针对滑坡位移难以预测、影响因素难以选择等问题,提出一种结合了二次移动平均(DMA)法、变分模态分解(VMD)、改进灰狼优化(IGWO)算法与支持向量回归(SVR)的模型进行滑坡位移预测。首先,利用DMA提取滑坡位移趋势项和周期项,采用多项式拟...针对滑坡位移难以预测、影响因素难以选择等问题,提出一种结合了二次移动平均(DMA)法、变分模态分解(VMD)、改进灰狼优化(IGWO)算法与支持向量回归(SVR)的模型进行滑坡位移预测。首先,利用DMA提取滑坡位移趋势项和周期项,采用多项式拟合对趋势项进行预测;其次,对滑坡周期项的影响因素进行分类,采用VMD对原始影响因子序列进行分解获得最优序列;再次,提出一种结合SVR与基于改进Circle多策略的灰狼优化算法CTGWO-SVR(Circle Tactics Grey Wolf Optimizer with SVR)对滑坡周期项进行预测;最后采用时间序列加法模型求出累计位移预测序列,并采用灰色预测的后验证差校验和小概率误差对模型进行评价。实验结果表明,与GA-SVR和GWO-SVR模型相比,CTGWO-SVR的预测精度更高,拟合度达到0.979,均方根误差分别减小了51.47%与59.25%,预测精度等级为一级,可满足滑坡预测的实时性和准确性要求。展开更多
Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displ...Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displacement difficult.Moreover,in engineering practice,insufficient monitoring data limit the performance of prediction models.To alleviate this problem,a displacement prediction method based on multisource domain transfer learning,which helps accurately predict data in the target domain through the knowledge of one or more source domains,is proposed.First,an optimized variational mode decomposition model based on the minimum sample entropy is used to decompose the cumulative displacement into the trend,periodic,and stochastic components.The trend component is predicted by an autoregressive model,and the periodic component is predicted by the long short-term memory.For the stochastic component,because it is affected by uncertainties,it is predicted by a combination of a Wasserstein generative adversarial network and multisource domain transfer learning for improved prediction accuracy.Considering a real mine slope as a case study,the proposed prediction method was validated.Therefore,this study provides new insights that can be applied to scenarios lacking sample data.展开更多
There are two technical challenges in predicting slope deformation.The first one is the random displacement,which could not be decomposed and predicted by numerically resolving the observed accumulated displacement an...There are two technical challenges in predicting slope deformation.The first one is the random displacement,which could not be decomposed and predicted by numerically resolving the observed accumulated displacement and time series of a landslide.The second one is the dynamic evolution of a landslide,which could not be feasibly simulated simply by traditional prediction models.In this paper,a dynamic model of displacement prediction is introduced for composite landslides based on a combination of empirical mode decomposition with soft screening stop criteria(SSSC-EMD)and deep bidirectional long short-term memory(DBi-LSTM)neural network.In the proposed model,the time series analysis and SSSC-EMD are used to decompose the observed accumulated displacements of a slope into three components,viz.trend displacement,periodic displacement,and random displacement.Then,by analyzing the evolution pattern of a landslide and its key factors triggering landslides,appropriate influencing factors are selected for each displacement component,and DBi-LSTM neural network to carry out multi-datadriven dynamic prediction for each displacement component.An accumulated displacement prediction has been obtained by a summation of each component.For accuracy verification and engineering practicability of the model,field observations from two known landslides in China,the Xintan landslide and the Bazimen landslide were collected for comparison and evaluation.The case study verified that the model proposed in this paper can better characterize the"stepwise"deformation characteristics of a slope.As compared with long short-term memory(LSTM)neural network,support vector machine(SVM),and autoregressive integrated moving average(ARIMA)model,DBi-LSTM neural network has higher accuracy in predicting the periodic displacement of slope deformation,with the mean absolute percentage error reduced by 3.063%,14.913%,and 13.960%respectively,and the root mean square error reduced by 1.951 mm,8.954 mm and 7.790 mm respectively.Conclusively,this model not o展开更多
