Search

ABSTRACTIn mountain regions, the impact of areas on the sediment conveyance can not only be described by their susceptibility to debris flow release, but also by their structural connectivity to the rivers. This generates the need to combine susceptibility and connectivity for accurate analyses of sediment transport. Our study exploits an approach developed by [Steger, er al. 2022; https://doi.org/10.1002/esp.5421] and upscales it to the South Tyrolean Dolomites region. The approach comprised the modeling of debris flow release susceptibility using an interpretable machine learning algorithm, the training of a logistic regression model, and the combination of the resultant classified maps to create a joint susceptibility-connectivity map. The results show the quantitative thresholds for the susceptibility probability and the Index of Connectivity (IC) that allow to discriminate between susceptible and not susceptible, as well as connected and disconnected areas, which are represented via a variety of maps.

Regional debris flow susceptibility assessment is an effective method to prevent debris flow hazards, and deep learning is emerging as a novel approach in this discipline with the development of computers. However, when debris flow samples are insufficient, there will be problems like overfitting or misclassification. To overcome these problems, this paper proposes a semi-supervised deep neural network model (LPA-DNN) combined with label propagation algorithm (LPA), which utilizes high confidence unlabeled samples as pseudo-samples reasonably in few-label scenarios. Xinzhou, Shanxi Province, was selected as the study area, and a dataset containing 292 debris flow samples and 10 types of impact factors was compiled based on watershed units. Using the dataset and pseudo-samples, the LPA-DNN model was built to get debris flow susceptibility map. Meanwhile, DNN and SVM were set up for comparison to demonstrate that the proposed LPA-DNN model has excellent performance and higher accuracy. LPA-DNN alleviates the problem of low accuracy that caused by samples lacking in deep learning to a certain extent, and obtains great classification results, which proves that it is quite potential in regional debris flow susceptibility assessment. [ABSTRACT FROM AUTHOR]

Debris flow has always been a serious problem in mountainous areas. Accurate debris flow susceptibility (DFS) assessment and interpretable prediction results play an important role in the prevention and control of debris flow disasters. Some commonly used machine learning algorithms based on Boosting ensemble techniques were widely used in the study of geohazard susceptibility due to its excellent predictive ability. However, the Categorical Boosting (CatBoost) and Natural Gradient Boosting (NGBoost) have not yet been applied in the field of DFS assessment, and few geohazard studies systematically compare and research these boosting-based algorithms. Meanwhile, previous researches have mostly focused on comparing the predictive ability of algorithms, identifying the susceptibility zones of the entire study area, and ranking the importance of the indicators, but little thorough analysis of the relationship between the indicators and debris flow susceptibility on different types of construction land. The aims of this study were to explore the optimal boosting-based DFS model, and the distribution characteristics and change rules of DFS in the study area, so as to provide decision supports for debris flow disaster prevention and reduction. This was the first time that six boosting-based machine learning algorithms have been compared in the study of DFS assessment. After determining the optimal model, the change rules of indicators in the entire study area and two types of construction lands under different DFS levels were studied respectively. An eXplainable Artifcial Intelligence (XAI) method called SHapley Additive exPlantations (SHAP), combined with zonal statistics function in geographic information system (GIS) were adopted to explore how each indicator affects the occurrence of debris flows. The results showed that the CatBoost performed best and provided the most reasonable DFS result among six boosting-based models. We found that debris flows were more likely to occur along rivers and construction lands at low altitude. Rural areas faced more stronger pressure from rainfall and were featured by worse disaster-breeding environment than urban areas. This research enriches the application of machine learning in DFS assessment, explores the changing trends of indicators between different DFS levels, and provides suggestions for better debris flow disaster prevention and mitigation management. [ABSTRACT FROM AUTHOR]

