Prediction of landslide displacement based on previous accumulated rainfall and Gaussian process regression model
CHEN Lang1，CHEN Yu2，HE Junlin2，LYU Shuning1
(1. Chongqing Steel Xichang Minning Co.，Ltd.，China Baowu Steel Group Corporation，Xichang，Sichuan 615000，China；
2. Sichuan Province Ninth Geological Brigade，Sichuan Bureau of Geology and Mineral Resources，Deyang，Sichuan 618000，China)
Abstract：Rainfall is an important factor inducing landslide deformation. Traditional displacement time series prediction models only consider historical displacement and do not consider the impact of rainfall to conduct landslide displacement prediction，resulting in significant errors in the medium to long term or long-term displacement prediction. Given that the Gaussian process regression(GPR) algorithm has the advantages of easy realization，adaptive acquisition of hyperparameter and probability significance of prediction output，a GPR prediction model of landslide displacement considering the previous accumulated rainfall by introducing the cumulative rainfall index is established in this study，which improves the long-term displacement prediction capability of the model. Taking the landslide in the southern mining area of Xichang as an example，the relationship curve of landslide displacement and daily cumulative rainfall was first analyzed，and the Pearson method was used to calculate the correlation coefficient between the landslide displacement and the previous cumulative rainfall days；Secondly，a GPR model was established，and trained and tested using existing monitoring data. The results showed that the prediction accuracy of the established model was significantly improved compared to the model without considering the previous accumulated rainfall. On this basis，a long-term displacement trend prediction was conducted for monitoring points S1–1 and S1–2，and a comparative analysis was performed on the displacement trend under the assumption of increasing rainfall by 10% and 20%. The results indicate that a 20% increase in rainfall leads to an increase in the deformation rate of the landslide to about 17 mm/d. Without taking control measures，the landslide will experience accelerated sliding to instability.
RASMUSSEN C E，CHRISTOPHER K I W. Gaussian processes for machine learning[M]. Cambridge：MIT Press Ltd.，2005：1-244.
[9]
黄润秋，许 强. 斜坡失稳时间的协同预测模型[J]. 山地研究，1997，15(1)：7-12.(HUANG Runqiu，XU Qiang. Collaborative prediction model for slope instability time[J]. Mountain Research，1997，15(1)：7-12.(in Chinese))
[2]
张 珍，李世海，马 力. 重庆地区滑坡与降雨关系的概率分析[J]. 岩石力学与工程学报，2005，24(17)：3 185-3 191.(ZHANG Zhen，LI Shihai，MA Li. Probability analysis of relationship between landslide and rainfall in Chongqing Area[J]. Chinese Journal of Rock Mechanics and Engineering，2005，24(17)：3 185-3 191.(in Chinese))
[7]
刘鼎文. 突变理论在地震成因及地震危险性与岩体稳定性评价研究中的应用[J]. 国际地震动态，1991，(3)：35-36.(LIU Dingwen. Application of catastrophe theory in the study of earthquake genesis seismic hazard and rock mass stability evaluation[J]. Recent Developments in World Seismology，1991，(3)：35-36.(in Chinese))
[14]
宋 超，赵腾远，许 领. 基于贝叶斯高斯过程回归与模型选择的岩石单轴抗压强度估计方法[J]. 岩土工程学报，2023，45(8)：1 664-1 673.(SONG Chao，ZHAO Tengyuan，XU Ling. Estimation of uniaxial compressive strength based on fully Bayesian Gaussian process regression and model selection[J]. Chinese Journal of Geotechnical Engineering，2023，45(8)：1 664-1 673.(in Chinese))
[17]
戴福初，陈守义，李卓芬. 从土的应力-应变特性探讨滑坡发生机理[J]. 岩土工程学报，2000，22(1)：127-130.(DAI Fuchu，CHEN Shouyi，LI Zhuofen. Analysis of landslide initiative mechanism based on stress-strain behavior of soil[J]. Chinese Journal of Geotechnical Engineering，2000，22(1)：127-130.(in Chinese))
[5]
SAITO M. Forecasting time of slope failure by tertiary creep[C]// Proceedings of the 7th International Conference on Soil Mechanics and Foundation Engineering. Mexico：[s.n.]，1969：677-683.
