Filtering is one of the core post-processing steps for airborne LiDAR point cloud. In recent years, the morphology-based filtering algorithms have proven to be a powerful and efficient tool for filtering airborne LiDAR point cloud. However, most traditional morphology-based algorithms have difficulties in preserving abrupt terrain features, especially when using larger filtering windows. In order to suppress the omission error caused by protruding terrain features, this paper proposes an improved morphological algorithm based on multi-level kriging interpolation. This algorithm is essentially a combination of progressive morphological filtering algorithm and multi-level interpolation filtering algorithm. The morphological opening operation is performed with filtering window gradually downsizing, while kriging interpolation is conducted at different levels according to the different filtering windows. This process is iterative in a top to down fashion until the filtering window is no longer greater than the preset minimum filtering window. Fifteen samples provided by the ISPRS commission were chosen to test the performance of the proposed algorithm. Experimental results show that the proposed method can achieve promising results not only in flat urban areas but also in rural areas. Comparing with other eight classical filtering methods, the proposed method obtained the lowest omission error, and preserved protruding terrain features better.

This study introduces four rock–soil characteristics factors, that is, Lithology, Rock Structure, Rock Infiltration, and Rock Weathering, which based on the properties of rock formations, to predict Landslide Susceptibility Mapping (LSM) in Three Gorges Reservoir Area from Zigui to Badong. Logistic regression, artificial neural network, support vector machine is used in LSM modeling. The study consists of three main steps. In the first step, these four factors are combined with the 11 basic factors to form different factor combinations. The second step randomly selects training (70% of the total) and validation (30%) datasets out of grid cells corresponding to landslide and non-landslide locations in the study area. The final step constructs the LSM models to obtain different landslide susceptibility index maps and landslide susceptibility zoning maps. The specific category precision, receiver operating characteristic curve, and 5 other statistical evaluation methods are used for quantitative evaluations. The evaluation results show that, in most cases, the result based on Rock Structure are better than the result obtained by traditional method based on Lithology, have the best performance. To further study the influence of rock–soil characteristic factors on the LSM, these four factors are divided into “Intrinsic attribute factors” and “External participation factors” in accordance with the participation of external factors, to generate the LSMs. The evaluation results show that the result based on Intrinsic attribute factors are better than the result based on External participation factors, indicating the significance of Intrinsic attribute factors in LSM. The method proposed in this study can effectively improve the scientificity, accuracy, and validity of LSM.

In this study, a novel coupling model for landslide susceptibility mapping is presented. In practice, environmental factors may have different impacts at a local scale in study areas. To provide better predictions, a geographically weighted regression (GWR) technique is firstly used in our method to segment study areas into a series of prediction regions with appropriate sizes. Meanwhile, a support vector machine (SVM) classifier is exploited in each prediction region for landslide susceptibility mapping. To further improve the prediction performance, the particle swarm optimization (PSO) algorithm is used in the prediction regions to obtain optimal parameters for the SVM classifier. To evaluate the prediction performance of our model, several SVM-based prediction models are utilized for comparison on a study area of the Wanzhou district in the Three Gorges Reservoir. Experimental results, based on three objective quantitative measures and visual qualitative evaluation, indicate that our model can achieve better prediction accuracies and is more effective for landslide susceptibility mapping. For instance, our model can achieve an overall prediction accuracy of 91.10%, which is 7.8%–19.1% higher than the traditional SVM-based models. In addition, the obtained landslide susceptibility map by our model can demonstrate an intensive correlation between the classified very high-susceptibility zone and the previously investigated landslides.

The Zigui–Badong section of the Three Gorges Reservoir area is used as the research area in this study to research the impact of unbalanced sample sets on Landslide Susceptibility Mapping (LSM) and determine the sample ratio interval with the best performance for different models. We employ 12 LSM factors, five training sample sets with different sample ratios (1:1, 1:2, 1:4, 1:8, and 1:16), and C5.0, Support Vector Machine (SVM), Logistic Regression (LR), and one-dimensional Convolution Neural Network (CNN) models are used to obtain landslide susceptibility index and landslide susceptibility zoning in the study area, respectively. The prediction performance of the model is evaluated by the receiver operating characteristic curve area under the curve value, five statistical methods, and specific category precision. The results show that the CNN, SVM, and LR models in the sample ratio of 1:2 achieve better performance than on the balanced sample set, which indicates the importance of the unbalanced sample set in training the LSM modeling. The C5.0 model is always in a state of overfitting in this study and needs to be further studied. The conclusions put forward in this study help improve the scientificity and reliability of LSM.

Landslides, recognized as a significant global natural disaster, necessitate an exploration of the impact of various resolution types in sampling strategies on Landslide Susceptibility Mapping (LSM) results. This study focuses on the segment from Zigui to Badong within the Three Gorges Reservoir Area, utilizing two resolution types: sampling resolution and spatial resolution, The Support Vector Machine (SVM) is employed to obtain LSM results, which are then analyzed using Receiver Operating Characteristic (ROC) curve, specific category accuracy and statistical methods. Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) were used to verify the reliability of the results. Additionally, five common machine learning models, including Logistic Regression (LR), are used to conduct experiments on four sampling resolutions (10 m,30 m,50 m and 70 m) to further investigate the effect of sampling resolution on LSM results. These are evaluated using a comprehensive quantitative method. The results reveal that increasing spatial resolution improves the prediction accuracy, while increasing sampling resolution produces a contrary effect. Furthermore, the impact of spatial resolution on LSM results is more pronounced than that of sampling resolution. Finally, Fanjiaping landslide and Huangtupo landslide are selected as references for comparative analysis, with the results aligning with engineering reality.

China experiences frequent landslides, and therefore there is a need for landslide susceptibility maps (LSMs) to effectively analyze and predict regional landslides. However, the traditional methods of producing an LSM are unable to account for different spatial scales, resulting in spatial imbalances. In this study, Zigui-Badong in the Three Gorges Reservoir Area was used as a case study, and data was obtained from remote sensing images, digital elevation model, geological and topographic maps, and landslide surveys. A geographic weighted regression (GWR) was applied to segment the study area into different spatial scales, with three basic principles followed when the GWR model was applied for this propose. As a result, 58 environmental factors were extracted, and 18 factors were selected as LSM factors. Three of the most important factors (channel network basic level, elevation, and distance to river) were used as segmentation factors to segment the study area into 18 prediction regions. The particle swarm optimization (PSO) algorithm was used to optimize the parameters of a support vector machine (SVM) model for each prediction region. All of the prediction regions were merged to construct a GWR-PSO-SVM coupled model and finally, an LSM of the study area was produced. To verify the effectiveness of the proposed method, the outcomes of the GWR-PSO-SVM coupled model and the PSO-SVM coupled model were compared using three evaluation methods: specific category accuracy analysis, overall prediction accuracy analysis, and area under the curve analysis. The results for the GWR-PSO-SVM coupled model for these three evaluation methods were 85.75%, 87.86%, and 0.965, respectively, while the results for the traditional PSO-SVM coupled model were 68.35%, 84.44%, and 0.944, respectively. The method proposed in this study based on a spatial scale segmentation therefore acquired good results.