基于多算法参数优化与SVR模型的白水河滑坡位移预测

滑坡预测对于减轻地质灾害的危害十分重要,但对科学研究却很有挑战性。基于变形特征和位移监测数据,建立了三峡库区白水河滑坡的时间序列加法模型。在模型中,累计位移分为3个部分:趋势、周期和随机项,解释了由内部因素（地质环境,重力等）、外部因素（降雨,水库水位等）、随机因素（不确定性）共同作用的影响。在对位移数据进行统计分析后,提出了一个3次多项式模型对趋势项进行学习,并利用多算法寻优的支持向量回归机（SVR）模型对周期项进行训练与预测。结果表明,在预测精度上,基于时间序列与遗传算法-支持向量回归机（GA-SVR）耦合的位移预测模型要明显优于网格寻优（GS）以及粒子群算法（PSO）优化的支持向量回归机模型。因此,GA-SVR模型在滑坡位移预测方面可以得到较好的应用。在“阶跃型”滑坡位移预测中,GA-SVR将具有广阔的应用前景。     

基于粒子群-变分模态分解、非线性自回归神经网络与门控循环单元的滑坡位移动态预测模型研究

以三峡库区八字门阶跃型滑坡为例,针对静态机器学习模型在周期项位移预测中的不足以及高频随机项位移预测困难等问题,提出了一种新的滑坡位移预测方法。基于时间序列分解思想,采用粒子群算法（PSO）对变分模态分解（VMD）进行参数寻优,并将位移时间序列分解为趋势项、周期项和随机项。趋势项主要受滑坡内部因素影响,采用傅里叶曲线进行拟合预测;周期项由外部因素导致,基于格兰杰因果检验进行成因分析,并引入一种对时间序列历史状态具有较高敏感性的非线性自回归神经网络（NARX）进行预测;随机项频率较高且影响因素无法判定,采用一维门控循环单元（GRU）进行预测。最后将各分量预测位移进行叠加重构,实现滑坡累计位移的预测。结果表明,提出的（PSO-VMD）-NARX-GRU滑坡位移动态预测模型精度较高,且各位移分量预测精度明显高于静态模型中BP神经网络、支持向量机（SVM）和传统自回归模型ARIMA,可为阶跃型滑坡位移预测提供参考。     

基于时间序列与人工蜂群支持向量机的滑坡位移预测研究

总结以往滑坡预测方法存在的诸多不足,针对滑坡监测位移-时间曲线特点,本文提出了一种基于时间序列的人工蜂群算法（ABC）与支持向量回归机（SVR）相结合的滑坡位移预测方法。以三峡库区白水河滑坡为例,通过对滑坡位移、降雨、库水位等因素的分析,研究影响滑坡位移变化的因素。用时间序列加法模型和移动平均法将滑坡位移分解为趋势项和周期项。以多项式最小二乘法拟合滑坡位移趋势项,用人工蜂群支持向量机模型对滑坡位移周期项进行训练和预测。通过灰色系统关联分析法计算多项因子与滑坡位移周期项之间的关联性。最终的滑坡总位移预测值为周期项预测值与趋势项预测值之和。与BP神经网络、PSO-SVR模型方法相比,该方法在滑坡位移预测中有更高的精度,在防灾减灾工作中有较好的推广应用前景。     

基于粒子群优化支持向量机的延长县滑坡易发性评价

参数优化问题直接影响着支持向量机的预测精度和泛化能力,粒子群优化算法具有全局最优搜索能力,因此通过粒子群算法优化支持向量机参数可以有效提高预测精度。以延长县历史滑坡数据为基础,分析了岩性、地貌类型、土壤厚度、坡度、坡向、坡高与滑坡分布的关系,并利用滑坡密度值对各定性或定量因子进行了归一化处理;在此基础上,通过区域内所划分的16 300个斜坡单元作为评价单元,采用粒子群优化支持向量机(PSO-SVM)算法完成了延长县滑坡的易发性评价。从滑坡密度指标角度来看,评价结果中高易发区和极高易发区的历史滑坡数占比72.19%,通过滑坡面积百分比(LAR)等指标进行了有效的验证,均显示出对滑坡易发性评价效果良好。     

