Search

Landslides pose significant and serious geological threat disasters worldwide, threatening human lives and property; China is particularly susceptible to these disasters. This paper focuses on Pengyang County, which is situated in the Ningxia Hui Autonomous Region of China, an area prone to landslides. This study investigated the application of machine learning techniques for analyzing landslide susceptibility. To construct and validate the model, we initially compiled a landslide inventory comprising 972 historical landslides and an equivalent number of non-landslide sites (Data sourced from the Pengyang County Department of Natural Resources). To ensure an impartial evaluation, both the landslide and non-landslide datasets were randomly divided into two sets using a 70/30 ratio. Next, we extracted 15 landslide conditioning factors, including the slope angle, elevation, profile curvature, plan curvature, slope aspect, TWI (topographic wetness index), TPI (topographic position index), distance to roads and rivers, NDVI (normalized difference vegetation index), rainfall, land use, lithology, SPI (stream power index), and STI (sediment transport index), from the spatial database. Subsequently, a correlation analysis between the conditioning factors and landslide occurrences was conducted using the certainty factor (CF) method. Three landslide models were established by employing logistic regression (LR), functional trees (FTs), and random subspace functional trees (RSFTs) algorithms. The landslide susceptibility map was categorized into five levels: very low, low, medium, high, and very high susceptibility. Finally, the predictive capability of the three algorithms was assessed using the area under the receiver operating characteristic curve (AUC). The better the prediction, the higher the AUC value. The results indicate that all three models are predictive and practical, with only minor discrepancies in accuracy. The integrated model (RSFT) displayed the highest predictive performance, achieving an AUC value of 0.844 for the training dataset and 0.837 for the validation dataset. This was followed by the LR model (0.811 for the training dataset and 0.814 for the validation dataset) and the FT model (0.776 for the training dataset and 0.760 for the validation dataset). The proposed methods and resulting landslide susceptibility map can assist researchers and local authorities in making informed decisions for future geohazard prevention and mitigation. Furthermore, they will prove valuable and be useful for other regions with similar geological characteristics features. [ABSTRACT FROM AUTHOR]

Collapsing gully is one of the most serious ecological and environmental damage in southern China. The dynamic change of wall collapse is also difficult to monitor in the high-risk and complex terrain. Obviously, a more concise and accurate method is necessary to monitor the dynamic collapse, and further to clarify the collapsing gully erosion. Unmanned Aerial Vehicle (UAV) nap of the object photograph is brand new photogrammetry for the needs of fine measurement. Point cloud data was generated to extract different parameters of collapse terrain. The topographic features of the avalanche wall were extracted, and then the obtained data was used to analyze the spatial characteristics and soil migration changes under the photogrammetry. Collapsing gully research area was located in the AnXi County, Fujian Province of South China. The specific procedure was as follows. 1) The control points were arranged in the study area, where the coordinates of each control point were measured using Trimble R4 GNSS GPS, Trimble R2 GPS, and (1+1) RTK network mode. 2) The image data was acquired by the nap of photogrammetry technology. PIX4DMapper was utilized to evaluate the positioning accuracy of control point data obtained by RTK. 3) The Digital Surface Model (DSM) data in the study area was processed by ArcMap, whereas, the digital surface model of differences (DOD) values was obtained for measured accuracy. The DOD was equivalent to the change of soil erosion and deposition volume, accurately reflecting the volume change of soil dynamic migration. The elevation change was also measured in the research area during the monitoring period. Through CloudCompare, Scale-invariant feature transform-Clustering Views for Multi-View Stereo (SFM-MVS) technology was used to analyze the reproducibility of point cloud data. A Canon 5D Mark III SLR camera was applied to the surround fixed focus-range image to collect data, and simultaneously to measure the target wall collapse as the reference data. Three groups of control plots were arranged according to the lowest level (LODmin) in the study area. The error sources and feasibility close to photogrammetry were analyzed from the accuracy of positioning and measurement, as well as the point cloud reproducibility. 4) The distribution characteristics of landslide erosion deposition were evaluated during the monitoring period, combined with the rainfall data collected by an RG3-M rainfall recorder. The results showed that: 1) The average resolution of the image close to the photogrammetry technology was 4.1 mm in terms of positioning. The average projection error was controlled at about 0.19 mm in terms of control point calibration. 2) The total mean absolute error of DOD in measurement was 0.006 m³, 45.45% lower than that of traditional oblique photogrammetry. 3) The overall improvement was 162.5% in elevation accuracy. 4) In reproducibility, the average value of elevation error was only 0.36 mm for the repeated point cloud data, indicating high stability. 5) The dynamic change of erosion settlement in the collapsed wall was monitored in the study area during the study period. The total rainfall was 564.6 mm in the study area, while the soil loss of the collapsed wall was 4.758 m³. The UAV Nap of the object photograph can be expected to serve as efficient and accurate monitoring for the erosion sediment transport in south collapsing gully areas of China. [ABSTRACT FROM AUTHOR]

