Next Article in Journal
Multi-Criteria Assessment of Spatial Robust Water Resource Vulnerability Using the TOPSIS Method Coupled with Objective and Subjective Weights in the Han River Basin
Previous Article in Journal
From a Systematic Literature Review to a Classification Framework: Sustainability Integration in Fashion Operations
Open AccessArticle

An RVM-Based Model for Assessing the Failure Probability of Slopes along the Jinsha River, Close to the Wudongde Dam Site, China

1
Key Laboratory of Shale Gas and Geoengineering, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China
2
College of Construction Engineering, Jilin University, Changchun 130026, China
*
Author to whom correspondence should be addressed.
Academic Editor: Vincenzo Torretta
Sustainability 2017, 9(1), 32; https://doi.org/10.3390/su9010032
Received: 27 October 2016 / Revised: 16 December 2016 / Accepted: 21 December 2016 / Published: 27 December 2016
(This article belongs to the Section Environmental Sustainability and Applications)

Abstract

Assessing the failure potential of slopes is of great significance for land use and management. The objective of this paper is to develop a novel model for evaluating the failure probability of slopes based on a relevance vector machine (RVM), with a special attention to the characteristics of failed slopes along the lower reaches of the Jinsha River, close to the Wudongde dam site. Seven parameters that influence the occurrence of landslides were selected as environmental factors; namely lithology, slope angle, slope height, slope aspect, slope structure, distance from faults, and land use. A total of 55 landslides mapped in the study area were used to train and test the RVM model. The results suggest that the accuracy of the model in predicting the failure probability of slopes, using both training and testing data sets, is very high and deemed satisfactory. To validate the model performance, it was applied to 28 landslide cases identified in the upper reaches of the Jinsha River, where environmental and geological conditions are similar to those of the study area. An accuracy of approximately 92.9% was obtained, which demonstrates that the RVM model has a good generalization performance.
Keywords: landslide; relevance vector machine; influencing factor; failure probability landslide; relevance vector machine; influencing factor; failure probability

1. Introduction

Landslides are among the most notable geological processes that frequently occur in mountainous regions, resulting in financial losses measured in hundreds of billions of euros annually, injuries, and fatalities [1,2,3]. These disasters have caught unprecedented attention in the world; lots of researchers are continuously carrying out relevant research, mainly focusing on the prediction of landslides [4,5].
Various approaches have been developed for landslide hazard assessment, and can be grouped into three broad categories; analytic, statistical, and soft computing methods [6]. Analytic approaches consider the failure mechanisms of slopes and can provide an accurate prediction for the instability of slopes. However, when the study area is large, application of these approaches may be difficult. Statistical analyses such as discriminant analysis [4,7], logistic regression [8,9], and Bayes learning [10,11], are deemed to be more suitable for geological hazard assessment in large and complex areas [12,13]. With the development of science and technology, soft computing techniques, such as data mining and artificial intelligence, have also been widely used in geological hazard assessment. Examples of these approaches include artificial neural networks [14,15,16,17], genetic algorithms [18,19], decision trees [20,21], and support vector machines [22,23,24,25]. However predictions provided by these methods are not probabilistic.
Hybrid methods, which are established by combining statistical approaches and artificial intelligence, have also been adopted for assessing geological hazards; these include artificial neural network (ANN)-Bayes analysis [14], ANN-fuzzy logic [26], and neuro–fuzzy inference systems [27,28]. However the ANN-based approaches cannot provide objective and steady assessment results because their outcomes are operator dependent [13,15].
The Bayes learning algorithm is considered to be an effective tool for knowledge representation and reasoning under the influence of uncertainty [10]. Based on this algorithm, a recently developed machine learning technique, relevance vector machine (RVM), was originally introduced by Tipping [29]. As a Bayesian treatment of the sparse learning problem, the RVM can yield a probabilistic output [30].
In this study, a novel empirical model for slope failure analyses based on RVM is presented. We selected the lower reaches of the Jinsha River close to the Wudongde dam site as the study area; 55 landslides mapped in the region were utilized to train and test the RVM model. To evaluate the validity of the model, it was applied to another landslide site where the environmental conditions are similar to those of the study area.

2. Study Area

The study area (Figure 1) lies along the lower reaches of the Jinsha River and is the reservoir region of the Wudongde hydropower station, which is located in the mountains separating the Sichuan and Yunnan provinces. The occurrence of landslides not only poses a threat to human lives and properties, but also affects the stability of the Wudongde dam. Thus assessing the failure potential of slopes in this area is of great significance.
The elevation ranges from 740 to 3900 m. This area experiences a low-latitude plateau subtropical monsoon climate characterized by plenty of sun and large evaporation capacity throughout the year [31]. The mean annual temperature is 20.9 °C. It receives a mean annual rainfall varying from 600 to 800 mm, while the mean annual evaporation is 698 mm.

