首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 421 毫秒
1.
结合灰色模型和神经网络的数据处理特点,提出串联、并联和混联式3种结构的灰色神经网络滑坡变形预测模型。串联式将滑坡变形位移时序分解为趋势项和随机项,采用灰色模型提取滑坡位移时序趋势,利用神经网络逼近随机波动;并联式以灰色模型和神经网络分别对滑坡预测,采用智能非线性组合,按照预测目标精度动态调整权重,从而获取最终组合预测结果;混联式通过增加灰白化层及灰模型群,对神经网络拓扑结构进行优化,达到弱化滑坡原始监测数据随机性、提高预测模型稳健性的目的。将3种模型应用于古树屋滑坡变形预测,并对其适用性进行讨论。结果表明,3种结构的灰色神经网络耦合模型均提高了预测精度,适用于复杂状况下滑坡体的变形预测。  相似文献   

2.
Accurate prediction on geological hazards can prevent disaster events in advance and greatly reduce property losses and life casualties.Glacial debris flows are the most serious hazards in southeastern Tibet in China due to their complexity in formation mechanism and the difficulty in prediction.Data collected from 102 glacier debris flow events from 31 gullies since 1970 and regional meteorological data from 1970 to 2019 in ParlungZangbo River Basin in southeastern Tibet were used for Artificial Neural Network(ANN)-based prediction of glacial debris flows.The formation mechanism of glacial debris flows in the ParlungZangbo Basin was systematically analyzed,and the calculations involving the meteorological data and disaster events were conducted by using the statistical methods and two layers fully connected neural networks.The occurrence probabilities and scales of glacial debris flows(small,medium,and large)were predicted,and promising results have been achieved.Through the proposed model calculations,a prediction accuracy of 78.33%was achieved for the scale of glacial debris flows in the study area.The prediction accuracy for both large-and medium-scale debris flows are higher than that for small-scale debris flows.The debris flow scale and the probability of occurrence increase with increasing rainfall and temperature.In addition,the K-fold cross-validation method was used to verify the reliability of the model.The average accuracy of the model calculated under this method is about 93.3%,which validates the proposed model.Practices have proved that the combination of ANN and disaster events can provide sound prediction on geological hazards under complex conditions.  相似文献   

3.
??????μ???????????????????????????????????????????????????????????????з????????????????????????????????????????????????????￡?????????????????????????????????????????????????????????????????????Ч?????б????????????????????????????????????????????????????  相似文献   

4.
The Digital Elevation Model(DEM) data of debris flow prevention engineering are the boundary of a debris flow prevention simulation, which provides accurate and reliable DEM data and is a key consideration in debris flow prevention simulations. Thus, this paper proposes a multi-source data fusion method. First, we constructed 3D models of debris flow prevention using virtual reality technology according to the relevant specifications. The 3D spatial data generated by 3D modeling were converted into DEM data for debris flow prevention engineering. Then, the accuracy and applicability of the DEM data were verified by the error analysis testing and fusion testing of the debris flow prevention simulation. Finally, we propose the Levels of Detail algorithm based on the quadtree structure to realize the visualization of a large-scale disaster prevention scene. The test results reveal that the data fusion method controlled the error rate of the DEM data of the debris flow prevention engineering within an allowable range and generated 3D volume data(obj format) to compensate for the deficiency of the DEM data whereby the 3D internal entity space is not expressed. Additionally, the levels of detailed method can dispatch the data of a large-scale debris flow hazard scene in real time to ensure a realistic 3D visualization. In summary, the proposed methods can be applied to the planning of debris flow prevention engineering and to the simulation of the debris flow prevention process.  相似文献   

5.
《山地科学学报》2020,17(8):1860-1873
At present,most researches on the critical rainfall threshold of debris flow initiation use a linear model obtained through regression.With relatively weak fault tolerance,this method not only ignores nonlinear effects but also is susceptible to singular noise samples,which makes it difficult to characterize the true quantization relationship of the rainfall threshold.Besides,the early warning threshold determined by statistical parameters is susceptible to negative samples(samples where no debris flow has occurred),which leads to uncertainty in the reliability of the early warning results by the regression curve.To overcome the above limitations,this study develops a data-driven multiobjective evolutionary optimization method that combines an artificial neural network(ANN) and a multiobjective evolutionary optimization implemented by particle swarm optimization(PSO).Firstly,the Pareto optimality method is used to represent the nonlinear and conflicting critical thresholds for the rainfall intensity I and the rainfall duration D.An ANN is used to construct a dual-target(dual-task) predictive surrogate model,and then a PSO-based multiobjective evolutionary optimization algorithm is applied to train the ANN and stochastically search the trained ANN for obtaining the Pareto front of the I-D surrogate prediction model,which is intended to overcome the limitations of the existing linear regression-based threshold methods.Finally,a double early warning curve model that can effectively control the false alarm rate and negative alarm rate of hazard warnings are proposed based on the decision space and target space maps.This study provides theoretical guidance for the early warning and forecasting of debris flows and has strong applicability.  相似文献   