PSO-LSSVM模型在位移反分析中的应用

提出了一种基于均匀设计原理、最小二乘支持向量机(LSSVM)和粒子群优化算法(PSO)的快速位移反分析方法。该方法利用均匀设计和有限差分法获得学习样本,再用粒子群算法搜索最优的最小二乘支持向量机模型参数。并用最小二乘支持向量机回归模型建立反演参数与监测点位移值之间的非线性映射关系,最后用粒子群算法从全局空间上搜索与实测位移最吻合的反演参数。该反演模型利用了粒子群算法高效简单、均匀设计构造高质量小样本以及最小二乘支持向量机的小样本、泛化性能好的特点。将该模型应用于龙滩水电站左岸地下厂房区岩体地应力场的反演分析中,计算结果与实测的位移值和地应力值均吻合较好,说明了该模型在岩土工程快速反演分析中具有良好的应用价值。     

基于优化经验模态分解和聚类分析的滑坡位移智能预测研究

针对三峡库区"阶跃式"滑坡的变形特征,提出了一种新的滑坡位移预测方法。以白水河滑坡ZG118和XD-01监测点位移数据为例,采用基于软筛分停止准则的经验模态分解(SSSC-EMD)将累计位移-时间曲线和影响因子时间序列自适应地分解为多个固有模态函数(IMF),并采用K均值(K-Means)聚类法对其进行聚类累加,得到有物理含义的位移分量(趋势性位移、周期性位移以及随机性位移)和影响因子分量(高频影响因子和低频影响因子)。使用最小二乘法对趋势性位移进行拟合预测;采用果蝇优化-最小二乘支持向量机(FOA-LSSVM)模型对周期性位移和随机性位移进行预测。将各位移分量预测值进行叠加处理,实现滑坡累计位移的预测。研究结果表明,所提出的(SSSC-EMD)-K-Means-(FOA-LSSVM)模型能够预测"阶跃式"滑坡的位移变化规律,且预测精度高于传统的支持向量机回归(SVR)、最小二乘支持向量机(LSSVM)模型;并通过改变训练集长度,进行单因素分析,发现其与预测精度之间呈正相关关系。     

基于PSO和LSSVM的边坡稳定性评价方法

提出了基于粒子群算法（PSO）和最小二乘支持向量机（LSSVM）的边坡稳定性评价方法。该模型既利用了最小二乘支持向量机求解速度快、易于描述非线性关系的优良特性,同时也利用了粒子群算法快速全局优化的特点。粒子群算法用于搜索最小二乘支持向量机模型的最优参数,然后将模型用于预测边坡的安全系数。计算结果表明,该方法是合理的、有效的。     

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

高斯过程回归(GPR)学习机有着容易实现、超参数自适应获取及预测输出具有概率意义等优点。通常采用共轭梯度法获取GPR超参数,但其存在优化效果对初值依赖性太强,迭代次数难以确定,易陷入局部最优的缺点。改用粒子群优化 (PSO)算法进行最优超参数搜索,形成粒子群-高斯过程回归耦合算法(PSO-GPR)。将该算法引入三峡永久船闸高边坡、卧龙寺新滑坡、链子崖滑坡3个不同的典型滑坡变形时序分析中,对每个滑坡分别采用稳态核及一种新式神经网络（NN）、平方指数（SE）、有理二次型（RQ）3种单一核函数进行外推预报测试。工程应用表明,基于3种不同单一核函数的粒子群-高斯过程回归算法（PSO-GPR）均能完全适应不同滑坡时序分析,其中以NN核函数外推预测效果最佳,平均相对误差分别为6.37%、7.62%、1.07%,从而改善了在进行不同滑坡变形时序分析时采用单一核函数的核机器外推能力存在较大差异性的问题,提高了单一核函数对不同数据类型的兼容性     

联合多种数据驱动建模方法的滑坡位移预测研究

边坡位移是滑坡演化的宏观体现,分析并预测滑坡位移发展态势对于防灾减灾具有重要意义。由于滑坡位移曲线具有明显的非线性特征,单一模型往往难以刻画其非线性与复杂性。为发展一种普遍适用于滑坡位移的预测方法,提出了一种联合多种数据驱动模型的新方法。该方法根据时间序列分析理论,将滑坡位移序列分解为趋势项和周期项,趋势项采用并联型灰色神经网络处理,周期项则采用人工蜂群算法（ABC）优化后的极限学习机模型（ELM）处理,从而充分应用各种模型的优点。以三峡库区白水河和八字门滑坡为例,对位移数据进行分析处理后,灰色神经网络模型预测其趋势性位移,改进后的极限学习机模型对周期性位移进行训练及预测。结果表明:在预测精度上,优化后的极限学习机模型准确度高于极限学习机模型及小波神经网络等方法,提出的灰色神经网络与ABC-ELM的组合模型可作为实际工程的一个参考。     