2.1. Geological and Geomorphological Settings

From the tectonic standpoint, the study area is located in the eastern section of the Tethys-Himalaya tectonic domain, which is one of the tectonic zones of the Himalaya characterized by intense compressing and folding. The predominant regional structures are large-scale faults constituting the famous Chuan-Dian N-S tectonic belt [32]. A total of 13 regional faults are situated in this region and dominantly trend approximately N-S (Figure 2). Several strong earthquakes have been triggered by these faults since 1955 [33], such as the Lazha earthquake (magnitude scale 6.7, 1955) which was triggered by the Tanglang-Yimeng fault, and the Panzhihua earthquake (magnitude scale 6.1, 2008), triggered by the Mopanshan-Lvzhijiang fault.
The geology is comprised of two major components; a pre-Sinian crystalline basement and a Sinian-Cretaceous sedimentary cover. The former is mainly composed of a range of metamorphic rocks (phyllite, slate and schist), which widely outcrop along the Jinsha River. The latter consists of limestone, sandstone, mudstone, and shale formations and is also widespread.
The geomorphological settings reflect the complex interplay between the geological and structural conditions of the area. Steep topographical characteristics predominate this region, with the average slope angle ranging from 30° to 45°. The valleys present a mountain canyon geomorphology. Geomorphic features include cliffs, ridges, gorges, rocky slopes, and Quaternary deposits along the river valleys. The distribution and extension of the river network and ridges is controlled by the structures to some extent. The effect of high relief and structural control is also well reflected by deep gorges and narrow valleys carved by numerous channels.
Phyllite, slate, schist, shale, and mudstone are strongly weathered and fractured and are prone to slope failures. Quaternary deposits composed of alluvial and eluvial deposits often outcrop as a cover layer on the riverbed and gentle slopes and are affected by transitional or rotational landslides triggered by the undercutting of the Jinsha River.

2.2. Landslide Identification

Landslide identification was carried out using SPOT5 remote sensing images and field surveys. The SPOT5 images, which were obtained by the SPOT5 satellite launched in 2002 with a multispectral resolution of 10 m and a panchromatic resolution of 2.5 m, have been largely utilized in geological hazard surveys. A series of field investigations, aimed at the confirmation of the mapped landslides through remote sensing images and the investigation of the link between the occurrence of landslides and environmental factors, were conducted. In general, there are three main types of landslides present in the study area; translational movements (55 locations), rock falls (26 locations), and debris flows (239 locations). Each type of landslide has different mechanism requiring separate study for the spatial prediction of landslides. Therefore, in this study, only the 55 translational landslides (Figure 3) were used for analysis. At the time of fieldwork, 44% of the slope movements were classified as active, while the class of dormant movements corresponds to 33%, and 23% of the slope movements were considered stabilized. The highest frequency of landslide phenomena was recorded in mudstones and metamorphic rock formations (phyllite, slate, and schist). The smallest landslide covered an area of 0.03 km2, while the largest one was 4.2 km2. Figure 4 gives some examples of the landslides.

3. Influencing Factors

Landslide hazard assessment is often performed based on the assumption that future landslides will occur in the areas where environmental conditions are similar to those of past and present failures [34]. Therefore it relies strongly on identifying landslide scars, characterizing the properties of failed sites, and confirming the link between landslide distribution and spatial variation of parameters [35]. There is no standard principle for selecting the influencing parameters because they often vary from one area to another. However it is commonly recognized that the parameter selection depends on the environmental conditions of the study area, the mechanisms of failed slopes, and the scale of analyses [17]. It should be implemented according to the data availability and the significance of data in relation to the problem at question [23].
Based on the review of previous literature [13,16,17,25] and field surveys, seven factors that were identified as causative and triggering factors for landslide activity in the study area were selected to predict the failure potential of slopes. They are lithology, slope angle, slope aspect, slope height, slope structure, distance from faults, and land use. This research selected a single slope as a computing unit [16], and values of the influence factors were derived for each slope in the database. Table 1 presents the factors and their classes used in this study. The frequency distribution of landslide occurrence in each class is shown in Figure 5.

3.1. Lithology

Lithology has been considered to be one of the main parameters influencing the stability of slopes. Since different lithologic units have different slope stability performances, they are very important for landslide prediction [4]. The large surface development of formations, such as schist formations, flysch sediments, and metamorphic rock formations with anisotropic geomechanical behavior, facilitates the manifestation of abundant slope failures. The lithology was derived from a lithologic map at a 1:100,000 scale and was grouped into three categories (Table 1) according to Peng et al. [25] and Fourniadis et al. [36]. Figure 5a shows that approximately 87% of the landslides occurred on Quaternary deposits, strongly weathered sandstones, mudstones, and metamorphic rocks (phyllite, slate and schist).

