Centre dedocumentation
scientifique

Knowledge-guided consistent correlation analysis of multimode landslide monitoring data / Shuangxi Miao in International journal of geographical information science IJGIS, vol 31 n° 11-12 (November - December 2017)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 31 n° 11-12 (November - December 2017) . - pp 2255 - 2271 Titre : Knowledge-guided consistent correlation analysis of multimode landslide monitoring data Type de document : Article/Communication Auteurs : Shuangxi Miao, Auteur ; Qing Zhu, Auteur ; Bo Zhang, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 2255 - 2271 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] analyse spatio-temporelle [Termes descripteurs IGN] base de connaissances [Termes descripteurs IGN] Chensi (Chine) [Termes descripteurs IGN] corrélation [Termes descripteurs IGN] données multisources [Termes descripteurs IGN] effondrement de terrain [Termes descripteurs IGN] regroupement de données [Termes descripteurs IGN] structure géologique [Termes descripteurs IGN] surveillance géologique Résumé : (Auteur) A novel method called knowledge-guided spatio-temporal consistent correlation analysis (KSTCCA) was developed to discover reliable deformation features induced by multiple factors based on multimode landslide monitoring data. Compared to conventional approaches, KSTCCA integrates both temporal and spatial correlation analysis to improve the consistency of deformation patterns and capture the spatio-temporal heterogeneities in multimode monitoring data. KSTCCA considers both the landslide deformation mechanisms and the relationships between different influential factors as knowledge. Moreover, the method extracts the morphological structures of monitoring curves based on a seven-point approach and identifies knowledge rules using the k-means clustering method. Under the guidance of prior knowledge, a spatial correlation analysis is conducted based on support vector regression, and a temporal correlation analysis of the time lag is carried out based on the morphological structure features. Finally, three kinds of typical monitoring data, including deformation, rainfall, and reservoir water level data collected in the Baishuihe landslide area, China, are used for experimental analysis to verify the validity of the proposed method. Numéro de notice : A2017-700 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2017.1356461 En ligne : https://doi.org/10.1080/13658816.2017.1356461 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88081 [article]

Réservation

Réserver ce document

Exemplaires (2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2017061	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
079-2017062	RAB	Revue	Centre de documentation	En réserve 3L	Disponible

An automated approach for updating land cover maps based on integrated change detection and classification methods / X. Chen in ISPRS Journal of photogrammetry and remote sensing, vol 71 (July 2012)

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 71 (July 2012) . - pp 86 - 95 Titre : An automated approach for updating land cover maps based on integrated change detection and classification methods Type de document : Article/Communication Auteurs : X. Chen, Auteur ; J. Chen, Auteur ; Y. Shi, Auteur ; Yasushi Yamaguchi, Auteur Année de publication : 2012 Article en page(s) : pp 86 - 95 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] carte d'occupation du sol [Termes descripteurs IGN] champ aléatoire de Markov [Termes descripteurs IGN] Chensi (Chine) [Termes descripteurs IGN] détection de changement [Termes descripteurs IGN] image Landsat-ETM+ [Termes descripteurs IGN] ITERATED TRAINING SAMPLE SELECTING [Termes descripteurs IGN] mise à jour de base de données Résumé : (Auteur) Updating land cover maps from remotely sensed data in a timely manner is important for many areas of scientific research. Unfortunately, traditional classification procedures are very labor intensive and subjective because of the required human interaction. Based on the strategy of updating land cover data only for the changed area, we proposed an integrated, automated approach to update land cover maps without human interaction. The proposed method consists primarily of the following three parts: a change detection technique, a Markov Random Fields (MRFs) model, and an iterated training sample selecting procedure. In the proposed approach, remotely sensed data acquired in different seasons or from different remote sensors can be used. Meanwhile, the approach is completely unsupervised. Therefore, the methodology has a wide scope of application. A case study of Landsat data was conducted to test the performance of this method. The experimental results show that several sub-modules in this method work effectively and that reasonable classification accuracy can be achieved. Numéro de notice : A2012-350 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31796 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2012051	SL	Revue	Centre de documentation	Revues en salle	Disponible

Evaluation of land use and cover changes in North Shaanxi, China / W. Wu in Photo interprétation, vol 39 n° 2 (Juin 2003)

Public [article]  inPhoto interprétation > vol 39 n° 2 (Juin 2003) . - pp 15 - 29 Titre : Evaluation of land use and cover changes in North Shaanxi, China Type de document : Article/Communication Auteurs : W. Wu, Auteur Année de publication : 2003 Article en page(s) : pp 15 - 29 Langues : Anglais (eng) Français (fre) Descripteur : [Vedettes matières IGN] Photo-interprétation [Termes descripteurs IGN] analyse diachronique [Termes descripteurs IGN] Chensi (Chine) [Termes descripteurs IGN] classification [Termes descripteurs IGN] désertification [Termes descripteurs IGN] environnement [Termes descripteurs IGN] géographie humaine [Termes descripteurs IGN] image Landsat-TM [Termes descripteurs IGN] image multitemporelle [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] surface cultivée Résumé : (Auteur) As a transitional belt between the Mu Us Sandy Land and Loess Plateau, the north part of Shaanxi is one of the ecologically vulnerable and areas in northwest China, which are subject to the impacts of both natural factors and human activity. It is therefore of special importance to select such an area to carry out an intensive land use change study and establish a dynamic monitoring system thereof aiming at understanding the change mechanism, human-environmental relationships and producing useful references for the central and local governments in their sustainable land use planning. Multitemporal Landsat images were used for change detection by adopting a synthetic method including atmospheric correction, Tasseled Cap transformation, indicator differencing, thresholding, change type identification and county-level quantification. A classification on the recent image was conducted to quantify the present land use and cover pattern. A panel analysis calibrated by multivariate regression model was applied to reveal the driving forces of land cover changes and understand the interaction between the human activities and environment modifications by incorporating the results obtained from the change detection with the county-level socio-economic data. The regression modelling results suggest that the vegetation degradation- the predominant change type in the study area, is probably related to the soil erosion (R' = 0.994) and grassland degradation; the farmland extension, occurring principally in the valleys in the Yulin County, is associated with the foodproduct increase (R' = 0.987); the urban extension, spatially related to coal mining, is linked to the urban population growth (R' = 0. 881); and the surface decrease of waterbodies, having taken place in the sandy land, is negatively correlated to the cultivated land change (R' = 0. 562). Therefore, the factors which govern these land use and cover changes are various human socio-economic activities, and the root cause of land degradation is, however, some unreasonable land use policies. Numéro de notice : A2003-392 Thématique : IMAGERIE Nature : Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26472 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
104-03021	RAB	Revue	Centre de documentation	Revues en salle	Disponible