基于集合经验模态分解与支持向量机回归的位移预测方法:以三峡库区滑坡为例

三峡库区滑坡地表位移-时间曲线多呈台阶型特征。基于位移响应成分模型的滑坡位移预测方法是该类滑坡位移预测的主要方法之一。针对目前水库滑坡波动项位移预测工作中尚未考虑主要诱发因素的高频成分与低频成分的问题,提出了基于时间序列集合经验模态分解(EEMD)与重构的粒子群优化-支持向量机回归(PSO-SVR)位移预测方法。以白水河滑坡2003年7月至2013年3月117个地表位移数据为例,采用EEMD法将位移时间序列分解为趋势项位移和波动项位移,该趋势项位移用最小二乘法的二次多项式拟合预测;根据EEMD和t检验法,确定高频降雨量、低频降雨量、高频库水位和低频库水位,结合其他常用因素,采用灰色关联分析确定白水河滑坡影响波动项位移的优势因素为高频降雨量和月间库水位变化,基于优势因素建立PSO-SVR模型预测波动项位移。结果表明,总预测值的平均相对误差为0.009 8,方差比为0.023 9,小误差概率为1,预测效果较好。利用该方法对三峡库区其他5个台阶型滑坡进行了预测,预测位移与实测位移较吻合,进一步证明了该方法的有效性,对同类滑坡的预测预报具有一定的借鉴意义。     

Prediction of landslide displacement with step-like behavior based on multialgorithm optimization and a support vector regression model

Landslide prediction is important for mitigating geohazards but is very challenging. In landslide evolution, displacement depends on the local geological conditions and variations in the controlling factors. Such factors have led to the “step-like” deformation of landslides in the Three Gorges Reservoir area of China. Based on displacement monitoring data and the deformation characteristics of the Baishuihe Landslide, an additive time series model was established for landslide displacement prediction. In the model, cumulative displacement was divided into three parts: trend, periodic, and random terms. These terms reflect internal factors (geological environmental, gravity, etc.), external factors (rainfall, reservoir water level, etc.), and random factors (uncertainties). After statistically analyzing the displacement data, a cubic polynomial model was proposed to predict the trend term of displacement. Then, multiple algorithms were used to determine the optimal support vector regression (SVR) model and train and predict the periodic term. The results showed that the landslide displacement values predicted based on data time series and the genetic algorithm (GA-SVR) model are better than those based on grid search (GS-SVR) and particle swarm optimization (PSO-SVR) models. Finally, the random term was accurately predicted by GA-SVR. Therefore, the coupled model based on temporal data series and GA-SVR can be used to predict landslide displacement. Additionally, the GA-SVR model has broad application potential in the prediction of landslide displacement with “step-like” behavior.     

Interval prediction of landslide displacement with dual-output least squares support vector machine and particle swarm optimization algorithms

For landslide displacement, interval predictions are generally more realistic and reliable compared with traditional point predictions. This paper presents a new interval prediction method for landslide displacement integrating dual-output least squares support vector machine (DO-LSSVM) and particle swarm optimization (PSO) algorithms. In this new method, the PSO algorithm is employed to optimize coefficients of the least squares support vector machine (LSSVM) model for obtaining point prediction results, and the interval prediction of the landslide displacement is made based on the dual-outputs obtained from the DO-LSSVM model. To assess the rationality of the predictions, three performance evaluation indicators, including the prediction interval coverage probability (PICP), normalized mean prediction interval width (NMPIW), and coverage width-based criterion (CWC), are established. Case studies of the Tanjiahe landslide and the Baishuihe landslide in the Three Gorges Reservoir region are then used to demonstrate the effectiveness of the proposed method in predicting the landslide displacement interval. The case study results demonstrate that this new method has the best overall performance compared with other existing methods, and this new method can provide accurate and reliable results for the medium- to long-term interval prediction of landslide displacement.

