Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Comparative perspective of studies integrating landslide susceptibility and social vulnerability.

More »

Table 1 Expand

Table 2.

General characteristics of landslide susceptibility models.

More »

Table 2 Expand

Table 3.

Common copula families and their bivariate properties.

More »

Table 3 Expand

Table 4.

Spatial and social input variables used in the landslide susceptibility analysis.

More »

Table 4 Expand

Fig 1.

Inputs used in the estimation of the landslide susceptibility map.

Inputs include DEM, aspect, roughness, land cover, tau DEM and landslide mask.

More »

Fig 1 Expand

Fig 2.

Model information flow.

The diagram show how inputs are transformed into landslide susceptibility maps through several algorithms, evaluated, and subsequently associated with socioeconomic variables.

More »

Fig 2 Expand

Fig 3.

Correlation matrix for every causative factor.

More »

Fig 3 Expand

Table 5.

Model performance based on AUC values and sensitivity to multicollinearity.

More »

Table 5 Expand

Fig 4.

AUC and ROC plots for every tested model.

This matrix plot shows every AUC and ROC for easy comparison purposes.

More »

Fig 4 Expand

Fig 5.

Landslide susceptibility maps created by each tested model.

Matrix plot allows for quick comparison between susceptibility maps.

More »

Fig 5 Expand

Fig 6.

Raw susceptibility map generated with XGBoost.

Full high-resolution susceptibility map of the champion model.

More »

Fig 6 Expand

Fig 7.

Uncertainty quantification plots.

Maximum and minimum plots per areal unit as uncertainty quantification method, to portray the whole range of values that may arise.

More »

Fig 7 Expand

Fig 8.

Categorized susceptibility map.

Susceptibility values categorized to create a simpler-to-read map.

More »

Fig 8 Expand

Table 6.

Classification of landslide susceptibility values into categorical classes.

More »

Table 6 Expand

Fig 9.

CENAPRED official susceptibility map.

Notice that CENAPRED categorization values do not necessarily coincide with our methodology, since we intend to highlight different zones. This implies that the range and scope of our categorical map may differ from that of CENAPRED, yet this map is presented for transparency purposes.

More »

Fig 9 Expand

Fig 10.

Feature importance plots.

Feature importance, Importance gain, and Geodetector ranks features according to their importance.

More »

Fig 10 Expand

Fig 11.

Combined landslide susceptibility plots.

Susceptibility tends to increase to the west, therefore, as it increases, the corresponding AGEBs are located to the west.

More »

Fig 11 Expand

Fig 12.

SLI vs landslide susceptibility.

Social lag index plotted against different landslide susceptibility values.

More »

Fig 12 Expand

Fig 13.

Full dataset SHAP plot.

Beeswarm plot for the entire dataset.

More »

Fig 13 Expand

Table 7.

Copula model performance based on log-likelihood and association.

More »

Table 7 Expand

Table 8.

Segment-wise model performance and SHAP-based importance of the Social Lag Index (SLI).

More »

Table 8 Expand

Fig 14.

SHAP plots for changepoint-induced partitions.

Beeswarm plot using changepoint induced partitioning.

More »

Fig 14 Expand

Table 9.

Segment-wise copula model selection based on log-likelihood.

More »

Table 9 Expand

Table 10.

R2 and permutation importance by decile.

More »

Table 10 Expand

Fig 15.

SHAP plots for decile-induced partitions.

Beeswarm plot for each of the 10 partitions generated.

More »

Fig 15 Expand

Table 11.

Decile-wise copula model selection based on log-likelihood and dependence.

More »

Table 11 Expand

Fig 16.

Individual variable boxplots.

Boxplots portray first quartile, median, third quartile, and outlier data.

More »

Fig 16 Expand

Fig 17.

Individual variable barplot.

Barplots shows the mean for each considered variable as separated by susceptibility class.

More »

Fig 17 Expand

Table 12.

Feature importances from XGBoost model.

More »

Table 12 Expand

Fig 18.

SHAP plots for each variable that was used to construct the Social Lag Index.

Beeswarm plots showing potential association for individual social variables.

More »

Fig 18 Expand

Table 13.

Copula fit per variable (variable IDs from master list).

More »

Table 13 Expand