Landslide susceptibility prediction (LSP) has been widely and effectively implemented by machine learning (ML) models based on remote sensing (RS) images and Geographic Information System (GIS). However, comparisons of the applications of ML models for LSP from the perspectives of supervised machine learning (SML) and unsupervised machine learning (USML) have not been explored. Hence, this study aims to compare the LSP performance of these SML and USML models, thus further to explore the advantages and disadvantages of these ML models and to realize a more accurate and reliable LSP result. Two representative SML models (support vector machine (SVM) and CHi-squared Automatic Interaction Detection (CHAID)) and two representative USML models (K-means and Kohonen models) are respectively used to scientifically predict the landslide susceptibility indexes, and then these prediction results are discussed. Ningdu County with 446 recorded landslides obtained through field investigations is introduced as case study. A total of 12 conditioning factors are obtained through procession of Landsat TM 8 images and high-resolution aerial images, topographical and hydrological spatial analysis of Digital Elevation Modeling in GIS software, and government reports. The area value under the curve of receiver operating features (AUC) is applied for evaluating the prediction accuracy of SML models, and the frequency ratio (FR) accuracy is then introduced to compare the remarkable prediction performance differences between SML and USML models. Overall, the receiver operation curve (ROC) results show that the AUC of the SVM is 0.892 and is slightly greater than the AUC of the CHAID model (0.872). The FR accuracy results show that the SVM model has the highest accuracy for LSP (77.80%), followed by the CHAID model (74.50%), the Kohonen model (72.8%) and the K-means model (69.7%), which indicates that the SML models can reach considerably better prediction capability than the USML models. It can be concluded that selecting recorded landslides as prior knowledge to train and test the LSP models is the key reason for the higher prediction accuracy of the SML models, while the lack of a priori knowledge and target guidance is an important reason for the low LSP accuracy of the USML models. Nevertheless, the USML models can also be used to implement LSP due to their advantages of efficient modeling processes, dimensionality reduction and strong scalability.

Land use and land cover change can increase or decrease landslide susceptibility (LS) in the mountainous areas. In the hilly and mountainous part of southwestern China, land use and land cover change (LUCC) has taken place in the last decades due to infrastructure development and rapid economic activities. This development and activities can worsen the slope susceptible to sliding due to mostly the cutting of slopes. This study, taking Zhushan Town, Xuan'en County, as the study area, aims to evaluate the influence of land use and land cover change on landslide susceptibility at a regional scale. Spatial distribution of landslides was determined in terms of visual interpretation of aerial photographs and remote sensing images, supported by field surveys. Two types of land use and land cover (LUC) maps, with a time interval covering 21 years (1992–2013), were prepared: the first was obtained by the neural net classification of images acquired in 1992 and the second by the object-oriented classification of images in 2002 and 2013. Landslide-susceptible areas were analyzed using the logistic regression model (LRM) in which six influencing factors were chosen as the landslide susceptibility indices. In addition, the hydrologic analysis method was applied to optimize the partitioning of the terrain. The results indicated that the LUCC in the region was mainly the transformation from the grassland and arable land to the forest land, which is increased by 34.3 %. An increase of 1.9 % is shown in the area where human engineering activities concentrate. The comparison of landslide susceptibility maps among different periods revealed that human engineering activities were the most important factor in increasing LS in this region. Such results emphasize the requirement of a reasonable land use planning activity process.

Although numerous models have been employed to address the issue of landslide susceptibility at regional scale, few have incorporated landslide typology into a model application. Thus, the aim of the present study is to perform landslide susceptibility zonation taking landslide classification into account using a data-driven model. The specific objective is to answer the question: how to select reasonable influencing factors for different types of landslides so that the accuracy of susceptibility assessment can be improved? The Qilihe District in Lanzhou City of northwestern China was undertaken as the test area, and a total of 12 influencing factors were set as the predictive variables. An inventory map containing 227 landslides was created first, which was divided into shallow landslides and debris flows based on the geological features, distribution, and formation mechanisms. A weighted frequency ratio model was proposed to calculate the landslide susceptibility. The weights of influencing factors were calculated by the integrated model of logistic regression and fuzzy analytical hierarchy process, whereas the rating among the classes within each factor was obtained by a frequency ratio algorithm. The landslide susceptibility index of each cell was subsequently calculated in GIS environment to create landslide susceptibility maps of different types of landslide. The analysis and assessment process were separately performed for each type of landslide, and the final landslide susceptibility map for the entire region was produced by combining them. The results showed that 73.3% of landslide pixels were classified into “very high” or “high” susceptibility zones, while “very low” or “low” susceptibility zones covered only 3.6% of landslide pixels. The accuracy of the model represented by receiver operating characteristic curve was satisfactory, with a success rate of 70.4%. When the landslide typology was not considered, the accuracy of resulted maps decreased by 1.5~5.4%.

