Objective This study aims to comprehensively evaluate and predict landslide hazard across China by establishing a random forest model, providing scientific evidence and decision-making support for disaster prevention and mitigation. Methods Based on landslide sample data from nine typical earthquake regions (e.g., Wenchuan, Lushan, and Ludian), positive and negative landslide sample points were comprehensively extracted. Combined with multiple factors such as topography, rainfall, land use, and NDVI, raster standardization processing and band synthesis techniques were used to establish a random forest model for training and validation. On this basis, the model was applied to predict landslide hazard nationwide. The model's performance was evaluated using indicators such as AUC values, and key influencing factors and their mechanisms were analyzed. Results 1) The random forest model demonstrated high prediction performance across multiple earthquake regions, with AUC values approaching 1, indicating strong applicability and stability of the model. 2) The key factors influencing landslide hazard were, in order, slope and slope curvature, which played a dominant role in identifying earthquake-induced landslide hazard. 3) The nationwide landslide hazard prediction results showed that the model effectively identified high-hazard areas, which were highly consistent with the actual distribution of landslides and exhibited distinct regional spatial patterns. Conclusion The random forest model has high accuracy and stability in landslide hazard assessment. By identifying key influencing factors and revealing their spatial distribution patterns, this study provides scientific support and reference for future landslide prediction, regional sustainable development planning, and the formulation of disaster prevention and mitigation strategies.
DAIF C, LEEC F, NGAIY Y. Landslide risk assessment and management: An overview[J].Engineering Geology,2002,64(1):65-87.
[2]
KORUPO, CLAGUEJ J. Natural hazards,extreme events,and mountain topography[J].Quaternary Science Reviews,2009,28(11/12):977-990.
[3]
HUNGRO, LEROUEILS, PICARELLIL. The Varnes classification of landslide types,an update[J].Landslides,2014,11(2):167-194.
[4]
ZHANGS, ZHANGL M. Impact of the 2008 Wenchuan earthquake in China on subsequent long-term debris flow activities in the epicentral area[J].Geomorphology,2017,276:86-103.
[5]
FANX M, XUQ, SCARINGIG, et al. A chemo-mechanical insight into the failure mechanism of frequently occurred landslides in the Loess Plateau,Gansu Province,China[J].Engineering Geology,2017,228:337-345.
[6]
GUZZETTIF, REICHENBACHP, CARDINALIM, et al. Probabilistic landslide hazard assessment at the basin scale[J].Geomorphology,2005,72(1):272-299.
[7]
HUX N, NAIMK, JIAS, et al. Disaster policy and emergency management reforms in China: From Wenchuan earthquake to Jiuzhaigou earthquake[J].International Journal of Disaster Risk Reduction,2021,52:e101964.
[8]
VAN DIJKEJ J, VAN WESTENC J. Rockfall hazard: A geomorphologic application of neighbourhood analysis with ILWIS[J].ITC Journal,1990:40-44.
[9]
ALEOTTIP, CHOWDHURYR. Landslide hazard assessment: Summary review and new perspectives[J].Bulletin of Engineering Geology and the Environment,1999,58(1):21-44.
HUANGR Q, LIY G. LOGICAl message model of stability predication ot bank slopes in Three Gorges[J].Hydrogeology and Engineering Geology,1992,19(1):15-20.
LIUC Z, WENM S, LIUY H, et al.Regional assessment on geological disasters in "5·12" Wenchuan seismic area,China[J].Hydrogeology and Engineering Geology,2016,43(5):1-16.
[14]
CHOWDHURYM S, RAHMANM N, SHEIKHM S, et al. GIS-based landslide susceptibility mapping using logistic regression, random forest and decision and regression tree models in Chattogram District, Bangladesh[J].Heliyon,2024,10(1):e23424
[15]
HAILUS, DERIBEWK T, TEFERIE, et al. Spatial assessment employing fusion logistic regression and frequency ratio models to monitor landslide susceptibility in the upper Blue Nile basin of Ethiopia: Muger watershed[J].Environmental Systems Research,2024,13(1):e54.
DUP, CHENN S, WUK L, et al. Evaluation of landslide susceptibility in southeast Xizang based on a random forest model[J].Journal of Chengdu University of Technology (Science and Technology Edition),2024,51(2):328-344.
JIAJ, MAOY M, MENGX J, et al. Comparison of landslide susceptibility evaluation by deep random forest and random forest model:A case study of Lueyang County,Hanzhong City[J].Northwestern Geology,2023,56(3):239-249.
LIUJ, LIS L, CHENT. Landslide susceptibility assesment based on optimized random forest model[J].Geomatics and Information Science of Wuhan University,2018,43(7):1085-1091.
ZHANGX Y, ZHANGC S, MENGH J, et al. Landslide hazard evaluation in the northern mountainous area of Guide County based on Random Forest and AHP[J].Hydrogeology and Engineering Geology,2018,45(4):142-149.
[27]
TEHRANYM S, PRADHANB, MANSORS, et al. Flood susceptibility assessment using GIS-based support vector machine model with different kernel types[J].Catena,2015,125:91-101.
[28]
HONGH Y, PRADHANB, JEBURM N, et al. Spatial prediction of landslide hazard at the Luxi area (China) using support vector machines[J].Environmental Earth Sciences,2015,75(1):e40.
XUC, XUX W, ZHOUB G, et al. Probability of coseismic landslides:A new generation of earthquake-triggered landslide hazard model[J].Journal of Engineering Geology,2019,27(5):1122-1130.
[33]
GUPTAN, DAS J, KANUNGOD P. Earthquake-induced landslide hazard assessment using ground motion parameters: A case study for Bhagirathi Valley, Uttarakhand, India[J].Journal of Earth System Science,2024,134(1):e5.
[34]
郑志成.地震滑坡危险性评价模型对比研究[D].成都:西南交通大学,2022.
[35]
ZHENGZ C. Comparative study on seismic landslide hazard assessment models[D].Chengdu: Southwest Jiaotong University,2022.
[36]
DAIF C, XUC, YAOX, et al. Spatial distribution of landslides triggered by the 2008 Ms 8.0 Wenchuan earthquake,China[J].Journal of Asian Earth Sciences,2011,40(4):883-895.
[37]
LIN, TANGC, ZHANGX Z, et al. Characteristics of the disastrous debris flow of Chediguan gully in Yinxing town,Sichuan Province,on August 20,2019[J].Scientific Reports,2021,11(1):e23666.
[38]
GUZZETTIF, PERUCCACCIS, ROSSIM, et al. The rainfall intensity–duration control of shallow landslides and debris flows: An update[J].Landslides,2008,5(1):3-17.
[39]
OHH J, LEES, HONGS M. Landslide susceptibility assessment using frequency ratio technique with iterative random sampling[J].Journal of Sensors,2017,2017(1):e3730913.
[40]
YANGH J, YANGT Q, ZHANGS J, et al. Rainfall-induced landslides and debris flows in Mengdong Town,Yunnan Province,China[J].Landslides,2020,17(4):931-941.
[41]
MUHAMMADA P J, FARAJR. Data normalization and standardization: A technical report[Z].2014, DOI:10.13140/RG.2.2.28948.04489.
[42]
AYALEWL, YAMAGISHIH, UGAWAN. Landslide susceptibility mapping using GIS-based weighted linear combination, the case in Tsugawa area of Agano River, Niigata Prefecture, Japan[J].Landslides,2004,1:73-81.