Different sampling strategies produce varying sample data, serve as the primary input data and directly affect the accuracy of predictions in data-driven grid-based susceptibility models. This study analyzes the accuracy and variation of debris flow susceptibility maps (DFSMs) generated by various sampling strategies. The study area is the Yingxiu region in China, where six sampling strategies were applied, including three sampling locations (deposition area, runout area, and source area) and two sampling types (centroid and polygon) for the debris flow inventory. The effectiveness of 10 conditioning factors used to build the model was assessed by using Pearson correlation coefficient, variance inflation factor, and information gain ratio (IGR) techniques. We then used Weight of Evidence (WofE), Logistic Regression (LR), and Deep Neural Network (DNN) models to produce DFSMs and quantify their performance using the receiver operating characteristic curve (ROC), Accuracy (ACC), Precision, F1 score, and Recall. The results show that the WofE (AUC: 0.754–0.960), LR (AUC: 0.761–0.965), and DNN (AUC: 0.786–0.976) models all perform well, but the DFSMs and dominant factors depend strongly on sampling strategies, especially on sampling location. If the sample areas are excessively large and span across different factor class labels, or if there is a concentration of either large or small sample areas within a specific region, the results of centroid and polygon sampling strategies may differ or even be contradictory.We recommend: (1) determining sampling locations based on the research objectives to provide more accurate evaluation results; (2) selecting the sampling type by first considering the sample size. If the aforementioned conditions are not present, the quicker and more convenient centroid sampling strategy can be chosen; and (3) determining an appropriate sampling strategy and ensuring the accuracy of initial samples are paramount before producing DFSMs.

The uncertainty arising from random sampling of non-debris flow samples significantly impacts the accuracy of debris flow susceptibility assessments (DFSA). This study introduces a novel uncertainty elimination method, Kernel Density Estimation (KDE), and compares it with Mean and Maximum Probability Analysis (MPA) methods. Furthermore, we investigate the responses of four commonly used machine learning models to sampling uncertainty, comparing two structurally similar models (Random Forest (RF) and Extremely Randomized Trees (ERT)) with two structurally different models (Support Vector Machine (SVM) and Multilayer Perceptron (MLP)). The results indicate that the application of these uncertainty elimination methods can significantly enhance AUC values and zoning accuracy, with the KDE method outperforming the others. Specifically, the AUC values based on KDE for RF, ERT, SVM, and MLP are 0.995, 0.999, 0.999, and 0.853, respectively. The corresponding zoning accuracy for these models is 1.00, 1.00, 1.00, and 0.78, respectively. The study further reveals that the responses to sampling uncertainty vary by model architecture: RF, ERT, and SVM typically exhibit bimodal normal distributions, while the MLP model shows a unimodal distribution. Additionally, MLP is more sensitive to variations in negative samples, whereas RF and ERT are less affected due to the ensemble structure.

Background: The Yunnan section of the Nujiang River (YNR) Basin in the alpine-valley area is one of the most critical areas of debris flow in China. Methods: We analyzed the applicability of three machine learning algorithms to model of susceptibility to debris flow—Random Forest (RF), the linear kernel support vector machine (Linear SVM), and the radial basis function support vector machine (RBFSVM)—and compared 20 factors to determine the dominant controlling in debris flow occurrence in the region. Results: We found that (1) RF outperformed RBFSVM and Linear SVM in terms of accuracy, (2) topographic conditions were prerequisites, and geology, precipitation, vegetation, and anthropogenic influence were critical to forming debris flows. Also, the relative elevation difference was the most prominent evaluation factor of debris flow susceptibility, and (3) susceptibility maps based on RF's debris flow susceptibility (DFS) showed that zones with very high susceptibility were distributed along the mainstream of the Nujiang River. These findings provide methodological guidance and reference for improvement of DFS assessment. It enriches the content of DFS studies in the alpine-valley areas. [ABSTRACT FROM AUTHOR]

Jiuzhaigou is situated on a mountain-canyon region and is famous for frequent tectonic activities. An abundance of loose co-seismic landslides and collapses were produced on gullies after the Jiuzhaigou Earthquake on August 8, 2017, which was served as material source for debris flow in later years. Debris flow appears frequently which are seriously endangering the safety of people's lives and properties. Even the earliest debris flow appeared in areas where no case ever reported before. The debris flow susceptibility evaluation (DFSE) is used for predicting the areas prone to debris flow, which is urgently required to avoid hazards and help to guide the strategy of preventive measures. Therefore, this work employs debris flow in Jiuzhaigou to reveal the characteristics of disaster-pregnant environment and to explore the application of machine learning in DFSE. Some new viewpoints are suggested: (i) Material density factor of debris flow is first adopted in this work, and it is proved to be a critical factor for triggering debris flows by sensitivity analysis method. (ii) Deep neural network and convolutional neural network (CNN) achieve relatively good area under the curve (AUC) values and are 0.021–0.024 higher than traditional machine learning methods. (iii) Watershed units combined with CNN-based model can achieve more accurate, reliable and practical susceptibility map. This work provides an idea for prevention of debris flow in mountainous lands. [ABSTRACT FROM AUTHOR]