Decomposing co-seismic deformation is an immediate need for researchers who are interested in earthquake inversion analysis and geo-hazard mapping. However, conventional InSAR or digital elevation models （DEMs） imag...Decomposing co-seismic deformation is an immediate need for researchers who are interested in earthquake inversion analysis and geo-hazard mapping. However, conventional InSAR or digital elevation models （DEMs） imagery analyses only provide the displacement in the Line-of-Sight （LOS） direction or elevation changes. The 2004 Mid-Niigata earthquake in Japan provides lessons on how to decompose co-seismic deformation from two sets of DEMs. If three adjacent points undergo a rigid-body-translation movement, their co-seismic deformation can be decomposed by solving simultaneous equations. Although this method has been successfully used to discuss tectonic deformations, the algorithm needed improvement and a more rigorous algorithm, including a new definition of nominal plane, DEMs comparability improvement and matrix condition check is provided. Even with these procedures, the obtained decomposed displacement often showed remarkable scatter prompting the use of the moving average method, which was used to determine both tectonic and localized displacement characteristics. A cut-off window and a pair of band-pass windows were selected according to the regional geology and construction activities to ease the tectonic and localized displacement calculations, respectively. The displacement field of the tectonic scale shows two major clusters of large lateral components, and coincidently major visible landslides were found mostly within them. The localized displacement helps to reveal hidden landslides in the target area. As far as the Kizawa hamlet is concerned, the obtained vectors show down-slope movements, which are consistent with the observed traces of dislocations that were found in the Kizawa tunnel and irrigation wells. The method proposed has great potential to be applied to understanding post-earthquake rehabilitation in other areas.展开更多
A fast algorithm FBTQ is presented which computes the QR factorization a block-Toeplitz matrix A (A∈R) in O(mns3) multiplications. We prove that the QR decomposition of A and the inverse Cholesky decomposition can be...A fast algorithm FBTQ is presented which computes the QR factorization a block-Toeplitz matrix A (A∈R) in O(mns3) multiplications. We prove that the QR decomposition of A and the inverse Cholesky decomposition can be computed in parallel using the sametransformation.We also prove that some kind of Toeplltz-block matrices can he transformed into the corresponding block-Toeplitz matrices.展开更多
文摘针对滑坡位移难以预测、影响因素难以选择等问题,提出一种结合了二次移动平均(DMA)法、变分模态分解(VMD)、改进灰狼优化(IGWO)算法与支持向量回归(SVR)的模型进行滑坡位移预测。首先,利用DMA提取滑坡位移趋势项和周期项,采用多项式拟合对趋势项进行预测;其次,对滑坡周期项的影响因素进行分类,采用VMD对原始影响因子序列进行分解获得最优序列;再次,提出一种结合SVR与基于改进Circle多策略的灰狼优化算法CTGWO-SVR(Circle Tactics Grey Wolf Optimizer with SVR)对滑坡周期项进行预测;最后采用时间序列加法模型求出累计位移预测序列,并采用灰色预测的后验证差校验和小概率误差对模型进行评价。实验结果表明,与GA-SVR和GWO-SVR模型相比,CTGWO-SVR的预测精度更高,拟合度达到0.979,均方根误差分别减小了51.47%与59.25%,预测精度等级为一级,可满足滑坡预测的实时性和准确性要求。
基金supported by the National Natural Science Foundation of China(Grant No.51674169)Department of Education of Hebei Province of China(Grant No.ZD2019140)+1 种基金Natural Science Foundation of Hebei Province of China(Grant No.F2019210243)S&T Program of Hebei(Grant No.22375413D)School of Electrical and Electronics Engineering。
文摘Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displacement difficult.Moreover,in engineering practice,insufficient monitoring data limit the performance of prediction models.To alleviate this problem,a displacement prediction method based on multisource domain transfer learning,which helps accurately predict data in the target domain through the knowledge of one or more source domains,is proposed.First,an optimized variational mode decomposition model based on the minimum sample entropy is used to decompose the cumulative displacement into the trend,periodic,and stochastic components.The trend component is predicted by an autoregressive model,and the periodic component is predicted by the long short-term memory.For the stochastic component,because it is affected by uncertainties,it is predicted by a combination of a Wasserstein generative adversarial network and multisource domain transfer learning for improved prediction accuracy.Considering a real mine slope as a case study,the proposed prediction method was validated.Therefore,this study provides new insights that can be applied to scenarios lacking sample data.