The expansion of mountainous urban areas and road networks can influence the terrain, vegetation, and material characteristics, thereby altering the susceptibility of landslides. Understanding the relationship between human engineering activities and landslide occurrence is of great significance for both landslide prevention and land resource management. In this study, an analysis was conducted on the landslide caused by Typhoon Megi in 2016. A representative mountainous area along the eastern coast of China—characterized by urban development, deforestation, and severe road expansion—was used to analyze the spatial distribution of landslides. For this purpose, high-precision Planet optical remote sensing images were used to obtain the landslide inventory related to the Typhoon Megi event. The main innovative features are as follows: (i) the newly developed patch generating land-use simulation (PLUS) model simulated and analyzed the driving factors of land-use land-cover (LULC) from 2010 to 2060; (ii) the innovative stacking strategy combined three strong ensemble models—Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM)—to calculate the distribution of landslide susceptibility; and (iii) distance from road and LULC maps were used as short-term and long-term dynamic factors to examine the impact of human engineering activities on landslide susceptibility. The results show that the maximum expansion area of built-up land from 2010 to 2020 was 13.433 km², mainly expanding forest land and cropland land, with areas of 8.28 km² and 5.99 km², respectively. The predicted LULC map for 2060 shows a growth of 45.88 km² in the built-up land, mainly distributed around government residences in areas with relatively flat terrain and frequent socio-economic activities. The factor contribution shows that distance from road has a higher impact than LULC. The Stacking RF-XGB-LGBM model obtained the optimal AUC value of 0.915 in the landslide susceptibility analysis in 2016. Furthermore, future road network and urban expansion have intensified the probability of landslides occurring in urban areas in 2015. To our knowledge, this is the first application of the PLUS and Stacking RF-XGB-LGBM models in landslide susceptibility analysis in international literature. The research results can serve as a foundation for developing land management guidelines to reduce the risk of landslide failures.

To study the uncertainties of a collapse susceptibility prediction (CSP) under the coupled conditions of different data-based models and different connection methods between collapses and environmental factors, An’yuan County in China with 108 collapses is used as the study case, and 11 environmental factors are acquired by data analysis of Landsat TM 8 and high-resolution aerial images, using a hydrological and topographical spatial analysis of Digital Elevation Modeling in ArcGIS 10.2 software. Accordingly, 20 coupled conditions are proposed for CSP with five different connection methods (Probability Statistics (PSs), Frequency Ratio (FR), Information Value (IV), Index of Entropy (IOE) and Weight of Evidence (WOE)) and four data-based models (Analytic Hierarchy Process (AHP), Multiple Linear Regression (MLR), C5.0 Decision Tree (C5.0 DT) and Random Forest (RF)). Finally, the CSP uncertainties are assessed using the area under receiver operation curve (AUC), mean value, standard deviation and significance test, respectively. Results show that: (1) the WOE-based models have the highest AUC accuracy, lowest mean values and average rank, and a relatively large standard deviation; the mean values and average rank of all the FR-, IV- and IOE-based models are relatively large with low standard deviations; meanwhile, the AUC accuracies of FR-, IV- and IOE-based models are consistent but higher than those of the PS-based model. Hence, the WOE exhibits a greater spatial correlation performance than the other four methods. (2) Among all the data-based models, the RF model has the highest AUC accuracy, lowest mean value and mean rank, and a relatively large standard deviation. The CSP performance of the RF model is followed by the C5.0 DT, MLR and AHP models, respectively. (3) Under the coupled conditions, the WOE-RF model has the highest AUC accuracy, a relatively low mean value and average rank, and a high standard deviation. The PS-AHP model is opposite to the WOE-RF model. (4) In addition, the coupled models show slightly better CSP performances than those of the single data-based models not considering connect methods. The CSP performance of the other models falls somewhere in between. It is concluded that the WOE-RF is the most appropriate coupled condition for CSP than the other models.