Coupling logistic model tree and random subspace to predict the landslide susceptibility areas with considering the uncertainty of environmental features
Rattachement africain : cn. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
Landslide disasters cause huge casualties and economic losses every year, how to accurately forecast the landslides has always been an important issue in geo-environment research. In this paper, a hybrid machine learning approach RSLMT is firstly proposed by coupling Random Subspace (RS) and Logistic Model Tree (LMT) for producing a landslide susceptibility map (LSM). With this method, the uncertainty introduced by input features is considered, the problem of overfitting is solved by reducing dimensions to increase the prediction rate of landslide occurrence. Moreover, the uncertainty of prediction will be deeply discussed with the rank probability score (RPS) series, which is an important evaluation of uncertainty but rarely used in LSM. Qingchuan county, China was taken as a study area. 12 landslide causal factors were selected and their contribution on landslide occurrence was evaluated by ReliefF method. In addition, Logistic Model Tree (LMT), Naive Bayes (NB) and Logistic Regression (LR) were researched for comparison. The results showed that RSLMT (AUC = 0.815) outperformed LMT (AUC = 0.805), NB (AUC = 0.771), LR (AUC = 0.785). LSM of Qingchuan county was produced using the novel model, it indicated that landslides tend to occur along with the fault belts and the middle-low mountain area that is strongly influenced by the large numbers of human engineering activities.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Coupling logistic model tree and random subspace to predict the landslide susceptibility areas with considering the uncertainty of environmental features
- Date Crossref
- 25/10/2019
- Éditeur
- Springer Science and Business Media LLC
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
China University of Geosciences pays non établi dans la noticeUniversité ou école supérieure
-
Chinese Academy of Geological Sciences pays non établi dans la noticeStructure de recherche
-
China Geological Survey pays non établi dans la noticeInstitution
-
School of Geography and Information Engineering pays non établi dans la noticeUniversité ou école supérieure
-
Class 3 Grade3 pays non établi dans la noticeInstitution
-
Institute of Hydrogeology and Environmental Geology pays non établi dans la noticeStructure de recherche
-
China Institute of Geo-Environment Monitoring pays non établi dans la noticeStructure de recherche
China University of Geosciences, Chinese Academy of Geological Sciences et China Geological Survey, avec 4 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.