Flooding is one of the most significant environmental challenges and can easily cause fatal incidents and economic losses. Flood reduction is costly and time-consuming task; so it is necessary to accurately detect flood susceptible areas. This work presents an effective flood susceptibility mapping framework by involving an adaptive neuro-fuzzy inference system (ANFIS) with two metaheuristic methods of biogeography based optimization (BBO) and imperialistic competitive algorithm (ICA). A total of 13 flood influencing factors, including slope, altitude, aspect, curvature, topographic wetness index, stream power index, sediment transport index, distance to river, landuse, normalized difference vegetation index, lithology, rainfall and soil type, were used in the proposed framework for spatial modeling and Dingnan County in China was selected for the application of the proposed methods due to data availability. There are 115 flood occurrences in the study area which were randomly separated into training (70% of the total) and verification (30%) sets. To perform the proposed framework, the step-wise weight assessment ratio analysis algorithm is first used to evaluate the correlation between influencing factors and floods. Then, two ensemble methods of ANFIS-BBO and ANFIS-ICA are constructed for spatial prediction and producing flood susceptibility maps. Finally, these resultant maps are assessed in terms of several statistical and error measures, including receiver operating characteristic (ROC) curve and area under the ROC curve (AUC), root-mean-square error (RMSE). The experimental results demonstrated that the two ensemble methods were more effective than ANFIS in the study area. For instance, the predictive AUC values of 0.8407, 0.9045 and 0.9044 were achieved by the methods of ANFIS, ANFIS-BBO and ANFIS-ICA, respectively. Moreover, the RMSE values for ANFIS, ANFIS-BBO and ANFIS-ICA using the verification set were 0.3100, 0.2730 and 0.2700, respectively. In addition, as regards ANFIS-BBO and ANFIS-ICA, a total areas of 39.30% and 35.39% were classified as highly susceptible to flooding. Therefore, the proposed ensemble framework can be used for flood susceptibility mapping in other sites with similar geo-environmental characteristics for taking measures to manage and prevent flood damages. Image 1 • Prediction power of two novel ensemble methods for flood susceptibility mapping. • The proposed ensemble methods can improve the prediction performance of ANFIS. • The proposed methods can accurately produce flood susceptibility maps for mitigation and management. [ABSTRACT FROM AUTHOR]

In this study, we introduced novel hybrid of evidence believe function (EBF) with logistic regression (EBF-LR) and logistic model tree (EBF-LMT) for landslide susceptibility modelling. Fourteen conditioning factors were selected, including slope aspect, elevation, slope angle, profile curvature, plan curvature, topographic wetness index (TWI), stream sediment transport index (STI), stream power index (SPI), distance to rivers, distance to faults, distance to roads, lithology, normalized difference vegetation index (NDVI), and land use. The importance of factors was assessed using correlation attribute evaluation method. Finally, the performance of three models was evaluated using the area under the curve (AUC). The validation process indicated that the EBF-LMT model acquired the highest AUC for the training (84.7%) and validation (76.5%) datasets, followed by EBF-LR and EBF models. Our result also confirmed that combination of a decision tree-logistic regression-based algorithm with a bivariate statistical model lead to enhance the prediction power of individual landslide models. [ABSTRACT FROM AUTHOR]

