PDF Download

[1]HE Qian,WANG Ming,LIU Kai.Assessement on Earthquake-Triggered Landslide Susceptibility Based on Logistic Regression and MCMC Method[J].Research of Soil and Water Conservation,2022,29(03):396-403+410.

Copy

Assessement on Earthquake-Triggered Landslide Susceptibility Based on Logistic Regression and MCMC Method

Research of Soil and Water Conservation[ISSN 1005-3409/CN 61-1272/P] Volume: 29 Number of periods: 2022 03 Page number: 396-403+410 Column: Public date: 2022-04-20

Title:: Assessement on Earthquake-Triggered Landslide Susceptibility Based on Logistic Regression and MCMC Method

Author(s):: HE Qian, WANG Ming, LIU Kai; (1.State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China; 2.Academy of Disaster Reduction and Emergency Management, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China; 3.Key Laboratory of Environmental Change and Natural Disasters, ministry of Education, Beijing Normal University, Beijing 100875, China)

Keywords:: Markov Chain Monte Carlo; Logistic regression; uncertainty; earthquake-induced landslide; landslide susceptibility

CLC:: P642.22

DOI:: -

Abstract:: Logistic regression(LR)model is widely used in the assessment of landslide susceptibility, but the research on the uncertainty of model parameters is relatively lacking. Markov Chain Monte Carlo(MCMC)method can combine the prior information of the parameters to obtain their posterior distribution, thereby analyzing the uncertainty of the estimated parameters. This study aims to explore the effectiveness of MCMC in the susceptibility modelling based on LR and quantify the uncertainty of the estimated parameters of the models. Taking the 2013 Lushan earthquake, the 2017 Jiuzhaigou earthquake and the 2014 Ludian earthquake in southwest China as examples, we estimated the regression coefficients of the Logistic regression model based on the MCMC method, constructed the regional earthquake-induced landslide susceptibility models, analyzed the uncertainty in parameter estimates, and drew the regional landslide susceptibility maps. The results show that: in the Lushan earthquake case, the uncertainty of all the model parameters is relatively low; in Jiuzhaigou case, the uncertainty of the lithology factor is relatively high; in Ludian case, uncertainty in parameter estimates of lithology, profile curvature and plan curvature is relatively high; generally, most parameter estimates have relatively low uncertainty; the Logistic regression models constructed in this study have high prediction accuracy in the three earthquake-induced landslide events, and the AUC(Area Under ROC Curve)values are all above 0.9, which demonstrates the accuracy of using the MCMC method to estimate the coefficients of the Logistic model; for the relative importance of the influencing factors, elevation, distance from the faults and MMI(Modified Mercalli Intensity)are the top three factors for these three cases. This study can provide a new idea and method for using Logistic regression model to assess landslide susceptibility.