To unveil the spatial patterns and susceptibility trends of debris flows in the Yellow River Basin in Qinghai Province, an information value coupling with Geodetector (Geo-IM) was employed to quantify the spatial explanatory power of disaster-inducing factors and the susceptibility of debris flows in the study area under different extreme rainfall scenarios. The result show that sediment connectivity, the number of days with >10 mm rainfall, maximum rainfall in three consecutive days, and lithology are critical factors determining the spatial patterns of debris flows. In the current scenario, areas with extremely high and high susceptibility to debris flows are primarily concentrated in the steep mountainous regions of the northeast and central parts. Under extreme rainfall scenarios, newly added areas with extremely high and high susceptibility are mainly concentrated in the northern and southern mountainous regions, as well as on both sides of the Aemye Ma-chhen Range in the central area. The research results can provide a reference for disaster prevention and reduction efforts related to debris flows in this region. [ABSTRACT FROM AUTHOR]

The selection of important factors in machine learning-based susceptibility assessments is crucial to obtain reliable susceptibility results. In this study, metaheuristic optimization and feature selection techniques were applied to identify the most important input parameters for mapping debris flow susceptibility in the southern mountain area of Chengde City in Hebei Province, China, by using machine learning algorithms. In total, 133 historical debris flow records and 16 related factors were selected. The support vector machine (SVM) was first used as the base classifier, and then a hybrid model was introduced by a two-step process. First, the particle swarm optimization (PSO) algorithm was employed to select the SVM model hyperparameters. Second, two feature selection algorithms, namely principal component analysis (PCA) and PSO, were integrated into the PSO-based SVM model, which generated the PCA-PSO-SVM and FS-PSO-SVM models, respectively. Three statistical metrics (accuracy, recall, and specificity) and the area under the receiver operating characteristic curve (AUC) were employed to evaluate and validate the performance of the models. The results indicated that the feature selection-based models exhibited the best performance, followed by the PSO-based SVM and SVM models. Moreover, the performance of the FS-PSO-SVM model was better than that of the PCA-PSO-SVM model, showing the highest AUC, accuracy, recall, and specificity values in both the training and testing processes. It was found that the selection of optimal features is crucial to improving the reliability of debris flow susceptibility assessment results. Moreover, the PSO algorithm was found to be not only an effective tool for hyperparameter optimization, but also a useful feature selection algorithm to improve prediction accuracies of debris flow susceptibility by using machine learning algorithms. The high and very high debris flow susceptibility zone appropriately covers 38.01% of the study area, where debris flow may occur under intensive human activities and heavy rainfall events. [ABSTRACT FROM AUTHOR]

In mountain regions, the impact of areas on the sediment conveyance can not only be described by their susceptibility to debris flow release, but also by their structural connectivity to the rivers. This generates the need to combine susceptibility and connectivity for accurate analyses of sediment transport. Our study exploits an approach developed by [Steger, er al. 2022; https://doi.org/10.1002/esp.5421] and upscales it to the South Tyrolean Dolomites region. The approach comprised the modeling of debris flow release susceptibility using an interpretable machine learning algorithm, the training of a logistic regression model, and the combination of the resultant classified maps to create a joint susceptibility-connectivity map. The results show the quantitative thresholds for the susceptibility probability and the Index of Connectivity (IC) that allow to discriminate between susceptible and not susceptible, as well as connected and disconnected areas, which are represented via a variety of maps. [ABSTRACT FROM AUTHOR]

Background The Yunnan section of the Nujiang River (YNR) Basin in the alpine-valley area is one of the most critical areas of debris flow in China. Methods We analyzed the applicability of three machine learning algorithms to model of susceptibility to debris flow—Random Forest (RF), the linear kernel support vector machine (Linear SVM), and the radial basis function support vector machine (RBFSVM)—and compared 20 factors to determine the dominant controlling in debris flow occurrence in the region. Results We found that (1) RF outperformed RBFSVM and Linear SVM in terms of accuracy, (2) topographic conditions were prerequisites, and geology, precipitation, vegetation, and anthropogenic influence were critical to forming debris flows. Also, the relative elevation difference was the most prominent evaluation factor of debris flow susceptibility, and (3) susceptibility maps based on RF’s debris flow susceptibility (DFS) showed that zones with very high susceptibility were distributed along the mainstream of the Nujiang River. These findings provide methodological guidance and reference for improvement of DFS assessment. It enriches the content of DFS studies in the alpine-valley areas.