Globally, and in China, landslides constitute one of the most important and frequently encountered natural hazard events. In the present study, landslide susceptibility evaluation was undertaken using novel ensembles of bivariate statistical-methods-based (evidential belief function (EBF), statistical index (SI), and weights of evidence (WoE)) kernel logistic regression machine learning classifiers. A landslide inventory comprising 222 landslides and 15 conditioning factors (slope angle, slope aspect, altitude, plan curvature, profile curvature, stream power index, sediment transport index, topographic wetness index, distance to rivers, distance to roads, distance to faults, NDVI, land use, lithology, and rainfall) was prepared as the spatial database. Correlation analysis and selection of conditioning factors were conducted using multicollinearity analysis and classifier attribute evaluation methods, respectively. The receiver operating characteristic curve method was used to validate the models. The areas under the success rate (AUC_T) and prediction rate (AUC_P) curves and landslide density analysis were also used to assess the prediction capability of the landslide susceptibility maps. Results showed that the EBF-KLR hybrid model had the highest predictive capability in landslide susceptibility assessment (AUC values of 0.814 and 0.753 for the training and validation datasets, respectively; AUC_T value of 0.8511 and AUC_P value of 0.7615), followed in descending order by the SI-KLR and WoE-KLR hybrid models. These findings indicate that hybrid models could improve the predictive capability of bivariate models, and that the EBF-KLR is a promising hybrid model for the spatial prediction of landslides in susceptible areas. [ABSTRACT FROM AUTHOR]

Suichuan is a mountainous area at the Jiangxi province in Central China, where rainfall-induced landslides occur frequently. The purpose of this study is to assess landslide susceptibility of this region using support vector machine (SVM) with four kernel functions: polynomial (PL), radial basis function (RBF), sigmoid (SIG), and linear (LN). A total of 178 landslides were used to accomplish this approach, of which, 125 (70%) landslides were randomly selected for training the landslide susceptibility models, whereas the remaining 53 (30%) were used for the model validation. Fifteen landslide conditioning factors were considered including slope-angle, altitude, slope-aspect, topographic wetness index (TWI), sediment transport index (STI), stream power index (SPI), plan curvature, profile curvature, distance to rivers, distance to faults, distance to roads, precipitation, landuse, normalized difference vegetation index (NDVI), and lithology. Using the training dataset, nine landslide susceptibility models for the Suichuan area were constructed with the four kernel functions. To evaluate the performance of these models, the receiver-operating characteristic curve (ROC) and area under the curve (AUC) were used. Using the training dataset, AUC values for the SVM-PL models with six degrees PL function (1–6) are 0.715, 0.801, 0.856, 0.891, 0.919, 0.953, respectively, and for the SVM-RBF model, the SVM-SIG model, and the SVM-LN model are 0.716, 0.741, and 0.740, respectively. Using the validation dataset, AUC values for the SVM-PL models with six degrees PL function (1–6) are 0.738, 0.730, 0.683, 0.648, 0.608, and 0.598, respectively, and for the SVM-RBF model, the SVM-SIG model, and the SVM-LN model are 0.716, 0.741, and 0.740, respectively. Our results suggested that the SVM-RBF model is the most suitable for landslide susceptibility assessment for the study area. [ABSTRACT FROM AUTHOR]

