Application of time series analysis and PSO–SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir, China

Zhou, Chao; Yin, Kunlong; Cao, Ying; Ahmed, Bayes

doi:10.1016/j.enggeo.2016.02.009

Cited by 299 publications

(130 citation statements)

References 33 publications

Supporting

Mentioning

130

Contrasting

Order By: Relevance

“…For example, principal component analysis (PCA) has been used to determine the main variables that affect eutrophication processes from a wide number of water quality parameters including TN, TP, oxygen, Chl-a, Secchi depth, phosphate, nitrate, nitrite, and ammonia (Lundberg et al, 2005;Primpas et al, 2010); Cluster analysis (CA) has been used to classify waters into the three eutrophication statuses including the oligotrophic, mesotrophic, and eutrophic state using several variables (Chl-a, phosphate, nitrate, nitrite, and ammonia) (Stefanou et al, 2000;Primpas et al, 2008); Discriminant factor analysis (DFA) has been used to identify different variables (nitrate, phosphate, Chl-a, DO, turbidity and temperature) that can differentiate sampling sites and to group them according to their eutrophication conditions (Tsirtsis and Karydis, 1999;Pinto et al, 2012); Artificial neural network (ANN) mode has been used for prediction of eutrophication conditions with reasonable accuracy by a wide range of variables (TP, TN, COD, the Secchi disk depth, DO and Chl-a) (Jiang et al, 2006;Kuo et al, 2007). Support vector machine (SVM) (Vapnik, 1995) is a promising power approach used to reflect the nonlinearity between responsive indicator and input variables using stochastic error minimization approaches (Zhou et al, 2016a) and is an effective tool to predict values from a wide variety of environmental fields (Ribeiro and Torgo, 2008;Farfani et al, 2015;Kisi et al, 2015). The grid search (GS) algorithm is straight forward to determine the optimized parameter values for the SVM (Sajan et al, 2015;Gao and Hou, 2016).…”

Section: Introductionmentioning

confidence: 99%

Real-time eutrophication status evaluation of coastal waters using support vector machine with grid search algorithm

Kong

Sun

et al. 2017

Marine Pollution Bulletin

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Real-time eutrophication status evaluation of coastal waters using support vector machine with grid search algorithm

Kong

Sun

et al. 2017

Marine Pollution Bulletin

View full text Add to dashboard Cite

“…(2) Landslides threaten the lives and properties of the residents around the disaster area. Typical landslide events caused by the change of reservoir water level such as the Bazimen landslide, which is located in Xiangxi Village, Guizhou Town, Zigui County, Hubei Province, China, and happened in June 2003 [9], as shown in Figure 1b, the Taping landslide, which is located in Quzhi Township, Wushan County, Chongqing City, China, and happened in June 2012 [10,11], as shown in Figure 1 (c), all caused great losses of lives and properties. Therefore, it is important to grasp the laws and contributing factors of slope instability caused by reservoir water level fluctuations in order to correctly understand the mechanisms of reservoir water seepage and to prevent and control landslide disasters.…”

Section: Introductionmentioning

confidence: 99%

Seepage, Deformation, and Stability Analysis of Sandy and Clay Slopes with Different Permeability Anisotropy Characteristics Affected by Reservoir Water Level Fluctuations

Ren

Zhang

et al. 2020

Water

View full text Add to dashboard Cite

Evaluation of slope stability under water level fluctuations is an important topic in the Three Gorges Reservoir (TGR) in China. However, most of the previous studies regarded slope soil as isotropic material, or only considered the influence of anisotropy ratio (kr = kx/ky) but ignored the anisotropy direction (α). Meanwhile, the pore pressure–stress coupling was rarely considered in the previous numerical simulations. In the present study, the SIGMA/W and SLOPE/W modules in Geo-studio are utilized to carry out the numerical simulation of Caipo slope under the drawdown of the reservoir water level, and the anisotropy ratio (kr) as well as the anisotropy direction (α) of two kinds of soils (clay and sand) are included. Results show that the anisotropy ratio kr and anisotropy direction α decrease the infiltration capacity of the soil, which increases the infiltration line hysteretic elevation (ILHE) as well as maximum horizontal displacement (MHD), and reduces the minimum safety factor (MSF). The slope toe firstly fails with the drawdown of water level. The influence of reservoir water level drop on seepage, deformation, and stability of the sand slope is less than that of the clay slope. For the sandy soil slope, it is not only necessary to consider the influence of kr, but also the influence of α. For the soil slope, we can only consider α in order to simplify calculation.

show abstract

“…To verify the performance of the proposed method, four methods, namely, the ABC-KELM, WT-ELM, ELM and SVM 21,48 , were executed with the same data. Regarding the ABC-KELM method, the parameters of KELM were optimized using the ABC algorithm.…”

Section: Resultsmentioning

confidence: 99%

“…Zhou et al . (2016) integrated time series decomposition and support vector machine (SVM) to establish a displacement prediction method by considering the response relationship between triggering factors and landslide deformation 21 .…”

Section: Introductionmentioning

confidence: 99%

A novel method for landslide displacement prediction by integrating advanced computational intelligence algorithms

Zhou

Yin

Cao

et al. 2018

Sci Rep

Self Cite

View full text Add to dashboard Cite

Landslide displacement prediction is considered as an essential component for developing early warning systems. The modelling of conventional forecast methods requires enormous monitoring data that limit its application. To conduct accurate displacement prediction with limited data, a novel method is proposed and applied by integrating three computational intelligence algorithms namely: the wavelet transform (WT), the artificial bees colony (ABC), and the kernel-based extreme learning machine (KELM). At first, the total displacement was decomposed into several sub-sequences with different frequencies using the WT. Next each sub-sequence was predicted separately by the KELM whose parameters were optimized by the ABC. Finally the predicted total displacement was obtained by adding all the predicted sub-sequences. The Shuping landslide in the Three Gorges Reservoir area in China was taken as a case study. The performance of the new method was compared with the WT-ELM, ABC-KELM, ELM, and the support vector machine (SVM) methods. Results show that the prediction accuracy can be improved by decomposing the total displacement into sub-sequences with various frequencies and by predicting them separately. The ABC-KELM algorithm shows the highest prediction capacity followed by the ELM and SVM. Overall, the proposed method achieved excellent performance both in terms of accuracy and stability.

show abstract

Application of time series analysis and PSO–SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir, China

Cited by 299 publications

References 33 publications

Real-time eutrophication status evaluation of coastal waters using support vector machine with grid search algorithm

Real-time eutrophication status evaluation of coastal waters using support vector machine with grid search algorithm

Seepage, Deformation, and Stability Analysis of Sandy and Clay Slopes with Different Permeability Anisotropy Characteristics Affected by Reservoir Water Level Fluctuations

A novel method for landslide displacement prediction by integrating advanced computational intelligence algorithms

Contact Info

Product

Resources

About