Comparing probabilistic and statistical methods in landslide susceptibility modeling in Rwanda/Centre-Eastern Africa

Assessing Landslide Susceptibility by Coupling Spatial Data Analysis and Logistic Model

Landslides represent one of the most critical issues for landscape managers. They can cause injuries and loss of human life and damage properties and infrastructure. The spatial and temporal distribution of these detrimental events makes them almost unpredictable. Studies on landslide susceptibility assessment can significantly contribute to prioritizing critical risk zones. Further, landslide prevention and mitigation and the relative importance of the affecting drivers acquire even more significance in areas characterized by seismicity. This study aimed to investigate the relationship between a set of environmental variables and the occurrence of landslide events in an area of the Apulia Region (Italy). Logistic regression was applied to a landslide-prone area in the Apulia Region (Italy) to identify the main causative factors using a large dataset of environmental predictors (47). The results of this case study show that the logistic regression achieved a good performance, with an AUC (Area Under Curve) >70%. Therefore, the model developed would be a useful tool to define and assess areas for landslide occurrence and contribute to implementing risk mitigation strategy and land use policy.

Performance Evaluation of GIS-Based Artificial Intelligence Approaches for Landslide Susceptibility Modeling and Spatial Patterns Analysis

The main purpose of this study was to apply the novel bivariate weights-of-evidence-based SysFor (SF) for landslide susceptibility mapping, and two machine learning techniques, namely the naïve Bayes (NB) and Radial basis function networks (RBFNetwork), as benchmark models. Firstly, by using aerial photos and geological field surveys, the 263 landslide locations in the study area were obtained. Next, the identified landslides were randomly classified according to the ratio of 70/30 to construct training data and validation models, respectively. Secondly, based on the landslide inventory map, combined with the geological and geomorphological characteristics of the study area, 14 affecting factors of the landslide were determined. The predictive ability of the selected factors was evaluated using the LSVM model. Using the WoE model, the relationship between landslides and affecting factors was analyzed by positive and negative correlation methods. The above three hybrid models were then used to map landslide susceptibility. Thirdly, the ROC curve and various statistical data (SE, 95% CI and MAE) were used to verify and compare the predictive power of the model. Compared with the other two models, the Sysfor model had a larger area under the curve (AUC) of 0.876 (training dataset) and 0.783 (validation dataset). Finally, by quantitatively comparing the susceptibility values of each pixel, the differences in spatial morphology of landslide susceptibility maps were compared, and the model was found to have limitations and effectiveness. The landslide susceptibility maps obtained by the three models are reasonable, and the landslide susceptibility maps generated by the SysFor model have the highest comprehensive performance. The results obtained in this paper can help local governments in land use planning, disaster reduction and environmental protection.

Landslide Susceptibility Mapping Using the Stacking Ensemble Machine Learning Method in Lushui, Southwest China

Landslide susceptibility mapping is considered to be a prerequisite for landslide prevention and mitigation. However, delineating the spatial occurrence pattern of the landslide remains a challenge. This study investigates the potential application of the stacking ensemble learning technique for landslide susceptibility assessment. In particular, support vector machine (SVM), artificial neural network (ANN), logical regression (LR), and naive Bayes (NB) were selected as base learners for the stacking ensemble method. The resampling scheme and Pearson’s correlation analysis were jointly used to evaluate the importance level of these base learners. A total of 388 landslides and 12 conditioning factors in the Lushui area (Southwest China) were used as the dataset to develop landslide modeling. The landslides were randomly separated into two parts, with 70% used for model training and 30% used for model validation. The models’ performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) and statistical measures. The results showed that the stacking-based ensemble model achieved an improved predictive accuracy as compared to the single algorithms, while the SVM-ANN-NB-LR (SANL) model, the SVM-ANN-NB (SAN) model, and the ANN-NB-LR (ANL) models performed equally well, with AUC values of 0.931, 0.940, and 0.932, respectively, for validation stage. The correlation coefficient between the LR and SVM was the highest for all resampling rounds, with a value of 0.72 on average. This connotes that LR and SVM played an almost equal role when the ensemble of SANL was applied for landslide susceptibility analysis. Therefore, it is feasible to use the SAN model or the ANL model for the study area. The finding from this study suggests that the stacking ensemble machine learning method is promising for landslide susceptibility mapping in the Lushui area and is capable of targeting areas prone to landslides.

Land Use Change Impacts on Water Erosion in Rwanda

Rwanda has experienced accelerated soil erosion as a result of unsustainable human activities and changes in land use. Therefore, this study aimed at applying the RUSLE (Revised Universal Soil Loss Equation) model using GIS (Geographical Information System) and remote sensing to assess water erosion in Rwanda, focusing on the erosion-prone lands for the time span 2000 to 2015. The estimated mean annual soil losses were 48.6 t ha−1 y−1 and 39.2 t ha−1 y−1 in 2000 and 2015, respectively, resulting in total nationwide losses of approximately 110 and 89 million tons. Over the 15 years, 34.6% of the total area of evaluated LULC (land use/land cover) types have undergone changes. The highest mean soil loss of 91.6 t ha−1 y−1 occurred in the area changing from grassland to forestland (0.5%) while a mean soil loss of 10.0 t ha−1 y−1 was observed for grassland converting to cropland (4.4%). An attempt has been made to identify the embedded driving forces of soil erosion in Rwanda. As a result, we found that mean soil loss for Rwanda’s districts in 2015 was significantly correlated with poverty (r = 0.45, p = 0.013), increased use of chemical fertilizers (r = 0.77, p = 0.005), and especially was related to extreme poverty (r = 0.77, p = 0.000). The soil conservation scenario analysis for Rwanda’s cropland in 2015 revealed that terracing could reduce the soil loss by 24.8% (from 14.6 t ha−1 y−1 to 11.7 t ha−1 y−1). Most importantly, the study suggests that (1) terracing integrated with mulching and cover crops could effectively control water erosion while ameliorating soil quality and fertility, and (2) reforestation schemes targeting the rapid-growing tree species are therefore recommended as an important feature for erosion control in the study area.