The main goal of this study is to produce landslide susceptibility maps for the Qianyang County of Baoji city, China, using both certainty factor (CF) and index of entropy (IOE) models. At first, a landslide inventory map was prepared using earlier reports and aerial photographs as well as by carrying out field surveys. A total of 81 landslide locations were detected. Out of these, 56 (70%) landslides were randomly selected as training data for building landslide susceptibility models and the remaining 25 (30%) were used for the validation purposes. Then, a total number of 15 landslide causative factors, such as slope angle, slope aspect, general curvature, plan curvature, profile curvature, altitude, distance to faults, distance to rivers, distance to roads, the sediment transport index (STI), the stream power index (SPI), the topographic wetness index (TWI), geomorphology, lithology, and rainfall, were used in the analysis. The susceptibility maps produced using CF and IOE models had five different susceptibility classes such as very low, low, moderate, high, and very high. Finally, the output maps were validated using the validation data (i.e., 30% landslide location data that was not used during the model construction), using the area under the curve (AUC) method. The 'success rate' curve showed that the area under the curve for CF and IOE models were 0.8433 (84.33%) and 0.8227 (82.27%) accuracy, respectively. Similarly, the validation result showed that the susceptibility map using CF model has the higher prediction accuracy of 82.32%, while for IOE model it was 80.88%. The results of this study showed that the two landslide susceptibility maps obtained were successful and can be used for preliminary land use planning and hazard mitigation purpose. [ABSTRACT FROM AUTHOR]

• The dam-break induced cascading hazard chain leading to a catastrophic event. • This paper used a typical outburst debris flow to describe the catastrophe process. • The flow amplification effect was analyzed based on the obstructive coefficient. • The movement process of outburst debris flow was simulated and validated. • Different scenario simulations were performed under the new mitigation projects. Strong earthquakes can induce large amounts of loose solid materials, forming landslide dams and blocking narrow flow channels. Under extreme rainfall conditions, instability can lead to an outburst of debris flow once the landslide dam has formed it. On July 10, 2013, a volume of 4.5 × 104 m3 of debris flow occurred in the Yangling gully, Wenchuan County, China. This event can be categorized as an outburst of the debris flow that might seriously threaten valley residents, existing sediment transport countermeasure works, and road infrastructures. This paper describes a typical outburst of debris flow, calculates its obstructive coefficient, simulates the process under various recurrence intervals, and analyzes the efficacy of a new mitigation project. Related research results have laid the foundation for further study of the risk assessment and early warning of debris flow due to landslide dam failure. In this paper, an accurate computational model for the obstructive coefficient, closely related to the flow amplification effect, is established based on a dam break's physical experiments. Combined with the numerical calculation method, the movement process of the Yangling gully was simulated under the old artificial dam and the flow channel engineering conditions. By comparing the measured and the simulated accumulation area, the verification results illustrate that the accumulation area considering the obstructive coefficient model is closer to the measured value. Based on the obstructive coefficient computational model, the results illustrate the outburst of debris flow discharge for various recurrence intervals (50, 100, and 200 years respectively) to perform scenario simulations of Yangling gully under the new mitigation project conditions. [ABSTRACT FROM AUTHOR]

• A landslide sediment supply capacity assessment model was developed for applications in debris flow basins. • Spatial and temporal variability of landslide sediment supply capacity is significant. • Decay of landslide sediment supply capacity to the pre-earthquake level is expected within 17 years. • The evolution of landslide activity has a positive effect on the landslide sediment transport capacity. After the Wenchuan earthquake, a large number of landslides in debris flow basins continued to provide loose debris for channels and further affected the occurrence of debris flows. Evaluating the landslide sediment supply capacity in debris flow basins requires understanding the landslide activity and the coupled relationship between the landslide and the channel. In this study, we proposed a model based on the landslide area density index (P Als) and the landslide connectivity (IC l) to evaluate the capacity of the landslide sediment supply for channels in 46 sub-catchments in the study area. The capacity of the landslide sediment supply for channels generally decreased from 2008 to 2018, but due to the influence of heavy rainfall, the actual capacity of the landslide sediment supply for channels in the study area may gradually diminish in an unstable way, and it may arrive at the pre-earthquake level by 2025 without the influence of extreme rainfall. However, higher debris flow activity may last longer than 2025 because sufficient gully materials are still accumulated in the channel. The sediment transport capacity of landslides was divided into five levels: extremely, high, moderate, slight and low. The capacity of the landslide sediment supply for channels changed from extreme levels and high levels to moderate levels and slight levels after the first 5 years of the Wenchuan earthquake and was then dominated by low levels. Simultaneously, the regions with higher landslide sediment supply capacities gradually changed from along the Minjiang River regions to the upper and middle reaches of the debris flow basin from 2008 to 2018. Hongchun gully, which is in the study area, was chosen as an example to compare the assessment results and field investigation. The long-term evolution of landslides is an important reason for the decrease in the sediment supply capacity of landslides. [ABSTRACT FROM AUTHOR]

