滑坡灾害空间预测支持向量机模型及其应用

随着GIS技术在滑坡灾害空间预测研究中的广泛应用,滑坡灾害空间预测模型成为研究的热点问题。在总结滑坡灾害空间预测研究现状的基础上,简要介绍了两类和单类支持向量机的基本原理。以香港自然滑坡空间预测为例,采用两类和单类支持向量机进行滑坡灾害空间预测,并与Logistic回归模型进行了比较。结果表明,两类支持向量机模型优于Logistic回归模型,而Logistic回归模型优于单类支持向量机模型。     

Comparing the Kalman filter with a Monte Carlo-based artificial neural network in the INS/GPS vector gravimetric system

Rigorous physical and mathematical analysis has been intensively developed to obtain the gravity disturbance vector from the inertial navigation system and the global positioning system. However, the combination of the observation noise and the systematic INS errors make it very challenging to accurately and efficiently describe the dynamics of the system with rigorous equations. Thus, the accuracy of the gravity disturbance estimates, especially in the horizontal components, is limited by the insufficient error models. To overcome the difficulty of directly modeling the systematic errors with exact mathematical equations, a Monte Carlo based artificial neural network is successfully applied in the moving base gravimetric system. The computation results show significant improvement in the precision of all components of the gravity disturbance estimates.     

用向量法求矿脉产状

对板状似板状的矿脉,依据控制顶板（或底板）三个点的坐标,求出其所在平面的方程,该平面与水平的交线和Ｘ轴夹角即矿脉走向,平面与水平的夹角即为矿脉倾角,文末给出实例及计算程序。     

支持向量机方法在郑州冬季气温趋势预测中试应用

将气候预测中常用的74项环流特征量进行归一化处理后,与郑州市冬季气温进行相关普查,利用SVM(SupportVectorM ach ine)两类分类方法,同时考虑气温的年代际变化,建立郑州冬季温度距平趋势预测推理模型,并对因子个数多少和年代际变化对预测模型的影响进行了试验。试验结果表明:用25个和15个因子分别建模时,产生最优模型时样本平均Ts评分均为56%,但后者预报准确率为75%,较前者提高了10%。用20世纪50年代和60年代做试验集,效果较好,产生最优模型时的样本Ts评分和预报准确率较高;用90年代做试验集,效果较差。     

考虑地应力的洞室围岩块体稳定性分析的理论与实践

地下洞室围岩的稳定性状态，在很大程度上受围岩应力状态决定，以前的地下洞室岩稳定性分析，一般仅考虑在自重作用下的稳定性状态。而吻略了地应力地围地应力对围岩稳定性的影响，所得结论往往偏于保守。     

支持向量机模型在火山岩储层预测中的应用——以徐家围子断陷徐东斜坡带为例

火山岩储层的发育程度是控制徐家围子断陷火山岩气藏的重要因素,但火山岩储层以岩性复杂、横向变化快、井间可对比性差为特点,火岩储层的准确识别、厚度的精确描述是火山岩气藏勘探开发的难题.针对这一难题,作者提出在专家优化地震属性组合的基础上确定支持向量机模型,进而预测火山岩储层厚度.该技术在实际应用中取得了良好效果,预测的火山...     

基于支持向量机模式识别的大雾预报方法

选取1971～2000年11～12月大雾发生前近地面层的气象要素(气温、降水、能见度、风向风速、相对湿度、云量等9个预报因子),将支持向量机(SVM)方法应用于大雾预报.采用支持向量机方法,应用径向基函数,建立了陕西公路站点大雾24 h预报模型,并进行了大雾预报的模拟、训练,其寻优标准TS评分达到了理想的效果.     

基于数据矢量特性的MODIS数据几何校正

MODIS探测器的大扫描角多探元并扫方式是造成扫描图像严重畸变的主要根源,应用基于SWATH的卫星遥感数据处理策略,分析MODIS 1B各分辨率数据空间位置关系及图像数据与经纬度数据的对应情况,结合探测器扫描方式、卫星升降轨和地球曲率等各方面因素按像元地理位置合成图像,抛弃数据光栅特性采取矢量特性实现对像元几何精定位。结果表明：应用该种方法处理的MODIS数据几何校正精度高,方便进行亚像元级精确几何校正,而且可以避免2次或多次像素重定位导致信息丢失,不会出现“BowTie”现象。     

Landslide susceptibility assessment using SVM machine learning algorithm

This paper introduces the current machine learning approach to solving spatial modeling problems in the domain of landslide susceptibility assessment. The latter is introduced as a classification problem, having multiple (geological, morphological, environmental etc.) attributes and one referent landslide inventory map from which to devise the classification rules. Three different machine learning algorithms were compared: Support Vector Machines, Decision Trees and Logistic Regression. A specific area of the Fruška Gora Mountain (Serbia) was selected to perform the entire modeling procedure, from attribute and referent data preparation/processing, through the classifiers' implementation to the evaluation, carried out in terms of the model's performance and agreement with the referent data. The experiments showed that Support Vector Machines outperformed the other proposed methods, and hence this algorithm was selected as the model of choice to be compared with a common knowledge-driven method – the Analytical Hierarchy Process – to create a landslide susceptibility map of the relevant area. The SVM classifier outperformed the AHP approach in all evaluation metrics (κ index, area under ROC curve and false positive rate in stable ground class).