[15]
苏国韶，宋咏春，燕柳斌. 岩体爆破效应预测的一种新方法[J]. 岩石力学与工程学报，2007，26(增1)：3 509-3 513.(SU Guoshao，SONG Yongchun，YAN Liubin. A new method for forecasting of blasting effect in rock mass[J]. Chinese Journal of Rock Mechanics and Engineering，2007，26(Supp.1)：3 509-3 513.(in Chinese))
[3]
朱智杰，卢书强，梅 军. 基于有效降雨量的滑坡位移-降雨相关性研究[J]. 长江科学院院报，2023，40(12)：162-168.(ZHU Zhijie，LU Shuqiang，MEI Jun. Study on Landslide displacement-rainfall correlation based on effective rainfall[J]. Journal of Yangtze River Scientific Research Institute，2023，40(12)：162-168.(in Chinese))
[13]
MARK N. GIBBS. Bayesian Gaussian processes for regression and classification[Ph. D. Thesis][D]. Cambridge：University of Cambridge，1998.
[1]
唐 栋，李典庆，周创兵，等. 考虑前期降雨过程的边坡稳定性分析[J]. 岩土力学，2013，34(11)：3 239-3 248.(TANG Dong，LI Dianqing，ZHOU Chuangbing，et al. Slope stability analysis considering antecedent rainfall process[J]. Rock and Soil Mechanics，2013，34(11)：3 239-3 248. (in Chinese))
[11]
张 俊，殷坤龙，王佳佳，等. 基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J]. 岩石力学与工程学报，2015，34(2)：382-391.(ZHANG Jun，YIN Kunlong，WANG Jiajia，et al. Displacement prediction of Baishuihe landslide based on time series and PSO-SVR model[J]. Chinese Journal of Rock Mechanics and Engineering，2015，34(2)：382-391.(in Chinese))
[8]
秦四清，张倬元，王士天，等. 滑坡时间预报的突变理论及灰色突变理论方法[J]. 大自然探索，1993，46(4)：62-68.(QIN Siqing，ZHANG Zhuoyuan，WANG Shitian，et al. Catastrophe theory and grey catastrophe theory method for landslide time prediction[J]. Discovery of Nature，1993，46(4)：62-68.(in Chinese))
[10]
杨背背，殷坤龙，杜 娟. 基于时间序列与长短时记忆网络的滑坡位移动态预测模型[J]. 岩石力学与工程学报，2018，37(10)：2 334-2 343.(YANG Beibei，YIN Kunlong，DU Juan. A model for predicting landslide displacement based on time series and long and short term memory neural network[J]. Chinese Journal of Rock Mechanics and Engineering，2018，37(10)：2 334-2 343.(in Chinese))
[6]
陈明东，玉兰生. 边坡变形破坏的灰色预报方法[C]// 第三届全国工程地质大会论文集. 成都：成都科技大学出版社，1988：8.(CHEN Mingdong，YU Lansheng. Grey prediction method for slope deformation and failure[C]// Proceedings of the Third National Engineering Geological Congress. Chengdu：Chengdu University of Science and Technology Press，1988：8.(in Chinese))
[16]
徐 冲，刘保国. 基于粒子群-高斯过程回归耦合算法的滑坡位移时序分析预测智能模型[J]. 岩土力学，2011，32(6)：1 669-1 675. (XU Chong，LIU Baoguo. Intelligent analysis model of landslide displacement time series based on coupling PSO-GPR[J]. Rock and Soil Mechanics，2011，32(6)：1 669-1 675.(in Chinese))
[4]
王念秦，王永锋，罗东海，等. 中国滑坡预测预报研究综述[J]. 地质论评，2008，54(3)：355-360. (WANG Nianqin，WANG Yongfeng，LUO Donghai，et al. Review of landslide prediction and forecast research in China[J]. Geological Review，2008，54(3)：355-360.(in Chinese))
2024, Vol. 43 