3.2. Slope Angle

Slope angle is an essential factor controlling the stability of a slope. The shear stress induced by gravity increases with the increase of the slope angle; therefore landslides tend to occur more frequently on steeper slopes [24]. The slope angle was measured from the slope profile that was derived from the digital elevation model (DEM). Note that a slope angle of 10° was taken as the threshold because very few slopes less than that angle have failed [16]. The slope angle of the study area was divided into five classes (Table 1): 0°–10°, 10°–20°, 20°–30°, 30°–40°, and >40°. Figure 5b illustrates that the largest numbers of landslides were recorded in the classes of 20°–30° (49.1%) and 10°–20° (32.7%).

3.3. Slope Height

Slope height denotes the difference value between the head and tail elevations of a slope. A slope with higher height often indicates a higher probability of experiencing a landslide event [37,38]. The slope height was directly derived from the DEM. As listed in Table 1, the slope height was partitioned into four classes according to Zhao et al. [38] and flied surveys. The distribution of landslides in the height classes is show in Figure 5c.

3.4. Slope Aspect

Aspect controls some microclimatic parameters, such as exposure to sunlight and winds, rainfall intensity, and soil moisture [17]. It was obtained from the DEM and was categorized into four classes according to Conforti et al. [17], as shown in Table 1. The relationship between lithology and failed slopes is presented in Figure 5d.

3.5. Slope Structure

Slope structure represents the spatial relationship between the rock strata and slope face. Slopes in the study area were measured from field investigations and were classified into four structural categories (Table 1): anti-dip, insequent, transverse, and dip-bedded. Field investigations demonstrate that dip-bedded slopes are prone to failures because of the erosion of slope toes caused by the Jinsha River. Figure 5e indicates that slope failures predominantly occurred on dip-bedded slopes, occupying 70.9% of the landslides in the area. However only 5.5% of the landslides occurred on anti-dip slopes.

3.6. Distance from Faults

Field evidence suggests a strong influence of tectonic settings on the occurrence of landslides [39]. The distance from faults was obtained from the geological map of the region (1:100,000). Approximately 49.1% (Figure 5f) of slope failures occurred in the sites with a minimum distance of less than 500 m from faults.

3.7. Land Use

Land use has been used as a predisposing factor in landslide hazard assessment. It was divided into three classes (Table 1) based on field surveys. Figure 5g shows that barren land and residential land have significant influence on the occurrence of landsides, and both of them occupy 41.8% of slope failures.

4. Relevance Vector Machine

RVM is based on a Bayesian learning framework and can output the probabilities of class membership. It has the same functional form as the support vector machine (SVM) and shares many of the characteristics of SVM whilst avoiding the SVM’s main limitations [40]. The structure of the RVM is represented by the sum of product of weights and kernel functions, which is expressed as follows [41]:
y ( x ; w ) = i = 1 N w i K ( x , x i ) + w 0
where wi is the weight and K(x, xi) is a kernel function. The commonly used kernel is the Gaussian kernel K(x, xi) = exp(–||xxi||22), where σ is the kernel parameter controlling the sensitivity of the kernel. This function is not sensitive to outliers and can handle the case in which the relationship between class labels and attributes is nonlinear [13].
In this paper, the basic theory of RVM classification is briefly introduced. For further details of RVM, readers can refer to Tipping [29,41] and Bishop [40]. For two-class (binary) classification, RVM is used to predict the posterior probability of class membership of one of the classes, given the input x. By applying the logistic sigmoid function σ(y) = 1/(1 + ey) to y(x) and adopting the Bernoulli distribution for p(t|w), the likelihood can be written as [40]:
p ( t | w ) = i = 1 N σ { y ( x i ; w ) } t i [ 1 σ { y ( x i ; w ) } ] 1 t i
where the targets ti {0, 1}. In this study, 0 and 1 denote the stable and failed cases, respectively. The weights w cannot be analytically obtained and so are denied the closed-form expression for either the weight posterior p(w|t, α) or the marginal likelihood p(t|α), with a hyper-parameter vector α. Therefore, according to Tipping [40], the following approximation procedure proposed by MacKay [42] and based on Laplace’s method is utilized:
(1) For the current fixed values of α, the most probable weights wMP are found, giving the location of the mode of the posterior distribution. Since p(w|t, α) p(t|w) p(w|α), this is equivalent to finding the maximum, over w, of
log { p ( t | w ) p ( w | α ) } = i = 1 N [ t i log y i + ( 1 t i ) log ( 1 y i ) 1 2 w T A w ]
where yi = σ{y(xi; w)} and A = diag(α0, α1, α2, …, αN) for the current values of α. Since Equation (3) is a penalized, logistic, log-likelihood function, iterative maximization is required. The iteratively reweighted least-square algorithm is adopted to find wMP in the following procedure.
(2) Equation (3) is differentiated twice to give:
w w log p ( w | t , α ) | w MP = ( Φ T B Φ + A )
where B = diag0, β1, β2, …, βN) is diagonal matrix with elements βi = σ{y(xi)}[1 − σ{y(xi)}], and Φ = [ϕ(x1), ϕ(x2), …, ϕ(xN)]T is the N × (N + 1) design matrix with ϕ(xi) = [1, K(xi, x1), K(xi, x2), …, K(xi, xN)]T. This is then negated and inverted to give the covariance ∑ for a Gaussian approximation to the posterior over weights centered at wMP:
= ( Φ T B Φ + A ) 1
(3) Using the statistics ∑ and wMP of the Gaussian approximation, MacKay’s approach is used to update the hyper-parameter α by
α i n e w = 1 α i i i w M P 2
where ∑ii is the ith diagonal element of the covariance ∑, and wMP = ∑ΦTBt.
During the optimization process, many αi will have large (in principle infinite) values; thus the values of the corresponding weights will tend toward zero. Therefore these weights and the corresponding basis functions are removed from the model and thus play no role in making predictions for new inputs. Those examples remaining with wi ≠ 0 are termed relevance vectors.