Accurately assessing the susceptibility of debris flow disasters is of great significance for reducing the cost of disaster prevention and mitigation, as well as disaster losses. Machine learning (ML) models have been widely used in the susceptibility assessment of debris flow disasters. However, these models often have randomness in the selection of non-disaster data, which can lead to redundant information and poor applicability and accuracy of susceptibility evaluation results. To address this issue, this paper focuses on debris flow disasters in Yongji County, Jilin Province, China; optimizes the sampling method of non-disaster datasets in machine learning susceptibility assessment; and proposes a susceptibility prediction model that couples information value (IV) with artificial neural network (ANN) and logistic regression (LR) models. A debris flow disaster susceptibility distribution map with higher accuracy was drawn based on this model. The model's performance is evaluated using the area under the receiver operating characteristic curve (AUC), information gain ratio (IGR), and typical disaster point verification methods. The results show that the rainfall and topography were found to be decisive factors in the occurrence of debris flow disasters, and the IV-ANN model established in this study had the highest accuracy (AUC = 0.968). Compared to traditional machine learning models, the coupling model produced an increase in economic benefit of about 25% while reducing the average disaster prevention and control investment cost by about 8%. Based on model's susceptibility map, this paper proposes practical disaster prevention and control suggestions that promote sustainable development in the region, such as establishing monitoring systems and information platforms to aid disaster management. [ABSTRACT FROM AUTHOR]

The main purpose of the present study is to develop a debris flow susceptibility map of a mountain area (Susa Valley, Western Italian Alps) by using an upgraded version of the Bonetto et al. (Journal of Mountain Science 18, 2021) approach based on the Rock Engineering System (RES) method. In particular, the area under investigation was discretized in a 5 × 5-m grid on which GIS-based analyses were performed. Starting from available databases, several geological, geo-structural, morphological and hydrographical predisposing parameters were identified and codified into two interaction matrices (one for outcropping lithologies and one for Quaternary deposits), to evaluate their mutual interactions and their weight in the susceptibility estimation. The result for each grid point is the debris flow propensity index (DfPI), an index that estimates the susceptibility of the cell to be a potential debris flow source. The debris flow susceptibility map obtained was compared with those obtained from two expedited and universally recognized susceptibility methods, i.e. the Regional Qualitative Heuristic Susceptibility Mapping (RQHSM) and the Likelihood Ratio (LR). Each map was validated by using the Prediction Rate Curve method. The limitations and strong points of the approaches analysed are discussed, with a focus on the innovativeness and uniqueness of the RES. In fact, in the study site, the RES method was the most efficient for the detection of potential source areas. These results prove its robustness, cost-effectiveness and speed of application in the identification and mapping of sectors capable of triggering debris flow. [ABSTRACT FROM AUTHOR]

