scholarly journals Spatial Predictions of Debris Flow Susceptibility Mapping Using Convolutional Neural Networks in Jilin Province, China

Water ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 2079
Author(s):  
Yang Chen ◽  
Shengwu Qin ◽  
Shuangshuang Qiao ◽  
Qiang Dou ◽  
Wenchao Che ◽  
...  
Keyword(s):  
Neural Networks ◽  
Debris Flow ◽  
Statistical Methods ◽  
Convolutional Neural Networks ◽  
Debris Flows ◽  
Susceptibility Mapping ◽  
Jilin Province ◽  
Support Vector ◽  
Validation Set ◽  
Debris Flow Susceptibility

Debris flows are a major geological disaster that can seriously threaten human life and physical infrastructures. The main contribution of this paper is the establishment of two–dimensional convolutional neural networks (2D–CNN) models by using SAME padding (S–CNN) and VALID padding (V–CNN) and comparing them with support vector machine (SVM) and artificial neural network (ANN) models, respectively, to predict the spatial probability of debris flows in Jilin Province, China. First, the dataset is randomly divided into a training set (70%) and a validation set (30%), and thirteen influencing factors are selected to build the models. Then, multicollinearity analysis and gain ratio methods are used to quantify the predictive ability of factors. Finally, the area under the receiver operatic characteristic curve (AUC) and statistical methods are utilized to measure the accuracy of the models. The results show that the S–CNN model gets the highest AUC value of 0.901 in the validation set, followed by the SVM model, the V–CNN model, and the ANN model. Three statistical methods also show that the S–CNN model produces minimum errors compared with other models. The S–CNN model is hailed as an important means to improve the accuracy of debris–flow susceptibility mapping and provides a reasonable scientific basis for critical decisions.

scholarly journals Application of Machine Learning to Debris Flow Susceptibility Mapping along the China–Pakistan Karakoram Highway

2020 ◽  
Vol 12 (18) ◽  
pp. 2933
Author(s):  
Feng Qing ◽  
Yan Zhao ◽  
Xingmin Meng ◽  
Xiaojun Su ◽  
Tianjun Qi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Debris Flow ◽  
Debris Flows ◽  
Susceptibility Mapping ◽  
Support Vector ◽  
Safe Operation ◽  
Extreme Gradient Boosting ◽  
Karakoram Highway ◽  
Debris Flow Susceptibility

The China–Pakistan Karakoram Highway is an important land route from China to South Asia and the Middle East via Pakistan. Due to the extremely hazardous geological environment around the highway, landslides, debris flows, collapses, and subsidence are frequent. Among them, debris flows are one of the most serious geological hazards on the Karakoram Highway, and they often cause interruptions to traffic and casualties. Therefore, the development of debris flow susceptibility mapping along the highway can potentially facilitate its safe operation. In this study, we used remote sensing, GIS, and machine learning techniques to map debris flow susceptibility along the Karakoram Highway in areas where observation data are scarce and difficult to obtain by field survey. First, the distribution of 544 catchments which are prone to debris flow were identified through visual interpretation of remote sensing images. The factors influencing debris flow susceptibility were then analyzed, and a total of 17 parameters related to geomorphology, soil materials, and triggering conditions were selected. Model training was based on multiple common machine learning methods, including Ensemble Methods, Gaussian Processes, Generalized Linear models, Navies Bayes, Nearest Neighbors, Support Vector Machines, Trees, Discriminant Analysis, and eXtreme Gradient Boosting. Support Vector Classification (SVC) was chosen as the final model after evaluation; its accuracy (ACC) was 0.91, and the area under the ROC curve (AUC) was 0.96. Among the factors involved in SVC, the Melton Ratio (MR) was the most important, followed by drainage density (DD), Hypsometric Integral (HI), and average slope (AS), indicating that geomorphic conditions play an important role in predicting debris flow susceptibility in the study area. SVC was used to map debris flow susceptibility in the study area, and the results will potentially facilitate the safe operation of the highway.

scholarly journals Comparison of Different Machine Learning Methods for Debris Flow Susceptibility Mapping: A Case Study in the Sichuan Province, China

2020 ◽  
Vol 12 (2) ◽  
pp. 295 ◽  
Author(s):  
Ke Xiong ◽  
Basanta Raj Adhikari ◽  
Constantine A. Stamatopoulos ◽  
Yu Zhan ◽  
Shaolin Wu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Debris Flow ◽  
Sichuan Province ◽  
Susceptibility Mapping ◽  
Boosted Regression Trees ◽  
Support Vector ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Susceptibility Maps ◽  
Debris Flow Susceptibility