5. Results and Discussions

5.1. Data Processing

RVM models require that each environmental parameter should be represented by a vector of real numbers. In this work, an m-digit number is used to represent an m-category attribute [16]. Only one of the digits is one and the others are zero. For example, a four-category attribute (e.g., slope height in Table 1) is represented by (1,0,0,0), (0,1,0,0), (0,0,1,0) or (0,0,0,1). Therefore the seven influencing factors of each slope can be converted into a vector of 27 bites.

5.2. Preparation of Training and Testing Data

For a two-class RVM, ‘stable’ sites are necessary. In this study, 20 ‘stable’ sites were randomly chosen from the non-landslide sites where slope angles are less than 10°, a value which was taken as the threshold because very few slopes less than that angle have failed. The landslide data and non-landslide data were randomly divided into two groups [16]: (1) group 1, which contained 80% of the landslides (45 cases) and in which the same ratio of the non-landslides (16 cases) formed the training dataset; and (2) group 2, which contained the remaining 20% of the landslides and in which non-landslides was used as testing dataset for verifying the performance of the model. The target values for landslides were given a value of 1, while a 0 value was assigned to those of non-landslides in the training dataset.

5.3. Parameter Determination

In an RVM, the controlling parameter (i.e., the kernel parameter σ) needs to be defined. Considering that there is a lack of information in most related papers concerning the determination of the optimal σ for RVM, a procedure of its estimation was conducted, in which several different values of σ were checked to determine which one of them gives better classification capabilities. As landslide hazard assessment is linearly non-separate problem, a cross-validation approach is adopted for the parameter search [13,30]. The accuracy is defined as the percentage of correct predictions for slope failure probabilities among all testing slopes [30]. In this research, “correct” could be defined as follows: for a failed slope, the model’s prediction is considered “correct” if the model’s output is greater than 0.5; on the other hand, for a stable slope, it is considered “correct” if the model’s output is less than 0.5. In this work, the 4-fold cross-validation technique is used by dividing the training dataset into 4 folds [30]; one fold (25%) is used as the validation set and the combination of the remaining three folds (75%) is used for training. By iterating each fold as the validation set and the aggregation of other folds as the training set, four validation accuracies can be obtained. The average of these accuracies is taken as the cross-validation accuracy (CVA) for a given σ. According to Wang et al. [30], several different values of σ are considered (Table 2). The value which yields the highest CVA is deemed to be the optimal value of σ. As shown in Table 2, the RVM provides the highest CVA value of 98.3% when σ = 4, which is in accordance with the results obtained by Wang et al. [43]. Therefore the ideal value of σ is 4.

5.4. Training and Testing of the RVM Model

Figure 6 presents a flow chart for the training and testing process. The training dataset was used to train and develop the RVM model. During the training process, many weights will have values very close to zero, and their corresponding basis functions are removed from the model. The examples remaining with wi ≠ 0 are termed relevance vectors and are used for slope failure prediction. Table 3 lists the relevance vectors and their corresponding weights. As shown in Table 3, the RVM model employs 27 cases (45%) of the training dataset as relevance vectors, including 17 failed cases and 10 stable cases. It is worth mentioning here that the relevance vectors used in the RVM model represent prototypical examples. These examples exhibit the essential features of the information of the data, and thus are able to transform the input data into the specified targets [44].
The goal of the RVM model is to correctly classify a given slope to the target observation of either failed slope (t = 1) or stable slope (t = 0). For a given slope with particular environmental factors described by a vector xi, its failure probability is represented by p(t = 1|xi), which is computed by Equation (3). The classification rule of the RVM used in this study is the following: if p(t = 1|xi) > 0.5, the slope is classified into the occurrence of a landslide; if p(t = 1|xi) < 0.5, it is divided into the absence of a landslide.
The RVM model was applied to predict the failure probabilities of the 60 slopes in the training dataset. The results (Figure 7) show that all the 45 failed slopes have the failure probabilities of more than 0.8, a value which is high enough for the occurrence of a landslide. In addition, the values of failure probability for the 15 stable slopes are all less than 0.25, suggesting that these slopes are impossible for suffering from slope failures. Therefore the prediction accuracy for the 60 slopes reaches 100%.
To test the performance of the model, it was then applied to the testing dataset. The failure probability for each slope is listed in Table 4. For the 15 failed slopes, one slope has a probability of approximately 0.83 to fail and the others have failure probabilities of more than 0.95, whivh is very close to 1. All the stable slopes have failure probabilities of less than 0.25. Thus the accuracy of the classification of the slopes in the testing dataset is also 100%. The results demonstrate that the RVM model can provide a stable reliable prediction for landslide hazards in the study area.