     

Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method

Landslide displacement prediction is an essential component for developing landslide early warning systems. In the Three Gorges Reservoir area (TGRA), landslides experience step-like deformations (i.e., periods of stability interrupted by abrupt accelerations) generally from April to September due to the influence of precipitation and reservoir scheduled level variations. With respect to many traditional machine learning techniques, two issues exist relative to displacement prediction, namely the random fluctuation of prediction results and inaccurate prediction when step-like deformations take place. In this study, a novel and original prediction method was proposed by combining the wavelet transform (WT) and particle swarm optimization-kernel extreme learning machine (PSO-KELM) methods, and by considering the landslide causal factors. A typical landslide with a step-like behavior, the Baishuihe landslide in TGRA, was taken as a case study. The cumulated total displacement was decomposed into trend displacement, periodic displacement (controlled by internal geological conditions and external triggering factors respectively), and noise. The displacement items were predicted separately by multi-factor PSO-KELM considering various causal factors, and the total displacement was obtained by summing them up. An accurate prediction was achieved by the proposed method, including the step-like deformation period. The performance of the proposed method was compared with that of the multi-factor extreme learning machine (ELM), support vector regression (SVR), backward propagation neural network (BPNN), and single-factor PSO-KELM. Results show that the PSO-KELM outperforms the other models, and the prediction accuracy can be improved by considering causal factors.     

基于时间序列分解和多变量混沌模型的滑坡阶跃式位移预测

三峡库区某些库岸滑坡在强降雨、库水位涨落等诱发因素影响下,其位移时间序列表现出阶跃式变化特征且可能存在混沌特性.但目前常用于滑坡位移预测的混沌模型,均建立在单变量混沌理论的基础之上.且已有的考虑了诱发因素的常规多变量模型,大都采用经验性的方法来选取输入变量;常规多变量模型对滑坡位移序列的非线性特征,及其与诱发因素间的动态响应关系缺乏数学理论上的深入分析.因此,提出一种基于指数平滑法、多变量混沌模型和极限学习机（extreme learing machine,ELM）的滑坡位移组合预测模型.指数平滑多变量混沌ELM模型首先对滑坡累积位移序列的混沌特性进行识别;然后用指数平滑法对累积位移进行预测,得到趋势项位移,并用累积位移减去趋势项位移得到剩余的波动项位移;之后对波动项位移及降雨量、库水位变化量这3个因子进行多变量相空间重构,并用ELM模型对多变量重构后的波动项位移进行预测;最后将预测得到的趋势项和波动项位移值相加,得到最终的累积位移预测值.以三峡库区白水河滑坡ZG93监测点的累积位移作为实例进行分析,并将模型与指数平滑多变量混沌粒子群-支持向量机（PSO-SVM）模型、指数平滑单变量混沌ELM模型作对比.结果表明滑坡位移序列存在混沌特性,模型能有效预测滑坡位移,其预测效果优于对比模型.且本文模型从混沌理论的角度将波动项位移与降雨量、库水位变化量的动态响应关系进行综合分析,更能反映滑坡位移系统演化的物理本质.      

Comparison on landslide nonlinear displacement analysis and prediction with computational intelligence approaches

Landslide displacement is widely obtained to discover landslide behaviors for purpose of event forecasting. This article aims to present a comparative study on landslide nonlinear displacement analysis and prediction using computational intelligence techniques. Three state-of-art techniques, the support vector machine (SVM), the relevance vector machine (RVM), and the Gaussian process (GP), are comparatively presented briefly for modeling landslide displacement series. The three techniques are discussed comparatively for both fitting and predicting the landslide displacement series. Two landslides, the Baishuihe colluvial landslide in China Three Georges and the Super-Sauze mudslide in the French Alps, are illustrated. The results prove that the computational intelligence approaches are feasible and capable of fitting and predicting landslide nonlinear displacement. The Gaussian process, on the whole, performs better than the support vector machine, relevance vector machine, and simple artificial neural network (ANN) with optimized parameter values in predictive analysis of the landslide displacement.     

基于时间序列与混合核函数SA-SVR的滑坡位移预测模型研究

本文针对阶跃型滑坡变形定量预测困难,提出一种基于时间序列分解与混合核函数SA-SVR的滑坡位移预测模型.首先基于时间序列分解原理,反复使用指数平滑法将滑坡累积位移分解为趋势项位移和周期项位移,使分解后的趋势项位移较平滑且能保证周期项位移的预测精度.同时针对多项式预测容易过拟合造成预测值偏离真实值的问题,采用K-flod...