基于影像交叉学习的CBERS CCD波段模拟

与TM/ETM+相比,CBERS CCD缺少2个红外波段(波段5和波段7),这便导致了许多针对TM/ETM+数据的图像处理方法难以直接应用于CBERS CCD图像.为此,采用基于影像交叉学习的波段模拟方法,即以ETM+数据作为先验知识,通过支持向量回归( Support Vector Regression,SVR),拟...     

Policy incentives for carbon capture and storage technologies in Europe: A qualitative multi-criteria analysis

In this paper, we compare different policy incentives for overcoming investment uncertainties that are typical for low-carbon technologies prior to their commercialisation, some of which may be attributable to market failures. The paper focuses on the particular case of carbon capture and storage (CCS) technologies and conducts a qualitative multi-criteria analysis of different public policy support schemes for CCS demonstration to evaluate their suitability. The assessed schemes include mandatory CCS, emission performance standards and several different financial incentives (in addition to the European Union Emission Trading Scheme). Based on the available literature and on experience in the UK and Germany with promotion instruments for low-carbon technologies, the results of our analysis suggest that two alternative schemes, a CCS bonus incentive or a carbon dioxide (CO₂) price guarantee, perform best in comparison with the other assessed instruments. While they reduce the uncertainty of CCS investments in the face of low European Union Allowance prices, they also avoid significant adverse impacts on operational and investment decisions in electricity markets.     

基于支持向量机的CloudSat卫星云分类算法

从基于云角色的分类思想出发,利用星载毫米波雷达探测资料提取云的特征参数,建立支持向量机（support vector machine,SVM）模型实现云的分类。通过与BP（back propagation）网络模型的分类结果进行对比,发现两种模型都具有较好的分类能力,但SVM模型的识别准确率更高,计算速度更快。基于CloudSat资料的云分类实例表明,SVM模型的分类结果与CloudSat数据处理中心（Data Processing Center,DPC）发布产品具有很好的一致性。     

Ricker子波核最小二乘支持向量回归滤波方法的稳健性研究

除了信噪比、有效子波畸变等,稳健性(Robustness)也是度量滤波方法效果的一个重要的物理量,它刻画了滤波系统应对异常点值的能力.一般用影响函数作为评价稳健性的工具.支持向量机方法已较成功地应用于信号与图像的滤波中,尤其Ricker子波核方法更适于地震勘探信号处理.通过考察Ricker子波核最小二乘支持向量回归(L...     

支持向量机与微电阻率成像测井识别火山岩岩性

针对火山岩储层,从岩石化学成分分类和岩石结构分类两个角度出发,提出了一种利用测井资料识别火山岩岩性的方法。基于取芯薄片鉴定资料获得对应井段的常规测井数据,利用统计学习理论中的支持向量机方法对其处理,得到地质上按岩石化学成分分类的火山岩岩性类别。建立地层微电阻率成像测井图像与不同结构火山岩岩性之间的对应关系,归纳出典型的微电阻率图像模式,从而得到地质上按岩石结构分类的火山岩岩性类别,结合上述两者结论确定最终岩性,实现了运用支持向量机算法处理常规测井资料与微电阻率图像模式相结合的火山岩岩性测井识别新方法。     

基于SVM的含约束地球化学单元素异常圈定方法及应用

地球化学元素异常的空间分布受限于地质背景、矿产空间分布和景观特征等因素,单元素异常图的绘制不应仅依据采样数据由计算机追踪等值线图的方法自动勾绘。传统的手工圈定方法效率低、受人为因素影响大。基于SVM(Support Vector Machine,支持向量机)提出了一种可以考虑地质约束的单元素异常圈定方法,并加入地质单元分区、地质构造等约束条件。该方法可以高效绘制出单元素异常图,并成功应用于2个实例中。     

无单元Galerkin法大地电磁三维正演模拟

无单元Galerkin法(EFGM)作为一种相对成熟的无网格方法,避免了网格剖分,其精度高,适用于复杂电导率分布和复杂边界形状的计算。本文将EFGM用于大地电磁三维正演,详述了三维EFGM形函数的构造过程,从大地电磁三维变分问题出发,利用Galerkin法结合高斯积分公式推导了相应的系统矩阵离散表达式,简述了边界条件的加载技术,研究了支持域尺寸对EFGM三维正演计算精度的影响,最后通过数值计算验证了EFGM三维算法的正确性。     

基于SVM的资源三号测绘卫星影像分类

以江苏省宜兴市为研究区,利用支持向量机(SVM)方法对资源三号测绘卫星影像进行了分类,其总分类精度为97.76%,Kappa精度为0.968 7。为了评价算法的适用性,同时应用最大似然法与最小距离法对同一影像进行分类测试,支持向量机分类法精度高于其他2种方法,可以满足土地覆盖分类调查需求。     

Prediction of ultimate axial load-carrying capacity of piles using a support vector machine based on CPT data

The support vector machine (SVM) is a relatively new artificial intelligence technique which is increasingly being applied to geotechnical problems and is yielding encouraging results. In this paper SVM models are developed for predicting the ultimate axial load-carrying capacity of piles based on cone penetration test (CPT) data. A data set of 108 samples is used to develop the SVM models. These data were obtained from the literature containing pile load tests and each sample contains information regarding pile geometry, full-scale static pile load tests and CPT results. Moreover, a sensitivity analysis is carried out to examine the relative significance of each input variable with respect to ultimate strength prediction. Finally, a statistical analysis is conducted to make comparisons between predictions obtained from the SVM models and three traditional CPT-based methods for determining pile capacity. The comparison confirms that the SVM models developed in this paper outperform the traditional methods.