文摘There are two technical challenges in predicting slope deformation.The first one is the random displacement,which could not be decomposed and predicted by numerically resolving the observed accumulated displacement and time series of a landslide.The second one is the dynamic evolution of a landslide,which could not be feasibly simulated simply by traditional prediction models.In this paper,a dynamic model of displacement prediction is introduced for composite landslides based on a combination of empirical mode decomposition with soft screening stop criteria(SSSC-EMD)and deep bidirectional long short-term memory(DBi-LSTM)neural network.In the proposed model,the time series analysis and SSSC-EMD are used to decompose the observed accumulated displacements of a slope into three components,viz.trend displacement,periodic displacement,and random displacement.Then,by analyzing the evolution pattern of a landslide and its key factors triggering landslides,appropriate influencing factors are selected for each displacement component,and DBi-LSTM neural network to carry out multi-datadriven dynamic prediction for each displacement component.An accumulated displacement prediction has been obtained by a summation of each component.For accuracy verification and engineering practicability of the model,field observations from two known landslides in China,the Xintan landslide and the Bazimen landslide were collected for comparison and evaluation.The case study verified that the model proposed in this paper can better characterize the"stepwise"deformation characteristics of a slope.As compared with long short-term memory(LSTM)neural network,support vector machine(SVM),and autoregressive integrated moving average(ARIMA)model,DBi-LSTM neural network has higher accuracy in predicting the periodic displacement of slope deformation,with the mean absolute percentage error reduced by 3.063%,14.913%,and 13.960%respectively,and the root mean square error reduced by 1.951 mm,8.954 mm and 7.790 mm respectively.Conclusively,this model not o
文摘Decomposing co-seismic deformation is an immediate need for researchers who are interested in earthquake inversion analysis and geo-hazard mapping. However, conventional InSAR or digital elevation models （DEMs） imagery analyses only provide the displacement in the Line-of-Sight （LOS） direction or elevation changes. The 2004 Mid-Niigata earthquake in Japan provides lessons on how to decompose co-seismic deformation from two sets of DEMs. If three adjacent points undergo a rigid-body-translation movement, their co-seismic deformation can be decomposed by solving simultaneous equations. Although this method has been successfully used to discuss tectonic deformations, the algorithm needed improvement and a more rigorous algorithm, including a new definition of nominal plane, DEMs comparability improvement and matrix condition check is provided. Even with these procedures, the obtained decomposed displacement often showed remarkable scatter prompting the use of the moving average method, which was used to determine both tectonic and localized displacement characteristics. A cut-off window and a pair of band-pass windows were selected according to the regional geology and construction activities to ease the tectonic and localized displacement calculations, respectively. The displacement field of the tectonic scale shows two major clusters of large lateral components, and coincidently major visible landslides were found mostly within them. The localized displacement helps to reveal hidden landslides in the target area. As far as the Kizawa hamlet is concerned, the obtained vectors show down-slope movements, which are consistent with the observed traces of dislocations that were found in the Kizawa tunnel and irrigation wells. The method proposed has great potential to be applied to understanding post-earthquake rehabilitation in other areas.
文摘A fast algorithm FBTQ is presented which computes the QR factorization a block-Toeplitz matrix A (A∈R) in O(mns3) multiplications. We prove that the QR decomposition of A and the inverse Cholesky decomposition can be computed in parallel using the sametransformation.We also prove that some kind of Toeplltz-block matrices can he transformed into the corresponding block-Toeplitz matrices.