Sediment routing in deep-water settings can be significantly different in lacustrine basins from their well-studied marine counterparts, which has been largely overlooked during the past decades. The seismically well-imaged lacustrine clinothems in the Eocene Dongying Depression provide a good opportunity to bridge the deep-water sediment partitioning with clinothem architecture and shelf-edge trajectories, which have been studied through the integration of 3D seismic data and well-logging data. In the study area, the Eocene delta-complexes are architecturally manifested as alternating aggradation dominated (AC) and progradation dominated clinothems (PC). The Eocene Dongying clinothem architecture has been documented in terms of shelf–edge trajectory angle (θ sht), edge-to-toe distance (ETT), aggradation height (Ah), progradation distance (Pd) and maximum foreset angle (γ mfa). Aggradation dominated clinothems are characterized by ascending shelf-edge trajectories with thick and widespread sand-prone bottomsets, suggesting higher efficiency of sediment delivery into the outlying lake floor. Progradation dominated clinothems, in contrast, are characterized by flat to slightly descending trajectories and generally by a lack of bottomsets. Alternations of rising and flat to slightly descending trajectories accompanied with different clinothem types probably indicate frequent relative lake level changes (on time-scales of 100s of kyr). Further analysis of seismic images and extensive well-logs suggest the distal aggradational bottomsets are generally consist of sub-lacustrine channel-lobe systems, whereas sediment slide, slump blocks occur in slope to slope toe areas of progradation dominated clinothems, which indicate varied processes of deep-water sediment transport associated with different clinothem types and shelf-edge trajectories. Lake-level, sediment supply, water salinity and density change induced by humid-arid climate cycle are suggested to be main factors controlling clinothems stacking pattern and sediment dispersal into deep-lacustrine. Humid climate are considered to be related with strongly aggradational clinothems, during which sediment can be directly transported to the distant bottomset areas due to increased sediment concentration and energy in river discharge. Whereas during dry periods, progradation dominated clinothems start to build under stillstand or falling lake level conditions, sediment generally accumulates at river mouth and collapses due to sediment overload or fault activity. Therefore, a relationship between deep-lacustrine depositional process and climatic signature was established which may provide new thoughts in both the study of deep-water sequences and deep-water exploration in lacustrine basins. • Alternation of two different growth styles of lacustrine clinothems is identified. • Strongly aggradational clinothems suggest increased deep-water sediment delivery. • Strongly progradational clinothems suggest limited deep-water sediment delivery. • Climate-cycle controls clinothem patterns and associated deep-water processes. [ABSTRACT FROM AUTHOR]

In this study, hybrid integration of MultiBoosting based on two artificial intelligence methods (the radial basis function network (RBFN) and credal decision tree (CDT) models) and geographic information systems (GIS) were used to establish landslide susceptibility maps, which were used to evaluate landslide susceptibility in Nanchuan County, China. First, the landslide inventory map was generated based on previous research results combined with GIS and aerial photos. Then, 298 landslides were identified, and the established dataset was divided into a training dataset (70%, 209 landslides) and a validation dataset (30%, 89 landslides) with ensured randomness, fairness, and symmetry of data segmentation. Sixteen landslide conditioning factors (altitude, profile curvature, plan curvature, slope aspect, slope angle, stream power index (SPI), topographical wetness index (TWI), sediment transport index (STI), distance to rivers, distance to roads, distance to faults, rainfall, NDVI, soil, land use, and lithology) were identified in the study area. Subsequently, the CDT, RBFN, and their ensembles with MultiBoosting (MCDT and MRBFN) were used in ArcGIS to generate the landslide susceptibility maps. The performances of the four landslide susceptibility maps were compared and verified based on the area under the curve (AUC). Finally, the verification results of the AUC evaluation show that the landslide susceptibility mapping generated by the MCDT model had the best performance. [ABSTRACT FROM AUTHOR]