• Constructed a debris flow inventory for Yingxiu using six sampling strategies to evaluate the performance of DFSMs. • Compared the performance of WofE, LR, and DNN models in producing DFSMs, revealing a strong dependence on sampling strategy, especially sampling locations. • Demonstrated that centroid and polygon sampling strategies can result in different, and sometimes opposite, DFSM outcomes depending on the sample area size. • Emphasized the critical importance of determining the sampling strategy and ensuring the accuracy of initial samples before producing DFSMs. Different sampling strategies produce varying sample data, serve as the primary input data and directly affect the accuracy of predictions in data-driven grid-based susceptibility models. This study analyzes the accuracy and variation of debris flow susceptibility maps (DFSMs) generated by various sampling strategies. The study area is the Yingxiu region in China, where six sampling strategies were applied, including three sampling locations (deposition area, runout area, and source area) and two sampling types (centroid and polygon) for the debris flow inventory. The effectiveness of 10 conditioning factors used to build the model was assessed by using Pearson correlation coefficient, variance inflation factor, and information gain ratio (IGR) techniques. We then used Weight of Evidence (WofE), Logistic Regression (LR), and Deep Neural Network (DNN) models to produce DFSMs and quantify their performance using the receiver operating characteristic curve (ROC), Accuracy (ACC), Precision, F1 score, and Recall. The results show that the WofE (AUC: 0.754–0.960), LR (AUC: 0.761–0.965), and DNN (AUC: 0.786–0.976) models all perform well, but the DFSMs and dominant factors depend strongly on sampling strategies, especially on sampling location. If the sample areas are excessively large and span across different factor class labels, or if there is a concentration of either large or small sample areas within a specific region, the results of centroid and polygon sampling strategies may differ or even be contradictory.We recommend: (1) determining sampling locations based on the research objectives to provide more accurate evaluation results; (2) selecting the sampling type by first considering the sample size. If the aforementioned conditions are not present, the quicker and more convenient centroid sampling strategy can be chosen; and (3) determining an appropriate sampling strategy and ensuring the accuracy of initial samples are paramount before producing DFSMs. [ABSTRACT FROM AUTHOR]

In order to explore the impact of different evaluation index systems on the evaluation results of debris flow susceptibility, seven evaluation factors, including vegetation coverage, stratum lithology, topographic relief, surface roughness, gully density, distance to fault and PGA were selected to form a control group index system. The ratio index of potential instability area to the catchment area was obtained through slope stability analysis. Test group index system including topographic relief, surface roughness, gully density, distance to fault, PGA and ratio index of potential instability area to the catchment area. The certainty factor model was used to assess the susceptibility of debris flow, and the debris flow susceptibility were set as high, relatively high, middle, relatively low and low on Anning River. The results show that the frequency ratio of high and relatively high susceptibility of test group and control group index system on Anning River are 88. 17% and 85. 88%, respectively. The two evaluation index systems objectively and effectively evaluate the susceptibility of debris flow. The area under curve(AUC) of test group index system is 0. 767. Test group index system can improve evaluation 1. 99% compared to control group index system. The evaluation result of debris flow susceptibility by adding slope stability analysis factor in the debris flow susceptibility evaluation index system is better than that only considering disaster pregnant environmental factors. It provides a new idea for improving the evaluation results of debris flow susceptibility. [ABSTRACT FROM AUTHOR]

Debris flow susceptibility mapping (DFSM) has been reported in many studies, however, the irrational use of the same conditioning factor system for DFSM in regional-scale has not been thoroughly resolved. In this paper, a region-partitioning method that is based on the topographic characteristics of watershed units was developed with the objective of establishing multiple conditioning factor systems for regional-scale DFSM. First, watershed units were selected as the mapping units and created throughout the entire research area. Four topographical factors, namely, elevation, slope, aspect and relative height difference, were selected as the basis for clustering watershed units. The k-means clustering analysis was used to cluster the watershed units according to their topographic characteristics to partition the study area into several parts. Then, the information gain ratio method was used to filter out superfluous factors to establish conditioning factor systems in each region for the subsequent debris flow susceptibility modeling. Last, a debris flow susceptibility map of the whole study area was acquired by merging the maps from all parts. DFSM of Yongji County in Jilin Province, China was selected as a case study, and the analytical hierarchy process method was used to conduct a comparative analysis to evaluate the performance of the region-partitioning method. The area under curve (AUC) values showed that the partitioning of the study area into two parts improved the prediction rate from 0.812 to 0.916. The results demonstrate that the region-partitioning method on the basis of topographic characteristics of watershed units can realize more reasonable regional-scale DFSM. Hence, the developed region-partitioning method can be used as a guide for regional-scale DFSM to mitigate the imminent debris flow risk. [ABSTRACT FROM AUTHOR]

