Mapping earthquake-triggered landslide susceptibility by use of artificial neural network (ANN) models: an example of the 2013 Minxian (China) Mw 5.9 event

Tian, Yingying; Xu, Chong; Hong, Haoyuan; Zhou, Qing; Wang, Duo

doi:10.1080/19475705.2018.1487471

Cited by 103 publications

(42 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In other studies trigger-related factors (such as PGA, shake maps, Arias Intensity) referred to the triggering event have been explicitly considered as variables in the susceptibility function (e.g. Lee et al 2008;Bai et al 2012;Xu et al 2012b;Lee et al 2002;Tian et al 2019). Such studies can be formally regarded as hazard analyses but being trained on event-based inventories and eventspecific triggers, their results are not easily generalizable to triggering events with different magnitudes.…”

Section: Introductionmentioning

confidence: 99%

Earthquake-induced landslide scenarios for seismic microzonation: application to the Accumoli area (Rieti, Italy)

Martino¹,

Battaglia²,

D’Alessandro³

et al. 2019

Bull Earthquake Eng

View full text Add to dashboard Cite

Scenarios of earthquake-induced landslides are necessary for seismic microzonation (SM) studies since they must be integrated with the mapping of instability areas. The PARSI-FAL (Probabilistic Approach to pRovide Scenarios of earthquake-Induced slope FAiLures) approach provides extensive analyses, over tens to thousands of square kilometers, and is designed as a fully comprehensive methodology to output expected scenarios which depend on seismic input and saturation conditions. This allows to attribute a rating, in terms of severity level, to the landslide-prone slope areas in view of future engineering studies and designs. PARSIFAL takes into account first-time rock-and earth-slides as well as re-activations of existing landslides performing slope stability analyses of different failure mechanisms. The results consist of mapping earthquake-induced landslide scenarios in terms of exceedance probability of critical threshold values of co-seismic displacements (P[D ≥ Dc|a(t),a y ]). PARSIFAL was applied in the framework of level 3 SM studies over the municipality area of Accumoli (Rieti, Italy), strongly struck by the 2016 seismic sequence of Central Apennines. The use of the PARSIFAL was tested for the first time to screen the Susceptibility Zones (ZS FR) from the Attention Zones (ZA FR) in the category of the unstable areas, according to the guidelines by Italian Civil Protection. The results obtained were in a GIS-based mapping representing the possibility for a landslide to be induced by an earthquake (with a return period of 475 years) in three different saturation scenarios (i.e. dry, average, full). Only 41% of the landslide-prone areas in the Municipality of Accumoli are existing events, while the remaining 59% is characterized by first-time earth-or rock-slides. In dry conditions, unstable conditions or P[D ≥ Dc|a(t),a y ] > 0 were for 54% of existing landslides, 17% of first-time rock-slides and 1% of first-time earthslides. In full saturation conditions, the findings are much more severe since unstable conditions or P[D ≥ Dc|a(t),a y ] > 0 were found for 58% of the existing landslides and for more than 80% of first-time rock-and earth-slides. Moreover, comparison of the total area of the ZA FR versus ZS FR , resulted in PARSIFAL screening reducing of 22% of the mapped ZA FR .

show abstract

Section: Introductionmentioning

confidence: 99%

Earthquake-induced landslide scenarios for seismic microzonation: application to the Accumoli area (Rieti, Italy)

Martino¹,

Battaglia²,

D’Alessandro³

et al. 2019

Bull Earthquake Eng

View full text Add to dashboard Cite

show abstract

“…Although domain-knowledge-driven qualitative approach is advantageous in predicting landslides, data-driven quantitative methods are widely used because collecting field data from landslide areas are challenging and hard to acquire [3]. Pourghasemi et al [14] reported that a variety of quantitatively-statistical, multi-criteria decision making, and machine learning-methods have been applied for predicting landslide susceptibility, of which logistical regression [15][16][17][18] is the most frequently used method, followed by the frequency ratio [19,20], weights-of-evidence [18,21], artificial neural networks [22,23], analytic hierarchy process [24,25], statistical index [26], index of entropy [27][28][29][30], and support vector machine [31,32]. Environmental data collected from fields as well as extracted from satellite images to develop landslide prediction models are diverse in nature, and therefore prone to inaccuracies [13].…”

