An integrated approach for landslide susceptibility mapping by considering spatial correlation and fractal distribution of clustered landslide data
- 296 Downloads
Natural disasters often show highly heterogeneous character due to complex geo-environmental settings. The spatial distribution of landslides is generally clustered at different scales. In this paper, we proposed a methodology for landslide susceptibility mapping (LSM) with consideration of spatial correlation and distribution of clustered landslide data. To quantify the spatial correlation of landslides, a normalized spatial-correlated scale index (NSCI) was introduced. Based on the definition of landslide frequency ratio, calibrated landslide potential index (CLPI) was proposed to account for the effect of landslide clustering. Considering the fractal distribution of landslides, the variable fractal dimension model (VFDM) was introduced to measure the spatial association between clustered landslides and conditional factors. Based on the definition of fractal dimension (D), the weights of the factors were obtained from fractal perspective. We proposed a weighted calibrated landslide potential model (WCLPM), obtained by the combination of CLPI values and weights of the factors. The proposed method is illustrated by example in Xinjiang, NW China, where landslide points are clustered at regional scale. In the example, the landslides were randomly split into two groups: one for building landslide model (training dataset) and the other for validating the model (validating dataset). Five landslide conditional factors (lithology, tectonic faults, elevation, slope, aspect) were selected, processed, and analyzed in a geographic information system (GIS) environment. Predictive accuracy of the WCLPM was evaluated and compared based on the calculation of area under the prediction-rate curve (AUPRC). The example shows that the proposed WCLPM provides good prediction for the study area (AUPRC = 0.8700). This study provided a novel and practical method for LSM.
KeywordsLandslide clustering Fractal Spatial statistics Validation statistics Landslide susceptibility mapping
The authors would like to thank the two anonymous reviewers for their valuable and insightful comments to improve the paper. The first author gratefully acknowledges Ms. Yue Jiang at Xinjiang Institute of Geological Environment Monitoring (Urumchi, China) for providing the geological data.
This research was funded by the National Natural Science Foundation of China (No. 41272352), the National Key Research and Development Program of China (No. 2018YFC1504803-01) and Science and Technology Project of Xinjiang Land and Resource Department (No. XJDZFZ-XX2013).
- Ayalew L, Yamagishi H (2005) The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central Japan. Geomorphology 65, 15-31.Google Scholar
- Chung CJ, Fabbri AG (1999) Probabilistic prediction models for landslide hazard mapping. Photogramm Eng Remote Sens 65(12):1389–1399Google Scholar
- Corominas J, van Westen C, Frattini P, Cascini L, Malet JP, Fotopoulou S, Catani F, Van DenEeckhaut M, Marouli O, Agliardi F, Pitilakis K, Winte MG, Pastor M, Ferlisi S, Tofani V, Hervas J, Smith JT (2014) Recommendations for the quantitative analysis of landslide risk. Bull Eng Geol Environ 73:209–263Google Scholar
- Davis JC (2002) Statistics and data analysis in geology, 3rd edn. Wiley, Hoboken 638pGoogle Scholar
- Feizizadeh B, Blaschke T, Nazmfar H, Rezaei Moghaddam MH (2013) Landslide susceptibility mapping for the Urmia Lake basin, Iran: a multi-criteria evaluation approach using GIS. Int J Environ Res 7(2):319–336Google Scholar
- Lineback M, Marcus WA, Aspinall R, Custer SG (2011) Assessing landslide potential using GIS, soil wetness modeling and topographic attributes Payette River, Idaho. Geomorphology 37(1):149–165Google Scholar
- Oliveira SC, Zêzere JL, Garcia RAC (2014) Structure and characteristics of landslide input data and consequences on landslide susceptibility assessment and prediction capability. In: Lollino G et al (eds) Engineering geology for society and territory, vol 2. Springer International Publishing, BaselGoogle Scholar
- Qin ZH, Qin P (2010) Using improved variable dimension fractal to model seawall settlement. IEEE International Conference on Information Management & Engineering, pp 325–328Google Scholar
- Tien Bui D, Anh Tuan T, Klempe H, Pradhan B, Revhaug I (2016) Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides 13(2):361–378CrossRefGoogle Scholar
- Varnes DJ (1978) Slope movement types and processes. In: Schuster RL, Krizek RJ (eds) Landslides analysis and control, Special report, vol 176. Transportation Research Board, National Academy of Sciences, New York, pp 11–33Google Scholar
- Wu YP, Zhang QX, Tang HM, Cheng C, Shen L (2013) Deformation Prediction of Baishuihe landslide based on cumulative variable dimension fractal-artificial neural network model. Disaster Adv 13Google Scholar