6.
The phenomenon of debris flow is intermediate between mass movement and solid transport. Flows can be sudden, severe and destructive. Understanding debris flow erosion processes is the key to providing geomorphic explanations, but progress has been limited because the physical-mechanical properties, movement laws and erosion characteristics are different from those of sediment-laden flow. Using infinite slope theory, this research examines the process and mechanism of downcutting erosion over a moveable bed in a viscous debris flow gully. It focuses specifically on the scour depth and the critical slope for viscous debris flow,and formulas for both calculations are presented.Both scour depth and the critical conditions of downcutting erosion are related to debris flow properties(sand volume concentration and flow depth) and gully properties(longitudinal slope,viscous and internal friction angle of gully materials,and coefficient of kinetic friction). In addition, a series of flume experiments was carried out to characterize the scouring process of debris flows with different properties. The calculated values agreed well with the experimental data. These theoretical formulas are reasonable, and using infinite slope theory to analyze down cutting erosion from viscous debris flow is feasible.  相似文献   

7.
跨海大桥系统受外界影响扰动,其变形伴有混沌现象发生。对桥梁变形监测数据实现了混沌识别,运用C-C法计算时间序列的延迟时间,用G-P方法求得最佳嵌入维数,通过求取的时间延迟和最佳嵌入维数对桥梁变形监测数据进行相空间重构,为混沌时间序列预测模型的建立奠定基础;基于RBF神经网络建立混沌时间序列预测模型,对实测数据进行桥梁变形水平位移预测,并与基于最大Lyapunov指数混沌时间序列预测结果以及实测数据进行对比分析。结果表明,基于RBF神经网络建立的混沌时间序列预测模型的预测结果比基于最大Lyapunov指数混沌时间序列预测模型的预测结果要好,且短期预测效果好。  相似文献   

8.
针对地震观测数据难以准确预测的难题,提出基于核混合效应回归模型。为验证该算法模型的可行性,结合湖北地震台站地球物理仪器产出数据开展仿真实验,并与传统的神经网络算法作对比。结果表明,该模型能准确预测地震地球物理观测数据且性能优于其他神经网络算法,对水温、水位数据的预测相对误差低于0.05%及0.48%。该研究为地震监测预报人员积累、分析地震基础数据提供了全新思路,同时也为较复杂的深度学习类算法框架模型的构建提供了实践基础。  相似文献   

9.
Techniques of gully-specific debris flow hazard assessment developed in four periods since the end of the1980s have been discussed in the present paper. The improvement for the empirical assessment method is the sectional-ized function transformation for the factor value, rather than the classified logical transformation. The theoretical equationof the gully-specific debris flow hazard is expressed as the definite integral of an exponential function and its numericalsolution is expressed by the Poisson Limit Equation. Current methods for assessment of debris flow hazard in China arestill valid and practical. The further work should be put on the study of the reliability (or uncertainty) of the techniques.For the future, we should give a high priority to the relationship between debris flow magnitude and its frequency of occur-rence, make more developments of prediction model on debris flow magnitude, so as to finally reach the goal of assessingthe hazard of debris flow by theoretical model, and realize both actuality assessment and prediction appraisal of debris flow.  相似文献   

10.
Debris flows are recurrent natural hazards in many mountainous regions.This paper presents a numerical study on the propagation of debris flows in natural erodible open channels,in which the bed erosion and sedimentation processes are important.Based on the Bingham fluid theory,a mathematical model of the two-dimensional non-constant debris flow is developed.The governing equations include the continuity and momentum conservation equations of debris flow,the sediment convection-diffusion equation,the bed erosion-deposition equation and the bed-sediment size gradation adjustment equation.The yield stress and shear stress components are included to describe the dynamic rheological properties.The upwind control-volume Finite Volume Method (FVM) is applied to discretize the convection terms.The improved SIMPLE algorithm with velocity-free-surface coupled correction is developed to solve the equations on non-orthogonal,quadrilateral grids.The model is applied to simulate a debris flow event in Jiangjia Gully,Yunnan Province and to predict the flow pattern and bed erosion-deposition processes.The results show the effectiveness of the proposed numercial model in debris flow simulation and potential hazard analysis.  相似文献   

