A novel mathematical model for predicting landslide displacement
- PDF / 7,044,321 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 52 Downloads / 171 Views
(0123456789().,-volV)(0123456789(). ,- volV)
METHODOLOGIES AND APPLICATION
A novel mathematical model for predicting landslide displacement S. H. Li1 • L. Z. Wu1
•
Jinsong Huang2
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Landslide displacement evolution is important for predicting landslide geological disasters. Because landslide displacement monitoring data are limited, in this paper we propose a novel model for predicting landslide displacement, namely the kernel grey model with fractional operators (FKGM). By combining the advantages of fractional modeling, kernel function methods and grey models, we derived the theoretical framework of FKGM. The parameters of FKGM were obtained using particle swarm optimization algorithm. Then, FKGM was applied in a case study of a landslide in Hubei, China. The engineering geological characteristics of the landslide were analyzed, and seven factors including rainfall and the rate of the reservoir water-level change were selected as inputs. The results show that the mean absolute percentage error and mean square error of FKGM are smaller than those of the least square support vector machine (LSSVM) and the classical grey prediction model—GM(1,1). The influence of the FKGM parameters was investigated. Our results indicate that FKGM can be applied to reliably predict large deformation of landslides. Keywords Kernel grey model with fractional operators Mathematical model Prediction Engineering application Landslide displacement
1 Introduction Landslides are common geological events which occur worldwide (Iverson 2000; Dai et al. 2002; Zhou et al. 2018), causing injury and loss of life as well as economic losses. In 2016, there were 9710 geological disasters in China, including 7403 landslides, 1484 rockfalls, 584 cases of debris flow, 221 cases of ground subsidence, 12 ground fissures and 6 cases of ground settlement, accounting for 76.2%, 15.3%, 6.0%, 2.3%, 0.1% and 0.1% of the total geological disasters, respectively (Fig. 1) (National Bureau of Statistics of China 2017).
Communicated by V. Loia. & L. Z. Wu [email protected] 1
State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, Sichuan, People’s Republic of China
2
Discipline of Civil, Surveying and Environmental Engineering Priority Research Centre for Geotechnical Science and Engineering, The University of Newcastle, Callaghan, NSW, Australia
Displacement is the large-scale external manifestation of landslide evolution (Lu and Rosenbaum 2003; Chen et al. 2018). Data-based landslide displacement analysis has been frequently applied in recent landslide studies (Crosta et al. 2017; Shihabudheen et al. 2017). To achieve nonlinear mapping between landslide displacement and its influencing factors, an extreme learning adaptive neurofuzzy inference system was proposed for predicting landslide displacement. The system successfully estimated the displacement of the Baishuihe and Shiliushubao landslides (Shihabu
Data Loading...