Debris flow susceptibility mapping is considered to be useful for hazard prevention and mitigation. As a frequent debris flow area, many hazardous events have occurred annually and caused a lot of damage in the Sichuan Province, China. Therefore, this study attempted to evaluate and compare the performance of four state-of-the-art machine-learning methods, namely Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), and Boosted Regression Trees (BRT), for debris flow susceptibility mapping in this region. Four models were constructed based on the debris flow inventory and a range of causal factors. A variety of datasets was obtained through the combined application of remote sensing (RS) and geographic information system (GIS). The mean altitude, altitude difference, aridity index, and groove gradient played the most important role in the assessment. The performance of these modes was evaluated using predictive accuracy (ACC) and the area under the receiver operating characteristic curve (AUC). The results of this study showed that all four models were capable of producing accurate and robust debris flow susceptibility maps (ACC and AUC values were well above 0.75 and 0.80 separately). With an excellent spatial prediction capability and strong robustness, the BRT model (ACC = 0.781, AUC = 0.852) outperformed other models and was the ideal choice. Our results also exhibited the importance of selecting suitable mapping units and optimal predictors. Furthermore, the debris flow susceptibility maps of the Sichuan Province were produced, which can provide helpful data for assessing and mitigating debris flow hazards.

scholarly journals A Method for Improving Controlling Factors Based on Information Fusion for Debris Flow Susceptibility Mapping: A Case Study in Jilin Province, China

Entropy ◽  
2019 ◽  
Vol 21 (7) ◽  
pp. 695 ◽  
Author(s):  
Qiang Dou ◽  
Shengwu Qin ◽  
Yichen Zhang ◽  
Zhongjun Ma ◽  
Junjun Chen ◽  
...  
Keyword(s):  
Debris Flow ◽  
Information Fusion ◽  
Slope Angle ◽  
Controlling Factors ◽  
Susceptibility Mapping ◽  
Jilin Province ◽  
Vegetation Coverage ◽  
Slope Aspect ◽  
Susceptibility Maps ◽  
Debris Flow Susceptibility

Debris flow is one of the most frequently occurring geological disasters in Jilin province, China, and such disasters often result in the loss of human life and property. The objective of this study is to propose and verify an information fusion (IF) method in order to improve the factors controlling debris flow as well as the accuracy of the debris flow susceptibility map. Nine layers of factors controlling debris flow (i.e., topography, elevation, annual precipitation, distance to water system, slope angle, slope aspect, population density, lithology and vegetation coverage) were taken as the predictors. The controlling factors were improved by using the IF method. Based on the original controlling factors and the improved controlling factors, debris flow susceptibility maps were developed while using the statistical index (SI) model, the analytic hierarchy process (AHP) model, the random forest (RF) model, and their four integrated models. The results were compared using receiver operating characteristic (ROC) curve, and the spatial consistency of the debris flow susceptibility maps was analyzed while using Spearman’s rank correlation coefficients. The results show that the IF method that was used to improve the controlling factors can effectively enhance the performance of the debris flow susceptibility maps, with the IF-SI-RF model exhibiting the best performance in terms of debris flow susceptibility mapping.

Exploring the impact of introducing a physical model into statistical methods on the evaluation of regional scale debris flow susceptibility

2021 ◽  
Vol 106 (1) ◽  
pp. 881-912
Author(s):  
Jingbo Sun ◽  
Shengwu Qin ◽  
Shuangshuang Qiao ◽  
Yang Chen ◽  
Gang Su ◽  
...  
Keyword(s):  
Debris Flow ◽  
Physical Model ◽  
Statistical Methods ◽  
Regional Scale ◽  
The Impact ◽  
Debris Flow Susceptibility

Pretrained Convolutional Neural Networks Perform Well in a Challenging Test Case: Identification of Plant Bugs (Hemiptera: Miridae) Using a Small Number of Training Images

2021 ◽  
Vol 5 (2) ◽  
Author(s):  
Alexander Knyshov ◽  
Samantha Hoang ◽  
Christiane Weirauch
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Training Image ◽  
Species Level ◽  
Identification Accuracy ◽  
Support Vector ◽  
Test Case ◽  
Learning Approaches ◽  
Lower Accuracy ◽  
Neural Network Classifiers

Abstract Automated insect identification systems have been explored for more than two decades but have only recently started to take advantage of powerful and versatile convolutional neural networks (CNNs). While typical CNN applications still require large training image datasets with hundreds of images per taxon, pretrained CNNs recently have been shown to be highly accurate, while being trained on much smaller datasets. We here evaluate the performance of CNN-based machine learning approaches in identifying three curated species-level dorsal habitus datasets for Miridae, the plant bugs. Miridae are of economic importance, but species-level identifications are challenging and typically rely on information other than dorsal habitus (e.g., host plants, locality, genitalic structures). Each dataset contained 2–6 species and 126–246 images in total, with a mean of only 32 images per species for the most difficult dataset. We find that closely related species of plant bugs can be identified with 80–90% accuracy based on their dorsal habitus alone. The pretrained CNN performed 10–20% better than a taxon expert who had access to the same dorsal habitus images. We find that feature extraction protocols (selection and combination of blocks of CNN layers) impact identification accuracy much more than the classifying mechanism (support vector machine and deep neural network classifiers). While our network has much lower accuracy on photographs of live insects (62%), overall results confirm that a pretrained CNN can be straightforwardly adapted to collection-based images for a new taxonomic group and successfully extract relevant features to classify insect species.