11.
In the investigation of debris flow, the detection of the source area of the post-disaster debris flow is an important basis for evaluating the distribution of the debris flow accumulation layer and the subsequent control. In this paper, a shallow high-resolution TEM is used to detect the debris flow source area in Dashigou village, Yongji County, Jilin Province. The purpose of this investigation is to determine the depth range of debris flow damage. The detection results show that there is an obvious low resistance zone at about 10 m depth along the survey line, which is in good agreement with the drilling data and the high density electrical detection. It is proved that the depth is the maximum impact depth of the debris flow. The practical engineering proves that the method has high resolution in shallow layer detection, high efficiency and convenience in field acquisition. The maximum detection depth range of this method is 30--40 m, which meets the requirements of high efficiency and accurate detection for regional debris flow source area, and has high practical application value.  相似文献   

12.
BP( Back Propagation) neural network and PSO( Particle Swarm Optimization) are two main heuristic optimization methods,and are usually used as nonlinear inversion methods in geophysics. The authors applied BP neural network and BP neural network optimized with PSO into the inversion of 3D density interface respectively,and a comparison was drawn to demonstrate the inversion results. To start with,a synthetic density interface model was created and we used the proceeding inversion methods to test their effectiveness. And then two methods were applied into the inversion of the depth of Moho interface. According to the results,it is clear to find that the application effect of PSO-BP is better than that of BP network. The BP network structures used in both synthetic and field data are consistent in order to obtain preferable inversion results. The applications in synthetic and field tests demonstrate that PSO-BP is a fast and effective method in the inversion of 3D density interface and the optimization effect is evident compared with BP neural network merely,and thus,this method has practical value.  相似文献   

13.
A debris flow forecast model based on a water-soil coupling mechanism that takes the debrisflow watershed as a basic forecast unit was established here for the prediction of disasters at the watershed scale.This was achieved through advances in our understanding of the formation mechanism of debris flow.To expand the applicable spatial scale of this forecasting model,a method of identifying potential debris flow watersheds was used to locate areas vulnerable to debris flow within a forecast region.Using these watersheds as forecasting units and a prediction method based on the water-soil coupling mechanism,a new forecasting method of debris flow at the regional scale was established.In order to test the prediction ability of this new forecasting method,the Sichuan province,China was selected as a study zone and the large-scale debris flow disasters attributable to heavy rainfall in this region on July 9,2013 were taken as the study case.According to debris flow disaster data on July 9,2013 which were provided by the geo-environmental monitoring station of Sichuan province,there were 252 watersheds in which debris flow events actually occurred.The current model predicted that 265 watersheds were likely to experience a debris flow event.Among these,43 towns including 204 debrisflow watersheds were successfully forecasted and 24 towns including 48 watersheds failed.The false prediction rate and failure prediction rate of thisforecast model were 23% and 19%,respectively.The results show that this method is more accurate and more applicable than traditional methods.  相似文献   

14.
四川省小流域泥石流危险性评价   总被引：1，自引：0，他引：1  
泥石流危险性评价是泥石流防灾减灾的重要内容。本文以四川省为研究区,以DEM为数据源,通过提取水流方向,计算汇流累积量,实现四川省小流域划分。基于收集的已查明泥石流流域资料,分析了泥石流孕灾环境与成灾特点,选择流域高差、流域面积为指标,建立基于能量条件的潜势泥石流流域判识模型,对划分的小流域进行判识,识别出7798个小流域具备泥石流发生所需能量条件,面积为31.1×104 km2,占四川省总面积的64.18 %。进而建立了泥石流危险性评价指标体系和可拓物元模型,开展了小流域泥石流危险性评价,划分了危险度等级,得到中度、高度、极高危险区的小流域个数分别为1946、1725和1002个,面积分别为9.1×104、7.7×104和3.4×104 km2,中度以上危险区面积共20.2×104 km2,占四川省总面积的41.67%。最后对评价结果可靠性和各等级泥石流危险区在各地市级行政区、各大流域的分布进行了分析。其结果对促进泥石流判识与危险性评价理论,区域泥石流防灾减灾与山区可持续发展等具有重要的理论和现实意义。  相似文献   