5.5. Evaluation of the Model

In this section, 28 landslides mapped in the upper reaches of the Jinsha River, close to the Rimian dam (Figure 1),where environmental conditions are similar to those of the study area [45], were selected as an example to evaluate the performance of the model. The distribution of the landslides is shown in Figure 8. Similar to the study area, this area is also located in the Chuandian N-S tectonic belt, with steep topology controlled by several large-scale faults. The main rock types include limestone, phyllite, schist, and shale. The mean annual precipitation and evaporation range from 350 to 650 mm, and from 750 to 2000 mm, respectively. The annual average temperature varies between 13.8 and 19.2 °C.
Table 5 lists the parameters of these slopes. The failure probabilities of these slopes were predicted using the RVM model, and the results are shown in Table 5. Among the 28 failed slopes, there are only two slopes that were wrongly partitioned into the group of stable ones, whose failure probabilities as calculated by the RVM model are less than 0.5. The prediction accuracy among the 28 slopes is approximately 92.9%, which is deemed satisfactory. Therefore the RVM model with seven triggering factors has a good prediction performance and could be extended to other sites where environmental conditions are similar to those of the study area.

6. Conclusions

This paper presents a novel approach for assessing the failure probability of slopes based on a relevance vector machine (RVM). The landslides mapped in the lower reaches of the Jinsha River were used to train and test the RVM model. Seven parameters, namely lithology, slope angle, slope height, slope aspect, slope structure, distance from faults, and land use, were selected as influencing factors of slope failures. The trained RVM model with seven factors is shown to be effective in classifying slopes into groups of stable ones and failed ones. The accuracies of the model in predicting the failure potential of slopes, using both training and testing data sets, are all very high and deemed satisfactory. To evaluate the model’s performance, it was applied to landslide sites identified in the lower reaches of the Jinsha River, where environmental conditions are similar to those of the study area. An accuracy of approximately 92.9% was obtained, indicating that the model has a good generalization performance.
The study demonstrates that the RVM model is stable and reliable and could be used to predict the occurrence of translational landslides in hazard mitigation and guarding systems. Another important advantage of the model is that it can provide a probabilistic prediction for slope failures.

Acknowledgments

This work was financially supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (No. XDB10030100), the China Postdoctoral Science Foundation funded project (No. 2015M580135), the National Natural Science Foundation of China (NSFC) (Nos. 41372324 and 41602327) and the Chinese Special Funds for Major State Basic Research Project (No. 2014CB046901).

