Assessing model of highway slope stability based on optimized SVM     

《China Geology》2020,3(2):339-344

Considering the geological hazards attributed to the highway slope, using a common simple model cannot accurately assess the stability of the slope. First, principal component analysis (PCA) was conducted to extract the principal components of six factors (namely, bulk density, cohesion, internal friction angle, slope angle, slope height, and pore water pressure ratio) affecting the slope stability. Second, four principal components were adopted as input variables of the support vector machine (SVM) model optimized by genetic algorithm (GA). The output variable was slope stability. Lastly, the assessing model of highway slope stability based on PCA-GA-SVM is established. The maximal absolute error of the model is 0.0921 and the maximal relative error is 9.21% by comparing the assessment value and the practical value of the test sample. The above studies are conducive to enrich the assessing model of highway slope stability and provide some reference for highway slope engineering treatment.  相似文献   

红外卫星云图和相关向量机的有眼热带气旋客观定强模型   总被引：1，自引：1，他引：0  

戴李杰  张长江  薛利成  马雷鸣  鲁小琴 《遥感学报》2018,22(4):581-590

热带气旋TC(Tropical Cyclone)是全球影响最严重的自然灾害之一。TC强度和路径的准确预报,对于减轻其带来的灾害影响至关重要。本文基于静止红外卫星云图和相关向量机RVM(Relevance Vector Machine)构建有眼TC客观定强模型。首先,利用高斯平滑对红外卫星云图进行去噪;然后,利用基于测地活动轮廓GAC(Geodesic Active Contour)模型的偏微分方程PDE(Partial Differential Equation)法对有眼TC的眼壁进行分割,提取眼壁的亮温梯度信息,计算眼壁亮温梯度的最大值及梯度数据不同概率时的均值,从而构造与TC强度密切相关的特征因子;最后,利用RVM构建单特征因子、多特征因子与近地面最大中心风速的客观定强模型,研究不同特征维度对TC客观定强误差的影响。实验结果表明,在单特征因子的模型定强中,95%概率眼壁亮温梯度均值的定强误差最小,相比利用单特征因子所构建的定强模型,多特征因子的模型定强误差更小,即多特征因子中包含更多与TC强度相关的特征信息。在多特征因子的模型定强中,二特征因子优于三特征因子模型,说明应当合理选择特征因子维数,并非越多越好。本文所用RVM模型具有良好的高维非线性处理能力,能对TC强度进行有效估计。  相似文献   

Quantifying land use/land cover spatio-temporal landscape pattern dynamics from Hyperion using SVMs classifier and FRAGSTATS®     

Salim Lamine  Sudhir Kumar Singh  Szilárd Szabó  Nour El Islam Bachari  Prashant K. Srivastava 《国际地球制图》2018,33(8):862-878

This study aims to quantify the landscape spatio-temporal dynamics including Land Use/Land Cover (LULC) changes occurred in a typical Mediterranean ecosystem of high ecological and cultural significance in central Greece covering a period of 9 years (2001–2009). Herein, we examined the synergistic operation among Hyperion hyperspectral satellite imagery with Support Vector Machines, the FRAGSTATS^® landscape spatial analysis programme and Principal Component Analysis (PCA) for this purpose. The change analysis showed that notable changes reported in the experimental region during the studied period, particularly for certain LULC classes. The analysis of accuracy indices suggested that all the three classification techniques are performing satisfactorily with overall accuracy of 86.62, 91.67 and 89.26% in years 2001, 2004 and 2009, respectively. Results evidenced the requirement for taking measures to conserve this forest-dominated natural ecosystem from human-induced pressures and/or natural hazards occurred in the area. To our knowledge, this is the first study of its kind, demonstrating the Hyperion capability in quantifying LULC changes with landscape metrics using FRAGSTATS^® programme and PCA for understanding the land surface fragmentation characteristics and their changes. The suggested approach is robust and flexible enough to be expanded further to other regions. Findings of this research can be of special importance in the context of the launch of spaceborne hyperspectral sensors that are already planned to be placed in orbit as the NASA’s HyspIRI sensor and EnMAP.  相似文献   