References:: [1] Pourghasemi H R, Teimoori Yansari Z, Panagos P, et al. Analysis and evaluation of landslide susceptibility:a review on articles published during 2005—2016(periods of 2005—2012 and 2013—2016)[J]. Arabian Journal of Geosciences, 2018,11(9):1-12.
[2] Zhao B, Wang Y, Luo Y, et al. Landslides and dam damage resulting from the Jiuzhaigou earthquake(8 August 2017), Sichuan, China[J]. Royal Society Open Science, 2018,5(3):doi.org/10,1098/rsos.171418.
[3] 和海霞,李素菊,刘明,等.云南鲁甸6.5级地震灾区滑坡分布特征研判分析[J].灾害学,2016,31(1):92-95.
[4] 韩继冲,张朝,曹娟.基于逻辑回归的地震滑坡易发性评价:以汶川地震、鲁甸地震为例[J].灾害学,2021,36(2):193-199.
[5] Budimir M E A, Atkinson P M, Lewis H G. A systematic review of landslide probability mapping using logistic regression[J]. Landslides, 2015,12(3):419-436.
[6] Acquah H D. Bayesian logistic regression modelling via markov chain monte carlo algorithm[J]. Journal of Social and Development Sciences, 2013,4(4):193-197.
[7] Das I, Stein A, Kerle N, et al. Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logistic regression models[J]. Geomorphology, 2012,179:116-125.
[8] 方杰,张敏强.中介效应的点估计和区间估计:乘积分布法、非参数Bootstrap和MCMC法[J].心理学报,2012,44(10):1408-1420.
[9] 周翔,姜婷婷,徐丹,等.基于Logistic回归建模和马尔可夫链蒙特卡罗方法计算后验描述丁酸梭菌株对于给定辐照剂量区的应答趋势[J].原子核物理评论,2016,33(4):500-505.
[10] Reis Jr D S, Stedinger J R. Bayesian MCMC flood frequency analysis with historical information[J]. Journal of Hydrology, 2005,313(1/2):97-116.
[11] 刘章君,郭生练,许新发,等.贝叶斯概率水文预报研究进展与展望[J].水利学报,2019,50(12):1467-1478.
[12] Wang H, Wang C, Wang Y, et al. Bayesian forecasting and uncertainty quantifying of stream flows using Metropolis-Hastings Markov Chain Monte Carlo algorithm[J]. Journal of Hydrology, 2017,549:476-483.
[13] 王德辉,杨帆,杨凯.具有Logistic回归结构的几何分布参数贝叶斯估计及应用[J].辽宁师范大学学报:自然科学版,2016,39(3):295-298.
[14] Li L, Liu R, Pirasteh S, et al. A novel genetic algorithm for optimization of conditioning factors in shallow translational landslides and susceptibility mapping[J]. Arabian Journal of Geosciences, 2017,10(9):209. https://doi.org/10,1007/s12517-017-3002-4.
[15] 田颖颖,许冲,徐锡伟,等.2014年鲁甸M_S6.5地震震前与同震滑坡空间分布规律对比分析[J].地震地质,2015,37(1):291-306.
[16] Zhou J, Zhou J, Lu P, et al. Landslides triggered by the 3 August 2014 Ludian earthquake in China:geological properties, geomorphologic characteristics and spatial distribution analysis[J]. Geomatics, Natural Hazards and Risk, 2016,7(4):1219-1241.
[17] Tang C, Ma G, Chang M, et al. Landslides triggered by the 20 April 2013 Lushan earthquake, Sichuan Province, China[J]. Engineering Geology, 2015,187:45-55.
[18] 刘丽娜,许冲,陈剑. GIS支持下基于CF方法的2013年芦山地震滑坡因子敏感性分析[J].工程地质学报,2014,22(6):1176-1186.
[19] Cao J, Zhang Z, Wang C, et al. Susceptibility assessment of landslides triggered by earthquakes in the Western Sichuan Plateau[J]. Catena, 2019,175:63-76.
[20] Xu C, Xu X, Shyu J B H. Database and spatial distribution of landslides triggered by the Lushan, China Mw 6.6 earthquake of 20 April 2013[J]. Geomorphology, 2015,248:77-92.
[21] Zhu J, Baise L G, Thompson E M. An updated geospatial liquefaction model for global application [J]. Bulletin of the Seismological Society of America, 2017,107(3):1365-1385.
[22] Nowicki Jessee M A, Hamburger M W, Allstadt K, et al. A global empirical model for near-real-time assessment of seismically induced landslides [J]. Journal of Geophysical Research:Earth Surface, 2018,123(8):1835-1859.
[23] Tanyas H, Rossi M, Alvioli M, et al. A global slope unit-based method for the near real-time prediction of earthquake-induced landslides[J]. Geomorphology, 2019,327:126-146.
[24] 刘丽娜,许冲,徐锡伟,等. GIS支持下基于AHP方法的2013年芦山地震区滑坡危险性评价[J].灾害学,2014,29(4):183-191.
[25] Zhou S, Fang L. Support vector machine modeling of earthquake-induced landslides susceptibility in central part of Sichuan province, China[J]. Geoenvironmental Disasters, 2015,2(1):1-12.
[26] 马思远,许冲,田颖颖,等.基于逻辑回归模型的九寨沟地震滑坡危险性评估[J].地震地质,2019,41(1):162-177.
[27] Styron R, Pagani M. The GEM global active faults database[J]. Earthquake Spectra, 2020,36(1):160-180.
[28] Hartmann J, Moosdorf N. The new global lithological map database GLiM:A representation of rock properties at the Earth surface[J]. Geochemistry, Geophysics, Geosystems, 2012,13(12):1-37.
[29] Yang J, Song C, Yang Y, et al. New method for landslide susceptibility mapping supported by spatial logistic regression and GeoDetector: A case study of Duwen Highway Basin, Sichuan Province, China[J]. Geomorphology, 2019,324:62-71.
[30] Kalantar B, Pradhan B, Naghibi S A, et al. Assessment of the effects of training data selection on the landslide susceptibility mapping:a comparison between support vector machine(SVM), logistic regression(LR)and artificial neural networks(ANN)[J]. Geomatics, Natural Hazards and Risk, 2018,9(1):49-69.
[31] Martin A D, Quinn K M, Park J H. MCMCpack:Markov chain monte carlo in R[J]. Journal of Statistical Software, 2011,42(9):1-21.
[32] Chen W, Xie X, Wang J, et al. A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility[J]. Catena, 2017,151:147-160.
[33] Chen W, Xie X, Peng J, et al. GIS-based landslide susceptibility evaluation using a novel hybrid integration approach of bivariate statistical based random forest method[J]. Catena, 2018,164:135-149.
[34] Arabameri A, Pradhan B, Rezaei K, et al. GIS-based landslide susceptibility mapping using numerical risk factor bivariate model and its ensemble with linear multivariate regression and boosted regression tree algorithms[J]. Journal of Mountain Science, 2019,16(3):595-618.
[35] Roy J, Saha S. Landslide susceptibility mapping using knowledge driven statistical models in Darjeeling District, West Bengal, India[J]. Geoenvironmental Disasters, 2019,6(1):1-18.
[36] 张雷雨,杨毅,梁霄.地理加权回归模型的多重共线性诊断方法[J].测绘与空间地理信息,2017,40(10):28-31.
[37] Arabameri A, Saha S, Roy J, et al. Landslide susceptibility evaluation and management using different machine learning methods in the Gallicash River Watershed, Iran[J]. Remote Sensing, 2020,12(3):475. https://doi.org/10,3390/rs12030475.

Similar References:

Memo

Last Update: 2022-04-20