• Consequent, diagonal, transverse and obsequent slope structures and soil stability are incorporated into the DFS assessment. • Unsupervised learning is used to optimize the sampling strategy of negatives. • A state-of-the-art meta-modeling technique is used to optimize supervised learning. • A progressive framework is proposed to improve the reliability of DFS assessment. This research aims to improve the reliability of debris flow susceptibility (DFS) assessment, which is crucial for disaster prevention and mitigation in mountainous regions. A progressive framework was proposed and applied to Pinggu District, Beijing, China. First, 16 debris flow predisposing factors (DFPFs) were selected, and the slope structure and soil stability were incorporated to account for material sources. Watershed units instead of grid units were used to extract data. Then, the multi-collinearity among the factors was reduced by using variance inflation factors (VIF) and information gain (IG), and 13 DFPFs were retained. Three unsupervised learning algorithms (i.e., affinity propagation (AP), Gaussian mixture model (GMM) and self-organizing maps (SOM)) were used to optimize the sampling strategy of non-debris flow units. Subsequently, the occurrence probability of debris flows in each unit was predicted by using four supervised learning algorithms (i.e., logistic regression (LR), random forest (RF), adaptive boosting (ADAB) and extreme gradient boosting (XGB)). They were optimized by a state-of-the-art meta-modeling approach. Finally, the DFPF's importance was ranked. The main contributions of our framework are establishing a high-quality data set and optimizing the prediction algorithms. The results show that the tree-based models perform well, and the boosting-based algorithms outperform the bagging-based algorithms. Supervised learning is more suitable for DFS assessment than unsupervised learning. Debris flows are most likely to occur on a dolomite consequent or diagonal slope with a relief amplitude above 540 m. [ABSTRACT FROM AUTHOR]

Many debris flow spreading analyses have been conducted during recent decades to prevent damage from debris flows. An empirical approach that has been used in various studies on debris flow spreading has advantages such as simple data acquisition and good applicability for large areas. In this study, a GIS-based empirical model that was developed at the University of Lausanne (Switzerland) is used to assess the debris flow susceptibility. Study sites are classified based on the types of soil texture or geological conditions, which can indirectly consider geotechnical or rheological properties, to supplement the weaknesses of Flow-R which neglects local controlling factors. The mean travel angle for each classification is calculated from a debris flow inventory map. The debris flow susceptibility is assessed based on changes in the flow-direction algorithm, an inertial function with a 5-m DEM resolution. A simplified friction-limited model was applied to the runout distance analysis by using the appropriate travel angle for the corresponding classification with a velocity limit of 28 m/s. The most appropriate algorithm combinations that derived the highest average of efficiency and sensitivity for each classification are finally determined by applying a confusion matrix with the efficiency and the sensitivity to the results of the susceptibility assessment. The proposed schemes can be useful for debris flow susceptibility assessment in both the study area and the central region of Korea, which has similar environmental factors such as geological conditions, topography and rainfall characteristics to the study area. [ABSTRACT FROM AUTHOR]

The upper Yangtze River region is one of the most frequent debris flow areas in China. The study area contains a cascade of six large hydropower stations located along the river with total capacity of more than 70 million kilowatts. The purpose of the study was to determine potential and dynamic differences in debris flow susceptibility and intensity with regard to seasonal monsoon events. We analyzed this region's debris flow history by examining the effective peak acceleration of antecedent earthquakes, the impacts of antecedent droughts, the combined effects of earthquakes and droughts, with regard to topography, precipitation, and loose solid material conditions. Based on these factors, we developed a debris flow susceptibility map. Results indicate that the entire debris flow susceptibility area is 167,500 km, of which 26,800 km falls within the high susceptibility area, with 60,900 km in medium and 79,800 km are in low susceptibility areas. Three of the six large hydropower stations are located within the areas with high risk of debris flows. The synthetic zonation map of debris flow susceptibility for the study area corresponds with both the investigation data and actual distribution of debris flows. The results of debris flow susceptibility provide base-line data for mitigating, assessing, controlling and monitoring of debris flows hazards. [ABSTRACT FROM AUTHOR]

