Due to the influence of terrain and climate, the risk of highway slope disasters in Meizhou City is prominent. This study focuses on a 500-meter range on either side of the existing mainline highways in Meizhou, selecting eight evaluation factors—elevation, slope, curvature, lithology, NDVI, TWI, annual average rainfall, and maximum monthly rainfall—to construct a highway slope disaster susceptibility index evaluation system. Based on historical highway slope disaster data, a Bayesian network model is established to predict the susceptibility of highway slopes to disasters and further to analyze the distribution characteristics of landslide hazards under different rainfall scenarios. The conclusions are as follows: 1) The Bayesian network model for highway slope disaster susceptibility evaluation achieves an AUC of 0.832, indicating good reliability. Additionally, the SHAP values from the Bayesian network model show that lithology, slope, and maximum monthly rainfall are the three most influential factors affecting highway slope disasters in Meizhou City. 2) Considering three rainfall scenarios (1-in-10, 1-in-50, and 1-in-100-year events), the areas of extremely high-risk regions gradually increased, accounting for 13%, 19%, and 22%, respectively. 3) Based on web scraping tools to retrieve social media data, all historical highway slope disaster cases in Meizhou are located in regions classified as high and extremely high hazard levels. The findings of this study provide a valuable reference for the prevention and control of highway slope disasters in Meizhou City.
DUG L, ZHANGY S, YANGZ H,et al .Estimation of seismic landslide hazard in the eastern Himalayan syntaxis region of Tibetan Plateau[J]. Acta Geologica Sinica-English Edition,2017, 91(2): 658-668.
YAOZ Y. Susceptibility assessment of shallow landslides in Chenxi County based on SINMAP and TRIGRS models [D]. Beijing:China University of Geosciences (Beijing),2018.(in Chinese)
CHEND L, SUND L, WENH J, et al. LightGBM-SHAP landslide susceptibility by different factor screening methods[J]. Journal of Beijing Normal University (Natural Science), 2024, 60(1): 148-158.(in Chinese)
ZHONGK, TANX H, NIUM L,et al .Evaluation of slope stability based on rainfall intensity-duratio:taking three solpes in Anhui Province,China as examples[J].Journal of Earth Sciences and Environment,2023,45(6): 1380-1388.(in Chinese)
[8]
AMATYAP, KIRSCHBAUMD, STANLEYT. Rainfall-induced landslide inventories for Lower Mekong based on Planet imagery and a semi-automatic mapping method[J]. Geoscience Data Journal, 2022, 9(2): 315-327.
TAOW, SUNY. Review on the evaluation methods of landslide geological hazards based on GIS[J]. World Nonferrous Metals,2020(21): 157-159.(in Chinese)
[11]
CHAKRABORTTYR, PALS C, ROYP, et al .Novel ensemble approach for landslide susceptibility index assessment in a mountainous environment of India[J]. Geocarto International, 2022, 37(26): 13311-13336.
ZHOUS H, FUY H, XUZ W,et al .Geological disasters susceptibility mapping in Fujian Province based on subjective and objective weighting[J].Journal of Safety and Environment,2023,23(9): 3204-3214.(in Chinese)
[14]
CUIY L, JINJ Z, HUANGQ B,et al .A data-driven model for spatial shallow landslide probability of occurrence due to a typhoon in Ningguo City,Anhui Province,China[J]. Forests,2022, 13(5): 732.
[15]
YUANR, CHENJ. A hybrid deep learning method for landslide susceptibility analysis with the application of InSAR data[J].Natural Hazards,2022,114(2): 1393-1426.
HUANGF M, PANL H, YAOC,et al. Landslide susceptibility prediction modelling based on semi-supervised machine learning[J].Journal of Zhejiang University (Engineering Science),2021,55(9):1705-1713.(in Chinese)
[20]
MIHALJEVIĆB, BIELZAC, LARRAÑAGAP. Bayesian networks for interpretable machine learning and optimization[J]. Neurocomputing,2021, 456: 648-665.
