The risk assessment of landslides is an important component of landslide risk assessment, which is of great significance for the prediction and prevention of landslides. How to scientifically and reasonably select evaluation factors is a weak link in existing research. For the selection of landslide risk assessment factors, the data analysis method mistakenly deleted important factors in factor screening. Therefore, the hierarchical grey relational analysis was first used to calculate the comprehensive correlation degree of the assessment factors based on data analysis and expert experience, and then the random forest model was used to select the best assessment factors and assess the landslide risk. The impact of this method on the model performance was measured by comparing before and after the screening of assessment factors. The results showed that the area under the working characteristic curve of the Random forest model corresponding to the subjects could be increased from 0.82 to 0.91 by screening factors, which improved the prediction accuracy of the evaluation model; Comparing the landslide verification points with higher and high-risk areas, 89.7% of the landslide verification points are consistent with them. The risk assessment of landslides along the railway line based on hierarchical grey correlation analysis selects more reasonable evaluation factors, making the evaluation results more accurate and providing reference basis for risk control of landslides along the Ya'an city railway line.

Pan He, Yuqi Wang, Xinyue Ma, Yifei Chen, Yu Jia, Yu Qiao, Xinyu Han. Landslide Risk Assessment of Railway Lines Based on Hierarchical Grey Relation Analysis. Academic Journal of Engineering and Technology Science (2023) Vol. 6, Issue 9: 73-82. https://doi.org/10.25236/AJETS.2023.060911.

[1] Lu CF, Cai CX, 2019. Challenges and Countermeasures for Construction Safety during the Sichuan–Tibet Railway Project. Engineering, 5(05):49-61. DOI: CNKI:SUN:GOCH. 0. 2019-05-010. 

[2] Li XZ, Cui Y, Zhang XG, et al., 2019. Characteristics and spatial distribution law of landslides and collapses along Sichuan-Tibet railway. Journal of Engineering Geology, 27(S): 110-120. DOI:10. 26914/c. cnkihy. 2019. 014704. 

[3] Wang Ting, 2020. Landslide Risk Assessment Based on Combined Analysis of Weight Method and Simulation Method: A Case Study of Parts of Wanyuan City. DOI: 10. 26986/d. cnki. gcdlc. 2020. 000805. 

[4] Yu XY, Hu YJ, Niu RQ, 2016. Research on the Method to Select Landslide Susceptibility Evaluation Factors Based on RS-SVM Model. Geography and Geo-Information Science, 32(03): 23-28+2. Doi: CNKI: SUN: DLGT. 0. 2016-03-005. 

[5] Liu R, Li LY, Yang X, et al., 2021, Landslide Susceptibility Mappping Based on Factor Strong Correlation Analysis Method[J]. Earth and Environment, 49(02):198-206. Doi: 10. 14050/j. cnki. 1672-9250. 2020. 48. 108. 

[6] Tang RX, Yan EC, Tang W, 2017. Landslide susceptibility evaluation based on rough set and back-propagation neural network [J]. Coal Geology & Exploration, 45(06):129-138. 

[7] Aditian A, Kubota T, Shinohara Y, 2018. Comparison of GIS-based landslide susceptibility models using frequency ratio, logistic regression, and artificial neural network in a tertiary region of Ambon, Indonesia. Geomorphology, 318:101-111. DOI:10. 1016/j. geomorph. 2018. 06. 006. 

[8] Huang Y, Zhao L. 2018. Review on landslide susceptibility mapping using support vector machines. Catena, 165: 520−529. DOI:10. 1016/j. catena. 2018. 03. 003. 

[9] Luigi L, Martin M P. 2018. Presenting logistic regression-based landslide susceptibility results. Engineering Geology, 244: 14−24. DOI:10. 1016/j. enggeo. 2018. 07. 019. 

[10] Wu XQ, Lai CG, Chen XH, et al. A landslide hazard assessment based on random forest weight:a case study in the Dongjiang River Basin, Journal of Natural Disasters, 2017, 26(05): 119-129. DOI: 10. 13577/j. jnd. 2017. 0514. 

[11] Ahmed N, Firoze A, Rahman RM. 2020. Machine learning for predicting landslide risk of Rohingya refugee camp infrastructure. Journal of Information and Telecommunication, 4(2): 175-198. DOI: 10. 1080/ 24751839. 2019. 1704114. 

[12] Wang JH, Jin HL, Ni TX, et al., 2017. The application of fuzzy comprehensive evaluation model based on analytic hierarchy process in risk assessment of debris flow gully in Kangle County. The Chinese Journal of Geological Hazard and Control, 28(03):52-57. DOI: 10. 16031/j. cnki. issn. 1003- 8035. 2017. 03. 08. 

[13] Huang F, Wang Y, Dong Zhiliang, et al., 2019. Regional Landslide Susceptibility Mapping Based on Grey Relational Degree Model. Earth Science, 44(02):664-676. 

[14] Jaiswal P, Van. W C J, Jetten V. Quantitative assessment of direct and indirect landslide risk along transportation lines in southern India[J]. Natural hazards and earth system sciences, 2010, 10(6):1253-1267.DOI:10.5194/nhess-10-1253-2010.

[15] Zhang C, Wang Q, Chen JP, et al., 2011. Evaluation of debris flow risk in Jinsha River based on combined weight process. Rock and Soil Mechanics, 32(03):831-836. DOI: 10. 162 85/ j. rsm. 2011. 03. 019. 

[16] Tan GS, Cao SX, Zhao B, et al., 2020. An assessment of power transformers based on association rules and variable weight coefficients. Power System Protection and Control, 48(01): 88-95. DOI: 10. 19783/j. cnki. pspc. 190072. 

[17] Song RJ, Liu RY, Liu YW, et al., 2018. Key Indicator System Establishment and Application for Transformer Condition Assessment Based on Hierarchy Grey Relation Analysis. High Voltage Engineering, 44(08):2509-2515. DOI: 10. 133 36/j. 1003-6520. hve. 20180731010. 

[18] Zhang WQ, Luo GP, Zheng HW, et al., 2020. Analysis of vegetation index changes and driving forces in inland arid areas based on random forest model: a case study of the middle part of northern slope of the north Tianshan Mountains. Chinese Journal of Plant Ecology, 44(11): 1113-1126. 

[19] Breiman L. 2001. Random forests. Machine Learning, 2001, 45(1): 5-32. DOI: 10. 1023/A: 1010933404324. 

[20] Yang ZJ, Ding PP, Wang D, et al., 2018. Landslide Risk Analysis on et a Sichuan-Tibet Railway (Kangding to Nyingchi Section) Journal of the China Railway Society, 40(09): 97-103. DOI: CNKI: SUN: TDXB. 0. 2018-09-015. 

[21] Wang WD, Fu QX, Tang R. 2018. Landslide spatiotemporal susceptibility analysis of Chengdu-Yaan section in Sichuan-Tibet railway. Journal of Railway Science and Engineering, 15(04): 862-870. DOI:10. 19713/j. cnki. 43-1423/u. 2018. 04. 006. 

[22] Reichenbach P, Rossi M, Malamud B D, et al. A review of statistically-based landslide susceptibility models [J]. Earth-Science Reviews, 2018, 180, 60-91.