The quality of digital elevation models (DEMs), as well as their spatial resolution, are important issues in geomorphic studies. However, their influence on landslide susceptibility mapping (LSM) remains poorly constrained. This work determined the scale dependency of DEM-derived geomorphometric factors in LSM using a 5 m LiDAR DEM, LiDAR resampled 30 m DEM, and a 30 m ASTER DEM. To verify the validity of our approach, we first compiled an inventory map comprising of 267 landslides for Sihjhong watershed, Taiwan, from 2004 to 2014. Twelve landslide causative factors were then generated from the DEMs and ancillary data. Afterward, popular statistical and machine learning techniques, namely, logistic regression (LR), random forest (RF), and support vector machine (SVM) were implemented to produce the LSM. The accuracies of models were evaluated by overall accuracy, kappa index and the receiver operating characteristic curve indicators. The highest accuracy was attained from the resampled 30 m LiDAR DEM derivatives, indicating a fine-resolution topographic data does not necessarily achieve the best performance. Additionally, RF attained superior performance between the three presented models. Our findings could contribute to opt for an appropriate DEM resolution for mapping landslide hazard in vulnerable areas.

Landslide risk prevention requires the delineation of landslide-prone areas as accurately as possible. Therefore, selecting a method or a technique that is capable of providing the highest landslide prediction capability is highly important. The main objective of this study is to assess and compare the prediction capability of advanced machine learning methods for landslide susceptibility mapping in the Mila Basin (Algeria). First, a geospatial database was constructed from various sources. The database contains 1156 landslide polygons and 16 conditioning factors (altitude, slope, aspect, topographic wetness index (TWI), landforms, rainfall, lithology, stratigraphy, soil type, soil texture, landuse, depth to bedrock, bulk density, distance to faults, distance to hydrographic network, and distance to road networks). Subsequently, the database was randomly resampled into training sets and validation sets using 5 times repeated 10 k-folds cross-validations. Using the training and validation sets, five landslide susceptibility models were constructed, assessed, and compared using Random Forest (RF), Gradient Boosting Machine (GBM), Logistic Regression (LR), Artificial Neural Network (NNET), and Support Vector Machine (SVM). The prediction capability of the five landslide models was assessed and compared using the receiver operating characteristic (ROC) curve, the area under the ROC curves (AUC), overall accuracy (Acc), and kappa index. Additionally, Wilcoxon signed-rank tests were performed to confirm statistical significance in the differences among the five machine learning models employed in this study. The result showed that the GBM model has the highest prediction capability (AUC = 0.8967), followed by the RF model (AUC = 0.8957), the NNET model (AUC = 0.8882), the SVM model (AUC = 0.8818), and the LR model (AUC = 0.8575). Therefore, we concluded that GBM and RF are the most suitable for this study area and should be used to produce landslide susceptibility maps. These maps as a technical framework are used to develop countermeasures and regulatory policies to minimize landslide damages in the Mila Basin. This research demonstrated the benefit of selecting the best-advanced machine learning method for landslide susceptibility assessment.