滑坡是一种严重威胁危害居民生命财产安全的自然灾害，滑坡位移预测有助于预测滑坡等自然灾害.滑坡体监测数据的处理和预测模型的建立是滑坡位移预测的基础.针对当前时间序列分析中应用广泛的EMD、EEMD分解算法的缺陷，将具有严格数学理论支撑且分解个数可控的变分模态分解算法应用于位移时间序列分解，以获得滑坡位移子序列.将自适应变异粒子群优化算法(AMPSO)和支持向量机(SVM)相结合，构建AMPSO-SVM位移预测耦合模型.运用耦合模型对分解所得位移子序列分别进行预测，然后重构子序列预测结果得到总位移预测值.以三峡库区白水河滑坡XD1监测点为例，针对2007～2012年监测数据，设置不同情景以验证所提出预测模型的有效性及稳定性.实例分析表明，基于变分模态分解和AMPSO-SVM耦合模型对于滑坡位移的预测性能优于BP神经网络预测模型和网格搜索优化的SVM模型，在滑坡位移预测中有良好的理论基础及工程应用价值.
Landslide is a natural disaster that seriously threatens and endangers the safety of life and property of residents. Landslide displacement prediction is helpful to predict natural disasters such as landslide. Monitoring data processing and the establishment of prediction model are the basis of landslide displacement prediction. According to the shortcomings of the EMD and EEMD decomposition algorithms which are applied widely in present analysis of time series，the variational mode decomposition algorithm is applied in signal processing to the landslide displacement sequences decomposition to obtain the subsequences. The AMPSO-SVM displacement prediction coupling model is constructed by combining adaptive mutation particle swarm optimization (AMPSO) and support vector machine (SVM). Apply the coupling model to predict displacement subsequences separately， then reconstruct all the sub-sequences prediction results and the total displacement prediction value is acquired. Taking the monitoring point XD1 in the Baishuihe landslide in the Three Gorges Reservoir area as an example, different scenarios are set to clarify the validity and stability of the proposed model. The case studies show that the prediction performance of landslide displacement based on variational mode decomposition and AMPSO-SVM coupling model is superior to BP neural network prediction model and SVM model optimized by the grid search algorithm, and it has a good theoretical basis and engineering application value.
［1］程温鸣, 彭令, 牛瑞卿. 基于粗糙集理论的滑坡易发性评价——以三峡库区秭归县境内为例［J］. 中南大学学报(自然科学版), 2013, 44(3): 1083-1090.
CHENG Wenming, PENG Ling, NIU Ruiqing. Landslide suspectibility assessment based on rough set theory: Taking Zigui County territory in Three Gorges Reservoir for example［J］. Journal of Central South University (Science and Technology), 2013, 44(3): 1083-1090.
［2］REN F, WU X, ZHANG K, et al. Application of wavelet analysis and a particle swarm-optimized support vector machine to predict the displacement of the Shuping landslide in the Three Gorges, China［J］. Environment Earth Sciences, 2015, 73(8): 4791-4804.
［3］SHIHABUDHEEN K V, PILLAI G N, PEETHAMBARAN B. Prediction of landslide displacement with controlling factors using extreme learning adaptive neuro-fuzzy inference system (ELANFIS)［J］. Applied Soft Computing, 2017, 61: 892-904.
［4］HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis［J］. Proceedings: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995.
［5］邓冬梅, 梁烨, 王亮清, 等. 基于时间序列EEMD重构的滑坡位移PSO-SVR预测方法——以三峡库区滑坡为例［J］. 岩土力学, 2017, 38(12): 1001-1009.
DENG Dongmei, LIANG Ye, WANG Liangqing, et al. PSO-SVR prediction method for landslide displacement based on reconstruction of time series by EEMD: A case study of landslides in Three Gorges Reservoir area［J］. Rock and Soil Mechanics, 2017, 38(12): 1001-1009.
［6］WU Z, HUANG N E. Ensemble empirical mode decomposition: A noise-assisted data analysis method［J］. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41.
［7］CAI Z, XU W, MENG Y, et al. Prediction of landslide displacement based on GA-LSSVM with multiple factors［J］. Bulletin of Engineering Geology and the Environment, 2016, 75(2): 637-646.
［8］ZHOU C, YIN K, CAO Y, et al. Application of time series analysis and PSO-SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir, China ［J］. Engineering Geology, 2016, 204: 108-120.
［9］DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition［J］. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
［10］EBERHART R. KENNEDY J. A new optimizer using particle swarm theory［C］//Proceedings of the Sixth International Symposium on Micro Machine and Human Science. Nagoya, Japan: IEEE, 1995: 39-43.
［11］吕振肃, 侯志荣. 自适应变异的粒子群优化算法［J］. 电子学报, 2004, 32(3): 416-420.
L Zhensu, HOU Zhirong. Particle swarm optimization with adaptive mutation［J］. Acta Electronica Sinica, 2004, 32(3): 416-420.
［12］VAPNIK V N. The nature of statistical learning theory ［M］. 2nd ed. New York, USA: Springer-Verlag, 2000.
［13］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.
［14］陈果, 周伽. 小样本数据的支持向量机回归模型参数及预测区间研究［J］. 计量学报, 2008, 29(1): 92-96.
CHEN Guo, ZHOU Jia. Research on parameters and forecasting interval of support vector regression mo-del to small sample ［J］. Acta Metrologica Sinica, 2008, 29(1): 92-96.
