicable unconditionally, and also ambiguous. However, ignoring systematics in the source positions of the datum sources inevitably leads to a degradation of the quality of the frame and, therefore, also of the derived quantities such as the Earth orientation parameters. One possible approach to overcome these deficiencies is to extend the parametrization of the source positions, similarly to what is done for the station positions. We decided to use the multivariate adaptive regression splines algorithm to parametrize the source coordinates. It allows a great deal of automation, by combining recursive partitioning and spline fitting in an optimal way. The algorithm finds the ideal knot positions for the splines and, thus, the best number of polynomial pieces to fit the data autonomously. With that we can correct the ICRF2 a priori coordinates for our analysis and eliminate the systematics in the position estimates. This allows us to introduce also special handling sources into the datum definition, leading to on average 30 % more sources in the datum. We find that not only the CPO can be improved by more than 10 % due to the improved geometry, but also the station positions, especially in the early years of VLBI, can benefit greatly. Numéro de notice : A2017-296 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : http://doi.org/10.1007/s00190-016-0954-1 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85331 [article]

Development and Comparison of Species Distribution Models for Forest Inventories / Óscar Rodríguez de Rivera in ISPRS International journal of geo-information, vol 6 n° 6 (June 2017)  

Public [article]  inISPRS International journal of geo-information > vol 6 n° 6 (June 2017) Titre : Development and Comparison of Species Distribution Models for Forest Inventories Type de document : Article/Communication Auteurs : Óscar Rodríguez de Rivera, Auteur ; Antonio López-Quílez, Auteur Année de publication : 2017 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] analyse de données [Termes descripteurs IGN] arbre (flore) [Termes descripteurs IGN] classification et arbre de régression [Termes descripteurs IGN] distribution spatiale [Termes descripteurs IGN] entropie maximale [Termes descripteurs IGN] inventaire forestier (techniques et méthodes) [Termes descripteurs IGN] modèle mathématique [Termes descripteurs IGN] régression multivariée par spline adaptative [Vedettes matières IGN] Inventaire forestier Résumé : (auteur) A comparison of several statistical techniques common in species distribution modeling was developed during this study to evaluate and obtain the statistical model most accurate to predict the distribution of different forest tree species (in our case presence/absence data) according environmental variables. During the process we have developed maximum entropy (MaxEnt), classification and regression trees (CART), multivariate adaptive regression splines (MARS), showing the statistical basis of each model and, at the same time, we have developed a specific additive model to compare and validate their capability. To compare different results, the area under the receiver operating characteristic (ROC) function (AUC) was used. Every AUC value obtained with those models is significant and all of the models could be useful to represent the distribution of each species. Moreover, the additive model with thin plate splines gave the best results. The worst capability was obtained with MARS. This model’s performance was below average for several species. The additive model developed obtained better results because it allowed for changes and calibrations. In this case we were aware of all of the processes that occurred during the modeling. By contrast, models obtained using specific software, in general, perform like “hermetic machines”, because it could sometimes be impossible to understand the stages that led to the final results. Numéro de notice : A2017-810 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi6060176 En ligne : https://doi.org/10.3390/ijgi6060176 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89250 [article]

Evaluating EO1-Hyperion capability for mapping conifer and broadleaved forests / Nicola Puletti in European journal of remote sensing, vol 49 (2016)  

Public [article]  inEuropean journal of remote sensing > vol 49 (2016) . - pp 157 - 169 Titre : Evaluating EO1-Hyperion capability for mapping conifer and broadleaved forests Type de document : Article/Communication Auteurs : Nicola Puletti, Auteur ; Nicola Camarretta, Auteur ; Piermaria Corona, Auteur Année de publication : 2016 Article en page(s) : pp 157 - 169 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] feuillu [Termes descripteurs IGN] forêt [Termes descripteurs IGN] image EO1-Hyperion [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] matrice de confusion [Termes descripteurs IGN] pinophyta [Termes descripteurs IGN] régression multivariée par spline adaptative Résumé : (auteur) The objective of the present study is the comparison of the combined use of Earth Observation-1 (EO-1) Hyperion Hyperspectral images with the Random Forest (RF), Support Vector Machines (SVM) and Multivariate Adaptive Regression Splines (MARS) classifiers for discriminating forest cover groups, namely broadleaved and coniferous forests. Statistics derived from classification confusion matrix were used to assess the accuracy of the derived thematic maps. We demonstrated that Hyperion data can be effectively used to obtain rapid and accurate large-scale mapping of main forest types (conifers-broadleaved). We also verified higher capability of Hyperion imagery with respect to Landsat data to such an end. Results demonstrate the ability of the three tested classification methods, with small improvements given by SVM in terms of overall accuracy and kappa statistic. Numéro de notice : A2016-832 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article En ligne : http://dx.doi.org/10.5721/EuJRS20164909 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82716 [article]

Statistical learning from a regression perspective / Richard A. Berk (2016)  

Public Titre : Statistical learning from a regression perspective Type de document : Monographie Auteurs : Richard A. Berk, Auteur Editeur : Springer International Publishing Année de publication : 2016 ISBN/ISSN/EAN : 978-3-319-44048-4 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes descripteurs IGN] analyse de données [Termes descripteurs IGN] arbre aléatoire [Termes descripteurs IGN] bagging [Termes descripteurs IGN] classification et arbre de régression [Termes descripteurs IGN] régression [Termes descripteurs IGN] régression multivariée par spline adaptative [Termes descripteurs IGN] régression quantile [Termes descripteurs IGN] séparateur à vaste marge Résumé : (éditeur) This textbook considers statistical learning applications when interest centers on the conditional distribution of the response variable, given a set of predictors, and when it is important to characterize how the predictors are related to the response. As a first approximation, this can be seen as an extension of nonparametric regression. This fully revised new edition includes important developments over the past 8 years. Consistent with modern data analytics, it emphasizes that a proper statistical learning data analysis derives from sound data collection, intelligent data management, appropriate statistical procedures, and an accessible interpretation of results. A continued emphasis on the implications for practice runs through the text. Among the statistical learning procedures examined are bagging, random forests, boosting, support vector machines and neural networks. Response variables may be quantitative or categorical. As in the first edition, a unifying theme is supervised learning that can be treated as a form of regression analysis. Key concepts and procedures are illustrated with real applications, especially those with practical implications. A principal instance is the need to explicitly take into account asymmetric costs in the fitting process. For example, in some situations false positives may be far less costly than false negatives. Also provided is helpful craft lore such as not automatically ceding data analysis decisions to a fitting algorithm. In many settings, subject-matter knowledge should trump formal fitting criteria. Yet another important message is to appreciate the limitation of one’s data and not apply statistical learning procedures that require more than the data can provide. The material is written for upper undergraduate level and graduate students in the social and life sciences and for researchers who want to apply statistical learning procedures to scientific and policy problems. The author uses this book in a course on modern regression for the social, behavioral, and biological sciences. Intuitive explanations and visual representations are prominent. All of the analyses included are done in R with code routinely provided. Note de contenu : 1- Statistical Learning as a Regression Problem 2- Splines, Smoothers, and Kernels 3- Classification and Regression Trees (CART) 4- Bagging 5- Random Forests 6- Boosting 7- Support Vector Machines 8- Some Other Procedures Briefly 9- Broader Implications and a Bit of Craft Lore Numéro de notice : 25800 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Monographie DOI : 10.1007/978-3-319-44048-4 En ligne : https://doi.org/10.1007/978-3-319-44048-4 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95043