[21]
VOGELK, RIGGELSENC, KORUPO,et al .Bayesian network learning for natural hazard analyses[J]. Natural Hazards and Earth System Sciences, 2014, 14(9): 2605-2626.
[22]
HUANGF M, YEZ, ZHOUX T, et al .Landslide susceptibility prediction using an incremental learning Bayesian network model considering the continuously updated landslide inventories[J]. Bulletin of Engineering Geology and the Environment, 2022, 81(6): 250.
LIX J, FUS C .Analysis on disaster regularity of artificial slope in Meizhou City and prevention countermeasures[J]. South China Journal of Seismology,2020,40(2):111-117.(in Chinese)
YANC L, ZHENGD F, NIANT K,et al. Fuzzy Bayesian network model based on ANP and its application to coastal zone geohazard risk assessment[J]. Journal of Engineering Geology,2021,29(6): 1862-1868.(in Chinese)
JIY T, WANGX, HAOY,et al .Investigation and evaluation of urban geo-hazards risk in Shaanxi Province based on slope unit:a case study of Jiangcun street in Xi’an[J]. Journal of Catastrophology,2022,37(4): 211-219.(in Chinese)
WANGC X, ZHUJ Y, YUC J,et al .Risk assessment of landslide geological hazards under different rainfall conditions based on the Pearson Ⅲ curves[J]. Bulletin of Geological Science and Technology,2025,44(1): 194-204.(in Chinese)
LIJ J, ZHANGN, WANGW L,et al .Hazards,causes and control countermeasures of rainfall-induced landslide in Meizhou[J]. Construction & Design for Engineering, 2023(1): 47-49.(in Chinese)
YAOY. Characteristics of geological disasters and their prevention planning in Meizhou City[J]. Bulletin of Soil and Water Conservation,2013,33(1):188-191.(in Chinese)
[37]
LANM, ZHUJ P,LO S. Hybrid Bayesian network-based landslide risk assessment method for modeling risk for industrial facilities subjected to landslides[J]. Reliability Engineering & System Safety, 2021, 215: 107851.
LONGX, SUNR, ZHENGT. Convolutional neural network-based liquefaction prediction model and interpretability analysis[J]. Rock and Soil Mechanics,2024, 45(9):2741-2753.(in Chinese)
CHENR P, DAIT, ZHANGP,et al .Prediction method of tunneling-induced ground settlement using machine learning algorithms[J].Journal of Hunan University (Natural Sciences),2021, 48(7): 111-118.(in Chinese)
XUL, JUN P, DENGM D,et al. Comparative analysis of landslide susceptibility assessment accuracy in different evaluation units[J]. Journal of Engineering Geology,2024,32(5):1640-1653.(in Chinese)
[46]
PHAMB T, PRAKASHI, KHOSRAVIK,et al. A comparison of support vector machines and Bayesian algorithms for landslide susceptibility modelling[J]. Geocarto International,2019, 34(13): 1385-1407.
ZHANGR C, LING F, ZHOUX C,et al .Prediction and inference of typhoon rainstorm disaster chains in Fujian Province based on dynamic Bayesian network[J].Journal of Subtropical Resources and Environment,2023,18(1): 17-25.(in Chinese)
基金资助
贵州省交通运输厅科技项目(2025-112-018)
Science and Technology Program of Guizhou Provincial Department of Communication and Transportation(2025-112-018)
长沙市自然科学基金资助项目(kq2402072)
Natural ScienceFoundation of Changsha(kq2402072)
贵州省科技支撑计划(2020-4Y047)
Science and Technology Infrastructure Program of Guizhou Province(2020-4Y047)
国家自然科学基金资助项目(12062026)
National Natural Science Foundation of China(12062026)
广东省交通集团有限公司科技项目(JT2022YB24)
Science and Technology Program of Guangdong Transportation Group Co., Ltd(JT2022YB24)