scholarly journals Debris-flow susceptibility assessment through cellular automata modeling: an example from 15–16 December 1999 disaster at Cervinara and San Martino Valle Caudina (Campania, southern Italy)

2003 ◽  
Vol 3 (5) ◽  
pp. 457-468 ◽  
Author(s):  
G. Iovine ◽  
S. Di Gregorio ◽  
V. Lupiano
Keyword(s):  
Cellular Automata ◽  
Debris Flow ◽  
Urban Areas ◽  
Debris Flows ◽  
Soil Cover ◽  
Southern Italy ◽  
Landslide Risk ◽  
Campania Region ◽  
Optimal Values ◽  
Debris Flow Susceptibility

Abstract. On 15–16 December 1999, heavy rainfall severely stroke Campania region (southern Italy), triggering numerous debris flows on the slopes of the San Martino Valle Caudina-Cervinara area. Soil slips originated within the weathered volcaniclastic mantle of soil cover overlying the carbonate skeleton of the massif. Debris slides turned into fast flowing mixtures of matrix and large blocks, downslope eroding the soil cover and increasing their original volume. At the base of the slopes, debris flows impacted on the urban areas, causing victims and severe destruction (Vittori et al., 2000). Starting from a recent study on landslide risk conditions in Campania, carried out by the Regional Authority (PAI –Hydrogeological setting plan, in press), an evaluation of the debris-flow susceptibility has been performed for selected areas of the above mentioned villages. According to that study, such zones would be in fact characterised by the highest risk levels within the administrative boundaries of the same villages ("HR-zones"). Our susceptibility analysis has been performed by applying SCIDDICA S3–hex – a hexagonal Cellular Automata model (von Neumann, 1966), specifically developed for simulating the spatial evolution of debris flows (Iovine et al., 2002). In order to apply the model to a given study area, detailed topographic data and a map of the erodable soil cover overlying the bedrock of the massif must be provided (as input matrices); moreover, extent and location of landslide source must also be given. Real landslides, selected among those triggered on winter 1999, have first been utilised for calibrating SCIDDICA S3–hex and for defining "optimal" values for parameters. Calibration has been carried out with a GIS tool, by quantitatively comparing simulations with actual cases: optimal values correspond to best simulations. Through geological evaluations, source locations of new phenomena have then been hypothesised within the HR-zones. Initial volume for these new cases has been estimated by considering the actual statistics of the 1999 landslides. Finally, by merging the results of simulations, a deterministic susceptibility zonation of the considered area has been obtained. In this paper, aiming at illustrating the potential for debris-flow hazard analyses of the model SCIDDICA S3–hex, a methodological example of susceptibility zonation of the Vallicelle HR-zone is presented.

scholarly journals Data Mining and Statistical Approaches in Debris-Flow Susceptibility Modelling Using Airborne LiDAR Data

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3451 ◽  
Author(s):  
Usman Salihu Lay ◽  
Biswajeet Pradhan ◽  
Zainuddin Bin Md Yusoff ◽  
Ahmad Fikri Bin Abdallah ◽  
Jagannath Aryal ◽  
...  
Keyword(s):  
Data Mining ◽  
Debris Flow ◽  
Airborne Lidar ◽  
Multivariate Adaptive Regression Splines ◽  
Slope Aspect ◽  
Support Vector ◽  
Mountainous Area ◽  
Topographic Wetness Index ◽  
Conditioning Factors ◽  
Debris Flow Susceptibility

Cameron Highland is a popular tourist hub in the mountainous area of Peninsular Malaysia. Most communities in this area suffer frequent incidence of debris flow, especially during monsoon seasons. Despite the loss of lives and properties recorded annually from debris flow, most studies in the region concentrate on landslides and flood susceptibilities. In this study, debris-flow susceptibility prediction was carried out using two data mining techniques; Multivariate Adaptive Regression Splines (MARS) and Support Vector Regression (SVR) models. The existing inventory of debris-flow events (640 points) were selected for training 70% (448) and validation 30% (192). Twelve conditioning factors namely; elevation, plan-curvature, slope angle, total curvature, slope aspect, Stream Transport Index (STI), profile curvature, roughness index, Stream Catchment Area (SCA), Stream Power Index (SPI), Topographic Wetness Index (TWI) and Topographic Position Index (TPI) were selected from Light Detection and Ranging (LiDAR)-derived Digital Elevation Model (DEM) data. Multi-collinearity was checked using Information Factor, Cramer’s V, and Gini Index to identify the relative importance of conditioning factors. The susceptibility models were produced and categorized into five classes; not-susceptible, low, moderate, high and very-high classes. Models performances were evaluated using success and prediction rates where the area under the curve (AUC) showed a higher performance of MARS (93% and 83%) over SVR (76% and 72%). The result of this study will be important in contingency hazards and risks management plans to reduce the loss of lives and properties in the area.

Sign in / Sign up

Export Citation Format

Share Document