Author Contributions

All authors were responsible for different parts of this paper. Yanyan Li and Jianping Chen conducted field investigations and wrote the whole paper; Yanjun Shang revised the paper.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Aleotti, P.; Chowdhury, R. Landslide hazard assessment: Summary review and new perspectives. Bull. Eng. Geol. Environ. 1999, 58, 21–44. [Google Scholar] [CrossRef]
  2. Pappalardo, G.; Mineo, S.; Rapisarda, F. Rockfall hazard assessment along a road on the Peloritani Mountains (northeastern Sicily, Italy). Nat. Hazards Earth Syst. Sci. 2014, 14, 2735–2748. [Google Scholar] [CrossRef][Green Version]
  3. Zhou, S.; Chen, G.; Fang, L.; Nie, Y. GIS-Based integration of subjective and objective weighting methods for regional landslides susceptibility mapping. Sustainability 2016, 8, 334. [Google Scholar]
  4. Carrara, A.; Merenda, L. GIS techniques and statistical models in evaluating landslide hazard. Earth Surf. Proc. Land. 1991, 16, 427–445. [Google Scholar] [CrossRef]
  5. Saroglou, H.; Marinos, V.; Marinos, P.; Tsiambaos, G. Rockfall hazard and risk assessment: An example from a high promontory at the historical site of Monemvasia, Greece. Nat. Hazards Earth Syst. Sci. 2012, 12, 1823–1836. [Google Scholar] [CrossRef][Green Version]
  6. Pradhan, B. A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Comput. Geosci. 2013, 51, 350–365. [Google Scholar] [CrossRef][Green Version]
  7. Günther, A.; Reichenbach, P.; Malet, J.P.; Van Den Eeckhaut, M.; Hervás, J.; Dashwood, C.; Guzzetti, F. Tier-Based approaches for landslide susceptibility assessment in Europe. Landslides 2012, 10, 529–546. [Google Scholar] [CrossRef][Green Version]
  8. Ayalew, L.; Yamagishi, H. The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, central Japan. Geomorphology 2005, 65, 15–31. [Google Scholar] [CrossRef]
  9. Manzo, G.; Tofani, V.; Segoni, S.; Battistini, A.; Catani, F. GIS techniques for regional scale landslide susceptibility assessment: The Sicily (Italy) case study. Int. J. Geogr. Inf. Sci. 2013, 27, 1433–1452. [Google Scholar] [CrossRef]
  10. Liang, W.J.; Zhuang, D.F.; Dong, J.; Pan, J.J.; Ren, H.Y. Assessment of debris flow hazards using a Bayesian Network. Geomorphology 2012, 171–172, 94–100. [Google Scholar] [CrossRef]
  11. Song, Y.Q.; Gong, J.H.; Gao, S.; Wang, D.C.; Cui, T.J.; Li, Y.; Wei, B.Q. Susceptibility assessment of earthquake-induced landslides using Bayesian network: A case study in Beichuan, China. Comput. Geosci. 2012, 42, 189–199. [Google Scholar] [CrossRef]
  12. Guzzetti, F.; Reichenbach, P.; Ardizzone, F.; Cardinali, M.; Galli, M. Estimating the quality of landslide susceptibility models. Geomorphology 2006, 81, 166–184. [Google Scholar] [CrossRef]
  13. Yao, X.; Tham, L.G.; Dai, F.C. Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China. Geomorphology 2008, 101, 572–582. [Google Scholar] [CrossRef]
  14. Lee, S.; Ryu, J.; Won, J.; Park, H. Determination and application of weights for landslide susceptibility mapping using an artificial neural network. Eng. Geol. 2004, 71, 289–302. [Google Scholar] [CrossRef]
  15. Ermini, L.; Catani, F.; Casagli, N. Artificial neural network to landslide susceptibility assessment. Geomorphology 2005, 66, 327–343. [Google Scholar] [CrossRef]
  16. Lin, H.M.; Chang, S.H.; Wu, J.H.; Juang, C.H. Neural network-based model for assessing failure potential of highway slopes in the Alishan, Taiwan Area: Pre- and post-earthquake investigation. Eng. Geol. 2009, 104, 280–289. [Google Scholar] [CrossRef]
  17. Conforti, M.; Pascale, S.; Robustelli, G.; Sdao, F. Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (Northern Calabria, Italy). Cetena 2014, 113, 236–250. [Google Scholar] [CrossRef]
  18. Chang, T.C.; Chien, Y.H. The application of genetic algorithm in debris flows prediction. Environ. Geol. 2007, 53, 339–347. [Google Scholar] [CrossRef]
  19. Liu, S.H.; Lin, C.W.; Tseng, C.M. A statistical model for the impact of the 1999 Chi-Chi earthquake on the subsequent rainfall-induced landslides. Eng. Geol. 2013, 156, 11–19. [Google Scholar] [CrossRef]
  20. Saito, H.; Nakayama, D.; Matsuyama, H. Comparison of landslide susceptibility based on a decision-tree model and actual landslide occurrence: The Akaishi Mountains, Japan. Geomorphology 2009, 109, 108–121. [Google Scholar] [CrossRef]
  21. Wan, S. A spatial decision support system for extracting the core factors and thresholds for landslide susceptibility map. Eng. Geol. 2009, 108, 237–251. [Google Scholar] [CrossRef]
  22. Samui, P. Slope stability analysis: A support vector machine approach. Environ. Geol. 2008, 56, 255–267. [Google Scholar] [CrossRef]
