A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
GIS-based logistic regression for rainfall-induced landslide susceptibility mapping under different grid sizes in Yueqing, Southeastern China
https://orcid.org/0000-0003-0453-1960
https://orcid.org/0000-0003-2336-5443
Abstract The logistic regression (LR) method was applied to assess landslide susceptibility in the northern Yueqing of Zhejiang Province, China. An inventory map of 323 landslides, digital elevation models (DEMs), remote sensing images, geological map, roads and rivers were collected and utilized in the analysis. LR models using partially continuous (LR-CON) and all categorized variables (LR-CAT) were carried out under different grid sizes of 5 m, 15 m and 30 m to investigate the influence of variable type and grid size on landslide susceptibility assessment. Ten different subsets of positive (landslide) and negative (non-landslide) cases were prepared for each kind of LR models. Receiver operation characteristic (ROC) curves were employed to evaluate the performance of the LR models while cross-validation was used to validate the effectiveness of susceptibility maps. The models with and without the rainfall factor were also compared. Among the three grid sizes, the result of 15 m shows the best performance with mean AUC (the area under a ROC curve) of 82.6%. The AUC values of LR-CON models with different grid sizes all demonstrated acceptable fit (0.7 < mean AUC <0.8) while those of LR-CAT models showed an excellent fit (mean AUC > 0.8), indicating that LR method has a better performance when using all categorical variables than using partially continuous variables. Random sampling is an adoptable method to generate training group and there is no significant difference of AUC values among different data subsets. The results also showed that the accuracy of the landslide susceptibility models is higher when rainfall is included in the analyses.
Highlights Landslide susceptibility under different grid sizes was assessed and compared. Several criteria are discussed to choose a proper grid size. Mean annual rainfall was an effective factor for improving assessment. Ten random samples were selected for cross-validation. Variable types has a significant influence on the accuracy of assessment.
GIS-based logistic regression for rainfall-induced landslide susceptibility mapping under different grid sizes in Yueqing, Southeastern China
https://orcid.org/0000-0003-0453-1960
https://orcid.org/0000-0003-2336-5443
Abstract The logistic regression (LR) method was applied to assess landslide susceptibility in the northern Yueqing of Zhejiang Province, China. An inventory map of 323 landslides, digital elevation models (DEMs), remote sensing images, geological map, roads and rivers were collected and utilized in the analysis. LR models using partially continuous (LR-CON) and all categorized variables (LR-CAT) were carried out under different grid sizes of 5 m, 15 m and 30 m to investigate the influence of variable type and grid size on landslide susceptibility assessment. Ten different subsets of positive (landslide) and negative (non-landslide) cases were prepared for each kind of LR models. Receiver operation characteristic (ROC) curves were employed to evaluate the performance of the LR models while cross-validation was used to validate the effectiveness of susceptibility maps. The models with and without the rainfall factor were also compared. Among the three grid sizes, the result of 15 m shows the best performance with mean AUC (the area under a ROC curve) of 82.6%. The AUC values of LR-CON models with different grid sizes all demonstrated acceptable fit (0.7 < mean AUC <0.8) while those of LR-CAT models showed an excellent fit (mean AUC > 0.8), indicating that LR method has a better performance when using all categorical variables than using partially continuous variables. Random sampling is an adoptable method to generate training group and there is no significant difference of AUC values among different data subsets. The results also showed that the accuracy of the landslide susceptibility models is higher when rainfall is included in the analyses.
Highlights Landslide susceptibility under different grid sizes was assessed and compared. Several criteria are discussed to choose a proper grid size. Mean annual rainfall was an effective factor for improving assessment. Ten random samples were selected for cross-validation. Variable types has a significant influence on the accuracy of assessment.
GIS-based logistic regression for rainfall-induced landslide susceptibility mapping under different grid sizes in Yueqing, Southeastern China
https://orcid.org/0000-0003-0453-1960
https://orcid.org/0000-0003-2336-5443
Abstract The logistic regression (LR) method was applied to assess landslide susceptibility in the northern Yueqing of Zhejiang Province, China. An inventory map of 323 landslides, digital elevation models (DEMs), remote sensing images, geological map, roads and rivers were collected and utilized in the analysis. LR models using partially continuous (LR-CON) and all categorized variables (LR-CAT) were carried out under different grid sizes of 5 m, 15 m and 30 m to investigate the influence of variable type and grid size on landslide susceptibility assessment. Ten different subsets of positive (landslide) and negative (non-landslide) cases were prepared for each kind of LR models. Receiver operation characteristic (ROC) curves were employed to evaluate the performance of the LR models while cross-validation was used to validate the effectiveness of susceptibility maps. The models with and without the rainfall factor were also compared. Among the three grid sizes, the result of 15 m shows the best performance with mean AUC (the area under a ROC curve) of 82.6%. The AUC values of LR-CON models with different grid sizes all demonstrated acceptable fit (0.7 < mean AUC <0.8) while those of LR-CAT models showed an excellent fit (mean AUC > 0.8), indicating that LR method has a better performance when using all categorical variables than using partially continuous variables. Random sampling is an adoptable method to generate training group and there is no significant difference of AUC values among different data subsets. The results also showed that the accuracy of the landslide susceptibility models is higher when rainfall is included in the analyses.
Highlights Landslide susceptibility under different grid sizes was assessed and compared. Several criteria are discussed to choose a proper grid size. Mean annual rainfall was an effective factor for improving assessment. Ten random samples were selected for cross-validation. Variable types has a significant influence on the accuracy of assessment.
GIS-based logistic regression for rainfall-induced landslide susceptibility mapping under different grid sizes in Yueqing, Southeastern China
Zhao, Yu (author) / Wang, Rui (author) / Jiang, Yuanjun (author) / Liu, Huajun (author) / Wei, Zhenlei (author)
Engineering Geology ; 259
2019-05-16
Article (Journal)
Electronic Resource
English
Rainfall-Induced Landslide Susceptibility Using a Rainfall–Runoff Model and Logistic Regression
| DOAJ | 2018
Presenting logistic regression-based landslide susceptibility results
| British Library Online Contents | 2018
| British Library Online Contents | 2014