The Dadu River Basin (DRB) is an important economic corridor on the Chuanxi Plateau. The DRB is located in the highly changeable terrain of the eastern Qinghai-Tibet Plateau and is often threatened by debris flows. To mitigate the damage of debris flow disasters to the construction and operation of large infrastructures such as railways, roads and hydropower stations in the DRB, it is necessary to evaluate debris flow susceptibility. The connectivity of potential material sources (CPMS), which proxies the possibility of potential material transfer from the source to the outlet, was calculated using an improved index of connectivity, excess topography and brittle fracture index to identify and quantify debris flow susceptibility. The results show that the IC and the gully scale have a Logartihmic function in the DRB, in which IC decreases as the catchment area increases. In 3967 gullies of the Dadu River and its tributaries, the total connectivity of potential material sources (TCPMS) could be used to distinguish between debris flow gullies and non-debris flow gullies (AUC = 0.748). The TCPMS and average connectivity of potential material sources (ACPMS) were used to classify the scale and activity intensity of the 2398 debris flow gullies into four levels. The moderate- and high-activity intensity and large- and extra large-scale debris flows are mainly distributed in Danba, Luding and Kangding. The results of this study provide reference and evidence for the identification and evaluation of debris flow susceptibility. • A new method for assessing debris flow susceptibility based on potential material sources and sediment connectivity. • The quantitative relationship between the scale of debris flow and conditioning factors. • The contribution of excess topography was considered. [ABSTRACT FROM AUTHOR]

Susceptibility analysis is important in any study of debris flows. Unlike debris flows in Southwest China, debris flows in Northern China occur with different characteristics and much lower frequency. However, neglecting the danger of possible debris flows in this northern area may result in a devastating disaster. In this paper, 12 debris flow catchments located near Zhirui town, in Heshigten Banner, Inner Mongolia, China, were investigated. A geographic information system, a global positioning system, and remote sensing were used to determine geological, topographical, morphological, and vegetation factors of influence. Principal component analysis was carried out to convert this set of possibly correlated factors into a set of values of linearly uncorrelated principal components. The accumulative contribution rate of the first five principal components retained most of the information on these factors, accounting for 90.9 %. An improved fuzzy C-means clustering analysis was applied to determine the susceptibility of debris flows in this area. This method is based on a quantum-behaved particle swarm optimization algorithm, which is an evolutionary algorithm that can achieve global optimization, and is not sensitive to the initial cluster centers. Results showed that the susceptibility levels for four of the debris flow catchments were high, six were moderate, and two were low. Our quantitative assessments based on these nonlinear methods were consistent with field investigations. [ABSTRACT FROM AUTHOR]

In this study, the frequency ratio and logistic regression models are applied and verified for the analysis of debris flow susceptibility in a portion of the Dry Frontal Andes and Occidental Preandes of San Juan at approximately 30°S latitude, through aninvestigation based on a Geographic Information System (GIS). The site under study covers an area of 2175.9 km² with a debris flow area of 42.45 km². For this purpose, thematic layers including debris flow inventory, lithology, elevation, slope, aspect, and solar radiation were used. The debris flow inventory map was prepared by interpreting aerial photographs and satellite images and was supported by field surveys. Lithology was extracted from an existing geological map. Slope, aspect and solar radiation were calculated from a Digital Elevation Model created from SRTM (Shuttle Radar Topographic Mission) and topographical maps. The relationship between the variables and the debris flow inventory was calculated using the frequency ratio and logistic regression models. Both models helped to produce debris flow susceptibility maps that classified susceptibility into five categories: very low, low, moderate, high and very high. Subsequently, each debris flow susceptibility map was compared with known debris flow locations and tested. The frequency ratio model (accuracy is 82.71%) was more accurate than the logistic regression model (accuracy is 75.64%) for predictons of the high and very high categories. [ABSTRACT FROM AUTHOR]