  23. Marjanović, M.; Kovačević, M.; Bajat, B.; Voženílek, V. Landslide susceptibility assessment using SVM machine learning algorithm. Eng. Geol. 2011, 123, 225–234. [Google Scholar] [CrossRef]
  24. Xu, C.; Dai, F.C.; Xu, X.W.; Lee, Y.H. GIS-Based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang River watershed, China. Geomorphology 2012, 145–146, 70–80. [Google Scholar] [CrossRef]
  25. Peng, L.; Niu, R.Q.; Huang, B.; Wu, X.L.; Zhao, Y.N.; Ye, R.Q. Landslide susceptibility mapping based on rough set theory and support vector machines: A case of the Three Gorges area, China. Geomorphology 2013, 101, 572–582. [Google Scholar] [CrossRef]
  26. Kanungo, D.P.; Arora, M.K.; Sarkar, S.; Gupta, R.P. A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas. Eng. Geol. 2006, 85, 347–366. [Google Scholar] [CrossRef]
  27. Vahidnia, M.H.; Alesheikh, A.A.; Alimohammadi, A.; Hosseinali, F. A GIS-based neuro-fuzzy procedure for integrating knowledge and data in landslide susceptibility mapping. Comput. Geosci. 2010, 36, 1101–1114. [Google Scholar] [CrossRef]
  28. Bui, D.T.; Pradhan, B.; Lofman, O.; Revhaug, I.; Dick, O.B. Landslide susceptibility mapping at Hoa Binh province (Vietnam) using an adaptive neuro-fuzzy inference system and GIS. Comput. Geosci. 2012, 45, 199–211. [Google Scholar]
  29. Tipping, M.E. The relevance vector machine. In Advances in Neural Information Processing Systems; Solla, S.A., Leen, T.K., Muller, K.R., Eds.; MIT Press: Cambridge, MA, USA, 2000; Volume 12, pp. 652–658. [Google Scholar]
  30. Wang, X.D.; Ye, M.Y.; Duanmu, C.J. Classification of data from electronic nose using relevance vector machines. Sens. Actuators B Chem. 2009, 140, 143–148. [Google Scholar] [CrossRef]
  31. Zhang, W.; Li, H.Z.; Chen, J.P.; Zhang, C.; Xu, L.M.; Sang, W.F. Comprehensive hazard assessment and protection of debris flows along Jinsha River close to the Wudongde dam site in China. Nat. Hazards 2011, 58, 459–477. [Google Scholar] [CrossRef]
  32. Chen, H.; Hu, J.M.; Qu, H.J.; Wu, G.L. Early Mesozoic structural deformation in the Chuandian N-S Tectonic Belt, China. Sci. China Ser. D 2011, 54, 1651–1664. [Google Scholar] [CrossRef]
  33. Zhang, W.; Chen, J.P.; Wang, Q.; An, Y.; Qian, X.; Xiang, L.; He, L. Susceptibility analysis of large-scale debris flows based on combination weighting and extension methods. Nat. Hazards. 2013, 66, 1073–1100. [Google Scholar] [CrossRef]
  34. Rozos, D.; Pyrgiotis, L.; Skias, S.; Tsagaratos, P. An implementation of rock engineering system for ranking the instability potential of natural slopes in Greek territory. An application in Karditsa County. Landslides 2008, 5, 261–270. [Google Scholar] [CrossRef]
  35. Che, V.B.; Kervyn, M.; Suh, C.E.; Fontijn, K.; Ernst, G.G.J.; del Marmol, M.-A.; Trefois, P.; Jacobs, P. Landslide susceptibility assessment in Limbe (SW Cameroon): A field calibrated seed cell and information value method. Catena 2012, 92, 83–98. [Google Scholar] [CrossRef]
  36. Fourniadis, I.G.; Liu, J.G.; Mason, P.J. Landslide hazard assessment in the Three Gorges area, China, using ASTER imagery: Wushan—Badong. Geomorphology 2007, 84, 126–144. [Google Scholar] [CrossRef]
  37. Dai, F.C.; Lee, C.F. Landslide characteristics and slope instability modeling using GIS, Lantau Island, Hong Kong. Geomorphology 2002, 42, 213–228. [Google Scholar] [CrossRef]
  38. Zhao, W.H.; Huang, R.Q.; Ju, N.P.; Zhao, J.J. Assessment model for earthquake-triggered landslides based on quantification theory I: Case study of Jushui River basin in Sichuan, China. Nat. Hazards 2014, 70, 821–838. [Google Scholar] [CrossRef]
  39. Mineo, S.; Pappalardo, G.; Rapisarda, F.; Cubito, A.; Di Maria, G. Integrated geostructural, seismic and infrared thermography surveys for the study of an unstable rock slope in the Peloritani Chain (NE Sicily). Eng. Geol. 2015, 195, 225–235. [Google Scholar] [CrossRef]
  40. Bishop, C.M. Pattern Recognition and Machine Learning; Springer: New York, NY, USA, 2006. [Google Scholar]
  41. Tipping, M.E. Sparse Bayesian leaning and relevance vector machine. J. Mach. Learn. Res. 2001, 1, 211–244. [Google Scholar]
  42. Mackay, D.J.C. The evidence framework applied to classification networks. Neural Comput. 1992, 4, 720–736. [Google Scholar] [CrossRef]
  43. Wang, F.; Gou, B.; Qin, Y. Modeling tunneling-induced ground surface settlement development using a wavelet smooth relevance vector machine. Comput. Geotech. 2013, 54, 125–132. [Google Scholar] [CrossRef]
  44. Samui, J.; Lansivaara, T.; Kim, D. Utilization relevance vector machine for slope reliability analysis. Appl. Soft Comput. 2011, 11, 4036–4040. [Google Scholar] [CrossRef]