15.
Grain composition plays a vital role in impact pressure of debris flow. Current approaches treat debris flow as uniform fluid and almost ignore its granular effects. A series of flume experiments have been carried out to explore the granular influence on the impact process of debris flow by using a contact surface pressure gauge sensor(Tactilus~?, produced by Sensor Products LLC). It is found that the maximum impact pressure for debris flow of low density fluctuates drastically with a long duration time while the fluctuation for flow of high density is short in time, respectively presenting logarithmic and linear form in longitudinal attenuation. This can be ascribed to the turbulence effect in the former and grain collisions and grainfluid interaction in the latter. The horizontal distribution of the impact pressure can be considered as the equivalent distribution. For engineering purposes, the longitudinal distribution of the pressure can be generalized to a triangular distribution, from which a new impact method considering granular effects is proposed.  相似文献   

16.
The quality of debris flow susceptibility mapping varies with sampling strategies. This paper aims at comparing three sampling strategies and determining the optimal one to sample the debris flow watersheds. The three sampling strategies studied were the centroid of the scarp area(COSA), the centroid of the flowing area(COFA), and the centroid of the accumulation area(COAA) of debris flow watersheds. An inventory consisting of 150 debris flow watersheds and 12 conditioning factors were prepared for research. Firstly, the information gain ratio(IGR) method was used to analyze the predictive ability of the conditioning factors. Subsequently, 12 conditioning factors were involved in the modeling of artificial neural network(ANN), random forest(RF) and support vector machine(SVM). Then, the receiver operating characteristic curves(ROC) and the area under curves(AUC) were used to evaluate the model performance. Finally, a scoring system was used to score the quality of the debris flow susceptibility maps. Samples obtained from the accumulation area have the strongest predictive ability and can make the models achieve the best performance. The AUC values corresponding to the best model performance on the validation dataset were 0.861, 0.804 and 0.856 for SVM, ANN and RF respectively. The sampling strategy of the centroid of the scarp area is optimal with the highest quality of debris flow susceptibility maps having scores of 373470, 393241 and 362485 for SVM, ANN and RF respectively.  相似文献   

17.
A Debris-flow Simulation Model for the Evaluation of Protection Structures   总被引：3，自引：0，他引：3  
Debris flow is the flow of a solid-fluid mixture and in this investigation it is treated as the flow of a continuum in routing. A numerical model is proposed describing debris flow including erosion and deposition processes with suitable boundary con-ditions. The numerical model is applied to evaluate the effects of protection structures against debris flow caused by heavy rainfall on the Shen-Mu Stream of Nantou County located in central Taiwan. Simulation results indicated that the proposed model can offer useful pre-planning guidelines for engineers.  相似文献   

18.
We investigate experimentally the depositions of two contiguous debris flows flowing into a main river reach.The aim of the present experimental research is to analyze the geometry and the mutual interactions of debris flow deposits conveyed by these tributaries in the main channel.A set of 19 experiments has been conducted considering three values of the confluence angle,two slopes of the tributary,and three different triggering conditions（debris flows occurring simultaneously in the tributaries,or occurring first either in the upstream or in the downstream tributary）.The flow rate along the main channel was always kept constant.During each experiment the two tributaries had the same slope and confluence angle.The analysis of the data collected during the experimental tests indicates that the volume of the debris fan is mainly controlled by the slope angle,as expected,while the shape of the debris deposit is strongly influenced by the confluence angle.Moreover,in the case of multiple debris flows,the deposit shape is sensitive to the triggering conditions.Critical index for damming formation available in literature has been considered and applied to the present case,and,on the basis of the collected data,considerations about possible extension of such indexes to the case of multiple confluences are finally proposed.  相似文献   

19.
针对GPS可降水量时间序列具有非线性、非平稳性的特征，研究一种基于小波分解（WD）、遗传算法（GA）和最小二乘支持向量机（LSSVM）的GPS可降水量短临预报方法。先采用小波分解将GPS可降水量时间序列分解成便于预报的低频分量和高频分量；然后利用遗传算法优化LSSVM参数，进而对各分量建立预报模型；再将各分量预报结果进行叠加重构得到最终预报结果。选取两组数据进行实验，并将预报结果分别与LSSVM和遗传小波神经网络（GA-WNN）预报结果进行对比。结果表明，该组合模型具有良好的泛化能力，可有效解决神经网络易陷于局部极小的问题，提高了全局预报精度。  相似文献   

20.
针对单一预测模型的不足,提出EEMD分解与粒子群灰色支持向量机（particle swarm optimization grey support vector machine,PSOGSVM）相结合的基坑位移预测模型。以基坑时间序列的混沌性为基础,利用EEMD分解时间序列,采用相空间重构技术构造样本,应用PSOGSVM模型进行基坑预测,并与GM(1,1)、SVM、遗传小波神经网络进行对比。结果表明,该算法预测精度好,具有良好的稳定性,可有效地应用于基坑位移预测。  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号