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Assessment by Novel Hybrid Machine Learning Algorithms

et al. 2019

View full text Add to dashboard Cite

Landslides have multidimensional effects on the socioeconomic as well as environmental conditions of the impacted areas. The aim of this study is the spatial prediction of landslide using hybrid machine learning models including bagging (BA), random subspace (RS) and rotation forest (RF) with alternating decision tree (ADTree) as base classifier in the northern part of the Pithoragarh district, Uttarakhand, Himalaya, India. To construct the database, ten conditioning factors and a total of 103 landslide locations with a ratio of 70/30 were used. The significant factors were determined by chi-square attribute evaluation (CSEA) technique. The validity of the hybrid models was assessed by true positive rate (TP Rate), false positive rate (FP Rate), recall (sensitivity), precision, F-measure and area under the receiver operatic characteristic curve (AUC). Results concluded that land cover was the most important factor while curvature had no effect on landslide occurrence in the study area and it was removed from the modelling process. Additionally, results indicated that although all ensemble models enhanced the power prediction of the ADTree classifier (AUC training = 0.859; AUC validation = 0.813); however, the RS ensemble model (AUC training = 0.883; AUC validation = 0.842) outperformed and outclassed the RF (AUC training = 0.871; AUC validation = 0.840), and the BA (AUC training = 0.865; AUC validation = 0.836) ensemble model. The obtained results would be helpful for recognizing the landslide prone areas in future to better manage and decrease the damage and negative impacts on the environment.

show abstract

“…The artificial neural networks (ANN), developed based on the neurons, is one of the well-known deep learning algorithms for regression, classification, and pattern recognition challenges [53][54][55][56]. A typical ANN architecture ( Figure 2) has three layers: (a) input layer, in this case all the predictors of LSCP that also decide the number of neurons in the ANN architecture; (b) hidden layer, the recipient of all the neurons containing a specific weight, and (c) output layer, i.e., the predicted value of LSCP.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

A Hybrid Intelligence Approach to Enhance the Prediction Accuracy of Local Scour Depth at Complex Bridge Piers

et al. 2020

View full text Add to dashboard Cite

Local scour depth at complex piers (LSCP) cause expensive costs when constructing bridges. In this study, a hybrid artificial intelligence approach of random subspace (RS) meta classifier, based on the reduced error pruning tree (REPTree) base classifier, namely RS-REPTree, was proposed to predict the LSCP. A total of 122 laboratory datasets were used and portioned into training (70%: 85 cases) and validation (30%: 37 cases) datasets for modeling and validation processes, respectively. The statistical metrics such as mean absolute error (MAE), root mean squared error (RMSE), correlation coefficient (R), and Taylor diagram were used to check the goodness-of-fit and performance of the proposed model. The capability of this model was assessed and compared with four state-of-the-art soft-computing benchmark algorithms, including artificial neural network (ANN), support vector machine (SVM), M5P, and REPTree, along with two empirical models, including the Florida Department of Transportation (FDOT) and Hydraulic Engineering Circular No. 18 (HEC-18). The findings showed that machine learning algorithms had the highest goodness-of-fit and prediction accuracy (0.885 < R < 0.945) in comparison to the other models. The results of sensitivity analysis by the proposed model indicated that pile cap location (Y) was a more sensitive factor for LSCP among other factors. The result also depicted that the RS-REPTree ensemble model (R = 0.945) could well enhance the prediction power of the REPTree base classifier (R = 0.885). Therefore, the proposed model can be useful as a promising technique to predict the LSCP.

show abstract

Mapping earthquake-triggered landslide susceptibility by use of artificial neural network (ANN) models: an example of the 2013 Minxian (China) Mw 5.9 event

Cited by 103 publications

References 64 publications

Earthquake-induced landslide scenarios for seismic microzonation: application to the Accumoli area (Rieti, Italy)

Earthquake-induced landslide scenarios for seismic microzonation: application to the Accumoli area (Rieti, Italy)

Landslide Susceptibility Assessment by Novel Hybrid Machine Learning Algorithms

A Hybrid Intelligence Approach to Enhance the Prediction Accuracy of Local Scour Depth at Complex Bridge Piers

Contact Info

Product

Resources

About