A Nonlinear Representation of Model Uncertainty in a Convective-Scale Ensemble Prediction System     

Zhizhen XU  Jing CHEN  Mu MU  Guokun DAI  Yanan MA 《大气科学进展》2022,39(9):1432-1450

How to accurately address model uncertainties with consideration of the rapid nonlinear error growth characteristics in a convection-allowing system is a crucial issue for performing convection-scale ensemble forecasts. In this study, a new nonlinear model perturbation technique for convective-scale ensemble forecasts is developed to consider a nonlinear representation of model errors in the Global and Regional Assimilation and Prediction Enhanced System (GRAPES) Convection-Allowing Ensemble Prediction System (CAEPS). The nonlinear forcing singular vector (NFSV) approach, that is, conditional nonlinear optimal perturbation-forcing (CNOP-F), is applied in this study, to construct a nonlinear model perturbation method for GRAPES-CAEPS. Three experiments are performed: One of them is the CTL experiment, without adding any model perturbation; the other two are NFSV-perturbed experiments, which are perturbed by NFSV with two different groups of constraint radii to test the sensitivity of the perturbation magnitude constraint. Verification results show that the NFSV-perturbed experiments achieve an overall improvement and produce more skillful forecasts compared to the CTL experiment, which indicates that the nonlinear NFSV-perturbed method can be used as an effective model perturbation method for convection-scale ensemble forecasts. Additionally, the NFSV-L experiment with large perturbation constraints generally performs better than the NFSV-S experiment with small perturbation constraints in the verification for upper-air and surface weather variables. But for precipitation verification, the NFSV-S experiment performs better in forecasts for light precipitation, and the NFSV-L experiment performs better in forecasts for heavier precipitation, indicating that for different precipitation events, the perturbation magnitude constraint must be carefully selected. All the findings above lay a foundation for the design of nonlinear model perturbation methods for future CAEPSs.  相似文献   

几种梯度场计算的数值算法及其地学应用          下载免费PDF全文

杨莉  张宝一 《地质找矿论丛》2018,33(2):306-311

梯度作为标量场在空间上最重要的微观变化特征,能较好地反映其在空间上的变化趋势。本文介绍了中心差分算子、相邻梯度因子和Sobel梯度算子三种梯度数值算法。以点电荷在三维空间中产生的电势场构造了一标量场,通过理论公式求解了其梯度值,并将理论梯度值与三种数值算法的结果进行了对比与统计分析,验证了三种梯度数值算法的有效性和适用性。结果表明,排除场源的影响后,Sobel梯度算子相较其它两种数值算法更逼近于理论梯度值。最后,利用Sobel梯度算子求取了某铜矿区可控源音频大地电磁法(CSAMT)三维视电阻率场的梯度场,用梯度场刻画了视电阻率在空间上的变化趋势,提高了对三维地下空间的电性分布规律和地质情况的认识。  相似文献   

基于MapGIS和MapInfo的矢量化方法--以土地整理制图为例   总被引：1，自引：0，他引：1  

许婧婧 《测绘工程》2006,15(1):62-63

以土地整理制图为例,介绍了以AutoCAD为中转工具的基于MapGIS和MapInfo的矢量化方法。  相似文献   

分数阶傅里叶变换联合支持向量机的建筑物变形预测     

古巍  李倩  陈代果 《大地测量与地球动力学》2022,42(12):1239-1245

提出一种分数阶傅里叶变换(fractional Fourier transformation, FrFT)与支持向量机(support vector machine, SVM)相结合的建筑物变形组合预测模型。首先利用FrFT对变形时间序列进行多尺度分析,将复杂时间序列分解为一系列结构较为简单的子序列;然后利用SVM对每个子序列分别建立预测模型,通过将各个子序列的预测结果进行综合叠加,得到最终预测结果;同时考虑到SVM模型参数选择的难题,提出一种改进果蝇优化算法(improved fruit fly optimization algorithm, IFOA)对其进行全局寻优,提升预测性能。以西南地区某混凝土坝变形实测数据为例开展验证实验,结果表明,本文组合预测模型能够充分挖掘数据中隐含的趋势性和规律性信息,获得较高的预测精度。  相似文献   

