Multi-scale support vector algorithms for hot spot detection and modelling

The algorithmic approach to data modelling has developed rapidly these last years, in particular methods based on data mining and machine learning have been used in a growing number of applications. These methods follow a data-driven methodology, aiming at providing the best possible generalization and predictive abilities instead of concentrating on the properties of the data model. One of the most successful groups of such methods is known as Support Vector algorithms. Following the fruitful developments in applying Support Vector algorithms to spatial data, this paper introduces a new extension of the traditional support vector regression (SVR) algorithm. This extension allows for the simultaneous modelling of environmental data at several spatial scales. The joint influence of environmental processes presenting different patterns at different scales is here learned automatically from data, providing the optimum mixture of short and large-scale models. The method is adaptive to the spatial scale of the data. With this advantage, it can provide efficient means to model local anomalies that may typically arise in situations at an early phase of an environmental emergency. However, the proposed approach still requires some prior knowledge on the possible existence of such short-scale patterns. This is a possible limitation of the method for its implementation in early warning systems. The purpose of this paper is to present the multi-scale SVR model and to illustrate its use with an application to the mapping of Cs¹³⁷ activity given the measurements taken in the region of Briansk following the Chernobyl accident.     

基于支持向量机的测井资料幅度异常验收方法研究

当前的测井资料质量标准基于人工验收制定,其中包含大量的定性标准.如何依据定性标准进行测井资料质量自动验收,是目前面临的一个难题.将支持向量机方法应用于测井资料幅度异常预测,在资料中挑选可疑样本,依据已有的专家验收结论建立预测模型,对测井资料幅度异常进行预测,避免了自动验收中必须将定性标准定量化的问题,在实际应用中有较好的效果,对同类工程问题的解决有一定的借鉴意义.     

居民地方感对区域旅游发展支持度影响——以九寨沟旅游核心社区为例

基于"地方感"、"期望理论"两个基本理论,从旅游核心社区居民地方感、旅游发展期望、旅游发展获益感知、旅游发展成本感知以及旅游发展支持度五个结构变量Ⅲ发,通过引入旅游发展期望值作为中介变量,构建居民地方感对旅游发展支持度内部影响机制的理论模型.以世界遗产地几寨沟为实证研究对象,通过验证性因子分析和三阶段结构方程模型的定量分析,校验理论模型中各结构因子、结构因子与其所含维度之间影响路径及其系数,定量测度了居民的旅游发展期望在居民地方感与旅游发展正反影响感知关联中的中介效用和影响机制,及对旅游发展支持度的潜在影响模式.研究结果表明:①居民地方感对居民旅游发展正反影响感知的作用存在差异,地方感对获益感知的作用远大于成本感知.②居民从旅游发展中感知获益有助于他们对当地旅游发展持更积极态度.而成本感知则会产生消极影响.③居民旅游发展期望中介效用的存在性和有效性,居民地方感通过发展期望,强化了对旅游发展影响感知及旅游支持度作用.④发展期望在居民旅游发展正反影响感知两结构模型中的中介效用存在强弱,在感知获益子结构模型的中介作用强于感知成本子模型.     

广东海岸带可持续发展决策支持系统总体框架

在阐述了广东海岸带可持续发展决策支持系统的概念后,根据系统的应用需求,确立了系统的总体目标和功能结构,并重点研究了地理信息技术、空间元数据、空间数据仓库技术和决策支持模型与方法等关键技术,在广东海岸带复杂动态海量多源数据的获取、更新、管理、分析与决策中的重要意义和作用,力求为广东海岸带可持续发展决策支持系统的详细分析设计和开发实践提供规范化的解决方案。     