In recent years, frequent attacks of heavy rain and typhoon have severely devastated the vulnerable mountains of Taiwan; slopelands are artificially disturbed by improper development and utilization. People are getting more aware of the importance of slopeland preservation as well as disaster prevention and mitigation. The government, realizing the criticality of gradually worsened land safety issues, has also set forth the 'Draft of National Land Planning Act' and the 'Draft of Regulations on Land Preservation Act' in the purposes of rehabilitating the excessively explored ecosystems and diminishing the development extent of environmentally susceptible areas, so as to effectively preserve soil, water, and organism resources and to achieve perpetual development of national lands. 'Classification of Slopeland Utilization Limitations' is a critical link to national land preservation. The classification is based on four factors, namely average slope, effective soil depth, soil erosion, and parent rock, with different utilization zones defined as bases of landuse planning. However, current classification results of the environmentally susceptible and disaster-prone mountain lands are mostly defined as suitable for forestry or husbandry. Scattered allocation of these lands results in critical issues such as segmented landuse and impaired landscape and ecotype. It is necessary to re-adjust land resources planning and usage management. Therefore a review of the current standards for classifying slopeland utilization limitations is proposed to facilitate rational allocation of slopeland use. Jhuoshuei River is selected as the scope of the case study, with data of debris flows induced by the typhoon Toraji in 2001 as the training data. Eight susceptibility factors, which include form factor of watershed, integral hypsometric, slope of main stream, density of stream network, density of road network, area ratio of historical landslide, and area ratio of triggered landslide, together with the total rainfall of the storm event as the triggering factor, are selected for creating the debris flow susceptibility model by employing the logistic regression within the multivariate geostatistics analysis. This model interprets the curve of success ratio of debris flows triggered by typhoon Toraji, of which the area under the curve is as high as 74.3%. The debris flow susceptibility model created in the study takes the Feng-Chiu section of Sinyi Township, Nantou County, Taiwan within the Jhuoshuei River as the scope of research. GIS technology has been applied in the feasibility study of classification standards. New concepts have been further proposed in view of national land preservation addressing the medium and high elevation disaster-prone areas that are not suitable for agricultural use, for standard revision reference. [ABSTRACT FROM AUTHOR]

• Lithology is an important related factor in the debris flow occurrence in the area. • Fifteen debris flows-related factors were applied to debris flow susceptibility. • All flow tracks and geometrical interval has higher prediction accuracy. • The methodology is easy to reproduce and applied to other mountainous regions. Debris flow and floods represent one of the main natural hazards that impact transport infrastructure, causing serious damage, economic losses and hinder regional economic development. These processes are eventually associated with massive traffic cuts and direct damage to road structures. To enable the prevention of such consequences, this paper employs statistical modeling techniques, various instability factors and geomorphological mapping to generate debris flow susceptibility maps in a portion of an important route on the Dry Andes of San Juan in the Agua Negra River basin, Argentina. A debris flows inventory map was prepared using satellite images and field checks. The debris flows inventory was randomly divided into a model dataset 80% (47 debris flows) and remaining 20% (12 debris flows) data was used for validation purpose. The instability factors chosen that influence debris flows occurrence were: elevation, slope angle, slope aspect, solar radiation, topographic wetness index, stream power index, topographic position index, Melton ruggedness number, terrain ruggedness index, sediment transport capacity index, plan curvature, profile curvature, lithology, distance to road and proximity to stream. Using these factors, six different models of debris flow susceptibility were calculated by Frequency ratio (Fr). Lithology (igneous complex) was found to be important debris flows-related factor in the study area. The precision of the results was evaluated by receiver operating characteristic (ROC) analysis. According to the area under the curve (AUC) the models of all flow track and natural breaks and all flow track and geometrical interval were 0.83 and 0.84, respectively, showing a practically identical predictive capacity. [ABSTRACT FROM AUTHOR]

Debris flows have been always a serious problem in the mountain areas. Research on the assessment of debris flows susceptibility (DFS) is useful for preventing and mitigating debris flow risks. The main purpose of this work is to study the DFS in the Shigatse area of Tibet, by using machine learning methods, after assessing the main triggering factors of debris flows. Remote sensing and geographic information system (GIS) are used to obtain datasets of topography, vegetation, human activities and soil factors for local debris flows. The problem of debris flow susceptibility level imbalances in datasets is addressed by the Borderline-SMOTE method. Five machine learning methods, i.e., back propagation neural network (BPNN), one-dimensional convolutional neural network (1D-CNN), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost) have been used to analyze and fit the relationship between debris flow triggering factors and occurrence, and to evaluate the weight of each triggering factor. The ANOVA and Tukey HSD tests have revealed that the XGBoost model exhibited the best mean accuracy (0.924) on ten-fold cross-validation and the performance was significantly better than that of the BPNN (0.871), DT (0.816), and RF (0.901). However, the performance of the XGBoost did not significantly differ from that of the 1D-CNN (0.914). This is also the first comparison experiment between XGBoost and 1D-CNN methods in the DFS study. The DFS maps have been verified by five evaluation methods: Precision, Recall, F1 score, Accuracy and area under the curve (AUC). Experiments show that the XGBoost has the best score, and the factors that have a greater impact on debris flows are aspect, annual average rainfall, profile curvature, and elevation. [ABSTRACT FROM AUTHOR]