东北亚地区M_S6.0以上地震异常电磁波动研究     

杨牧萍  钱庚  张学民  申旭辉  张萌  金艳铭 《大地测量与地球动力学》2022,42(7):669-674

利用2005-01~2009-12 DEMETER电磁卫星详查模式下磁场与电场的极低频（ELF）三分量波形数据,选取东北亚地区（38°~58°N,105°~145°E）6个M_S≥6地震,对震前30 d震中上空±10°的6 000余条1130和1135轨道数据进行波矢分析和坡印廷矢量分析。结果发现,2005-08-16日本本洲东岸近海M_S7.2地震和2009-06-05日本北海道地区M_S6.6地震震前在质子回旋频率以下记录到来源于地球的异常电磁波扰动;2005-11-10俄罗斯西伯利亚东南部M_S6.4地震和2007-08-02俄罗斯萨哈林岛(库页岛)M_S6.8地震震前在质子回旋频率以下没有记录到异常电磁波扰动;2007-02-17日本北海道地区M_S6.2地震和2008-06-13日本本州东岸近海M_S7.3地震震前在质子回旋频率以下记录到异常电磁波扰动,但并非来源于地球。  相似文献   

基于拓扑构建的多边形区域间运算的新方法     

陈波  薛本新  钱海忠  邓红艳 《测绘科学技术学报》2006,23(6):444-447

提出了一种新的直观的方法进行多边形区域之间的运算.首先将需要计算的多边形区域的边进行自动拓扑构建,利用多边形区域的边将平面划分为n个小多边形区域;然后生成这些多边形区域的内点,通过判断小多边形区域的内点是否在原始多边形区域内来确定小多边形区域是否选取;最后合并选取的小多边形即为所求.试验结果表明,该方法思路清晰、鲁棒性强,在GIS中得到了有效的运用.  相似文献   

甘肃白银厂铜多金属矿田重磁异常及构造特征北大核心CSCD     

郭小刚 《地质与勘探》2022,58(5):1057-1069

甘肃白银厂铜多金属硫化物矿田是受陆缘弧环境火山机构及其同生断裂控制的典型火山岩赋矿块状硫化物矿床(VHMS)。为了进一步探讨该矿床重磁场特征及与构造和矿床的关系,通过对区内的重磁场异常数据进行位场分离、小波分析和基于张量数据的三维欧拉反褶积自动确定地质体位置和埋藏深度的定量反演计算。结果表明,研究区布格重力场具有西部高、东部低的特征,其磁场可划分为4个磁场区;局部异常按一定分布规律呈圆形或似圆形正负相间分布,不同尺度的重磁细节异常图在一定程度上反映出引起重磁异常的地质异常体具有一定的延深且分布稳定,而且这些地质异常体具有向深部复合的趋势。经位场分离后正负相间的剩余重磁异常分布范围和分布特征大致反映了白银厂奥陶纪中酸性火山岩建造构造为一个继承性的火山穹窿构造,东、西部不同的重磁异常特征说明东西部的火山喷发具有不同的基底、源区和喷发方式。发育NW向、NE向、近NS向、NEE向等4组断裂构造,近NS向断裂F3、F4、F5、F6、F7形成时间稍晚于NEE向断裂,其与NEE向断裂F1、F2共同形成了研究区棋盘网格状的构造分布特征,这两组断裂为研究区内主要的控岩、控矿断裂。火山机构的分布明显受断裂构造控制,火山口集中分布在深大断裂、大断裂或两组断裂的交汇处。矿田内各矿床及成矿有利地段均处于研究区中部低缓重磁异常场内正负磁异常变化的梯度带内。本次研究为控矿要素研究和开展找矿预测工作提供了丰富、翔实的地球物理资料。  相似文献