应用SVM方法进行沉积微相识别

作者针对目前沉积微相中的特征提取问题,提出了应用ＳＶＭ（支持向量机）方法进行沉积微相识别的方案。该方法不是象传统方法那样首先试图将原输入空间降维（即特征选择变换）,而是设法将输入空间升维,以求在高维空间中问题变得线性可分（或接近线性可分）。因为升维后只是改变了内积运算,并没有使算法复杂性随着维数的增加而增加,因此这种方法才是可行的。所以。利用该方法更能胜任实际情况。实际处理表明该方法在小样本情况下     

GIS支持下基于支持向量机的滑坡危险性评价

以仙游县为例,探讨了将地理信息系统技术(GIS)和支持向量机(SVM)算法应用于滑坡灾害危险性评价的基本思路和技术路线。主要内容包括SVM的基本原理和方法、滑坡灾害危险性评价指标的选取和量化、SVM模型的建立以及具体的实现过程。实践证明该方法是一种较好的滑坡灾害危险性评价方法。     

基于集合预报极端天气预测指数的浙江分类强对流预报模型

利用2016—2021年ECWMF集合预报资料、浙江自动站实况资料等,计算浙江短时强降水、雷暴大风和冰雹等强对流天气相关物理量的极端天气预报指数（EFI：Extreme Forecast Index）,分析EFI分布特征,并构建了分类强对流预报模型。结果表明：强对流天气与物理量的EFI有密切联系,发生短时强降水时,对流有效位能、整层可降水量、850 hPa与500 hPa温差和位温差的EFI较大,而垂直风切变的EFI为负值,因而较小的垂直风切变更有利于出现极端降水;发生雷暴大风和冰雹时,对流有效位能、850 hPa与500 hPa温差和位温差以及850 hPa温度露点差的EFI较大,700 hPa露点温度的EFI为负值,与上层干冷下层暖湿的有利层结条件有关。利用支持向量机多分类方法,将强对流天气相关物理量的EFI作为特征值开展训练,构建的预报模型对于非局地强对流天气有较好的预报效果,其中短时强降水的误判率明显低于雷暴大风。     

Change of Support for Estimating Local Block Grade Distributions

An important aspect in mineral resource evaluation is the reduction of variance when post-processing the grade distributions defined on the support (volume) of the available data into distributions defined on the support of the proposed selective mining units. Although the volume-variance relationship is well understood for the estimation of global grade distributions, it is still an unsolved issue for local estimation studies based on non-parametric geostatistical methods, such as indicator kriging, for which the support correction is not inherent to the method. To clarify this relationship, the local change of support problem is examined in the scope of two parametric models (multi-Gaussian and discrete Gaussian models). It is shown that the variance reduction factor between point and block-support local distributions depends on the block being considered and is less than the global variance reduction factor. As a consequence, post-processing the local point-support grade distributions on the basis of the latter systematically understates the importance of the change of support at the local scale and makes selective mining appear more economically attractive than it really is. In the light of these results, a methodology is proposed to post-process the local point-support distributions obtained via non-parametric (indicator) methods into block-support distributions. An application to simulated data indicates that this methodology provides an accurate estimation at the block support when dealing with diffusion-type random fields.     

双流机场低能见度天气预报方法研究

在信息量较大, 而预报对象与预报因子的关系又不清楚的状况下, 智能机器学习方法是解决这类问题的较好手段。利用1997—2001年成都站的常规探空资料和双流机场的地面观测资料, 使用支持向量机 (Support Vector Machines, 简称SVM) 方法, 选取多种核函数进行双流机场低能见度天气的预报建模试验。测试结果表明:以径向基函数和拉普拉斯函数构造的SVM预报模型实验效果最好, Ts评分分别为0.287和0.292, 远高于双流机场低能见度天气出现的频率 (0.155)。试验结果还表明:以径向基函数构造的SVM预报模型空报较多, 漏报较少; 而以拉普拉斯函数构造的SVM预报模型空报较少, 漏报较多。因此, 如果强调模型对低能见度天气预报的准确性, 则应采用以拉普拉斯函数构造的预报模型, 如果强调对低能见度天气的预防性, 则应采用以径向基函数构造的预报模型。