  45. Zhou, F.J. Early Intelligence Identification Methods of Stability and Fuzzy Synthetic Prediction of Hazard for Landslides in Rimian Hydropower Station. Ph.D. Thesis, Jilin University, Changchun, China, 2013; p. 225. [Google Scholar]
Figure 1. Location map of the study area.
Figure 1. Location map of the study area.
Sustainability 09 00032 g001
Figure 2. Regional tectonic framework map [33].
Figure 2. Regional tectonic framework map [33].
Sustainability 09 00032 g002
Figure 3. Landslide map of the study area.
Figure 3. Landslide map of the study area.
Sustainability 09 00032 g003
Figure 4. Examples of slope failures in the study area. (a) Xiaochatou landslide; (b) Daopo landslide.
Figure 4. Examples of slope failures in the study area. (a) Xiaochatou landslide; (b) Daopo landslide.
Sustainability 09 00032 g004
Figure 5. Frequency of landslide occurrence in each category. (a) Lithology; (b) Slope angle; (c) Slope height; (d) Slope aspect; (e) Slope structure; (f) Distance from faults; (g) Land use.
Figure 5. Frequency of landslide occurrence in each category. (a) Lithology; (b) Slope angle; (c) Slope height; (d) Slope aspect; (e) Slope structure; (f) Distance from faults; (g) Land use.
Sustainability 09 00032 g005
Figure 6. Flow chart of the training and testing process.
Figure 6. Flow chart of the training and testing process.
Sustainability 09 00032 g006
Figure 7. Failure probabilities for slopes in the training dataset.
Figure 7. Failure probabilities for slopes in the training dataset.
Sustainability 09 00032 g007
Figure 8. Distribution of landslides close to the Rimian dam site.
Figure 8. Distribution of landslides close to the Rimian dam site.
Sustainability 09 00032 g008
Table 1. Landslide influencing factors and their classifications.
Table 1. Landslide influencing factors and their classifications.
DescriptionClass ID
1. Lithology
 Limestones and massive sandstones1
 Sandstones, shale, schist and mudstones2
 Mixed layers, and Quaternary deposits3
2. Slope angle
 0°–10°1
 10°–20°2
 20°–30°3
 30°–40°4
 >40°5
3. Slope height
 <100 m1
 100–200 m2
 200–300 m3
 >300 m4
4. Slope aspect
 315°–45° (N)1
 225°–315° (W)2
 45°–135° (E)3
 135°–225° (S)4
5. Slope structure
 Anti-dip1
 Insequent2
 Transverse3
 Dip-bedded4
6. Distance from faults
 >1500 m1
 1000–1500 m2
 500–1000 m3
 0–500 m4
7. Land use
 Barren land1
 Agriculture2
 Residential3
Table 2. Validation results obtained by the 4-fold cross-validation approach.
Table 2. Validation results obtained by the 4-fold cross-validation approach.
σ1234
CVA93.3%97.9%97.5%98.3%
Table 3. Relevance vectors and their weights.
Table 3. Relevance vectors and their weights.
SlopeStatusParametersWeight
LithologySlope AngleSlope HeightSlope AspectSlope StructureDistance from FaultsLand Use
R1Failed22434130.4
R2Failed33444435.69
R3Failed13443410.28
R4Failed24414210.06
R5Failed233344118.18
R6Failed22314432.69
R7Failed33414410.13
R8Failed23314210.46
R9Failed23334210.54
R10Failed33434410.03
R11Failed22314432.69
R12Failed22434430.08
R13Failed32334430.01
R14Failed22314432.69
R15Failed24244420.67
R16Failed24442420.03
R17Failed23433430.06
R18Stable3112123−2.46
R19Stable2113241−0.24
R20Stable2113131−12.81
R21Stable2113323−1.99
R22Stable1114221−0.42
R23Stable2112232−4.36
R24Stable1112212−1.4
R25Stable1113312−6.83
R26Stable1113341−1.35
R27Stable2111121−0.02
Table 4. Failure probabilities for slopes in the testing dataset.
Table 4. Failure probabilities for slopes in the testing dataset.
SlopeStatusParametersFailure Probability
LithologySlope AngleSlope HeightSlope AspectSlope StructureDistance from FaultsLand Use
T1Failed23222310.826
T2Failed22214230.997
T3Failed22414130.998
T4Failed32244330.985
T5Failed35314130.998
T6Failed23414320.992
T7Failed23424411.000
T8Failed32224330.959
T9Failed23333431.000
T10Failed33424420.999
T11Failed32414120.988
T12Stable11133330.003
T13Stable11144210.243
T14Stable31121320.001
T15Stable11122310.003
Table 5. Prediction results for failed slopes close to the Rimian dam site.
Table 5. Prediction results for failed slopes close to the Rimian dam site.
SlopeParametersFailure Probability
LithologySlope AngleSlope HeightSlope AspectSlope StructureDistance from FaultsLand Use
U133324411.000
U224424410.999
U324224410.999
U424424410.999
U522324411.000
U613232410.994
U723341411.000
U823231410.998
U924411430.985
U1013331410.999
U1133343431.000
U1233443430.998
U1322434431.000
U1423142410.992
U1533244411.000
U1632231430.959
U1732231330.407
U1823241120.788
U1933131110.293
U2023241130.935
U2134221110.461
U2233424110.996
U2333242210.966
U2434331410.994
U2533431310.739
U2613223430.975
U2734224310.908
U2812114330.740
Back to TopTop