On potentially negative space time covariances obtained as sum of products of marginal ones

Most of the literature on spatio-temporal covariance models proposes structures that are positive in the whole domain. However, problems of physical, biological or medical nature need covariance models allowing for negative values or oscillations from positive to negative values. In this paper, we propose an easy-to-implement and interpretable class of models that admits this type of covariances. We show particular analytical examples that may be of interest in the biometrical context. Work partially funded by grants GV04A724 (Generalitat Valenciana) and MTM2004-06231 (Spanish Ministry of Science and Education).     

Radon concentration values in the field: Correlation with underlying geology

In epidemiological and ecological studies of radon as a health hazard in a given area or region, it is becoming widely recognized that it is necessary to establish the significance of correlations, if any, between the incidence of diseases (e.g. lung cancer or leukaemias) and local radon concentration values. Measurements of soil-radon concentration levels in the field, especially under geostatistically controlled conditions, have underscored the highly erratic nature of radon emission on a scale often of only a few metres. It would appear that, while underlying geology does determine the longer scale of variation in soil-radon, many localized parameters, e.g. fissures, moisture content, thickness of overburden, etc., make it imperative that detailed in-situ measurements of radon emission are made before a reliable correlation can be established between, say, leukaemia clusters and radon concentration levels. A broad survey of measurement methods and reported results, examined in the above context, is presented and conclusions drawn in this paper.     

A Loss function approach to identifying environmental exceedances

A frequent problem in environmental science is the prediction of extrema and exceedances. It is well known that Bayesian and empirical-Bayesian predictors based on integrated squared error loss (ISEL) tend to overshrink predictions of extrema toward the mean. In this paper, we consider a geostatistical extension of the weighted rank squared error loss function (WRSEL) of Wright et al. (2003), which we call the integrated weighted quantile squared error loss (IWQSEL), as the basis for prediction of exceedances and their spatial location. The loss function is based on an ordering of the underlying spatial process using a spatially averaged cumulative distribution function. We illustrate this methodology with a Bayesian analysis of surface-nitrogen concentrations in the Chesapeake Bay and compare the new IWQSEL predictor with a standard ISEL predictor. We also give a comparison to predicted extrema obtained from a “plug-in” goestatistical analysis. AMS 2000 Subject Classification Primary—62M30; Secondary—62H11     

The Torgegram for Fluvial Variography: Characterizing Spatial Dependence on Stream Networks

We introduce a graphical diagnostic called the Torgegram for characterizing spatial dependence among observations of a variable on a stream network. The Torgegram consists of four component empirical semivariograms, each one corresponding to a particular combination of flow-connectedness within the network and model type (tail-up/tail-down). We show how an overall strategy for fluvial variography can be based on a careful examination of the Torgegram. An analysis of water temperature data from a stream network within the Columbia River basin of the northwest United States illustrates the diagnostic value of the Torgegram as well as its limitations. Additional uses and extensions of the Torgegram are discussed.     

Effective versus Total Porosity Based Geostatistical Models: Implications for Upscaling and Flow Simulation

This paper discusses issues related to the choice of total or effective porosity as the porosity basis for geostatistical model construction. Distributions of variables are different depending on the porosity basis. The distribution of variables has a strong effect on the performance of collo-cated simulation techniques. This paper presents the two porosity approaches and demonstrates some of the issues that may arise. In the examples shown here, total porosity appears to generate better behaved porosity-permeability co-distributions. Regardless of the porosity basis, upscaling methods are shown to potentially move hydrocarbon from low quality rock into more accessible coarser cells which means that any application of cutoffs is more meaningfully applied prior to upscaling if this movement is considered unrealistic for large-scale flow simulation.     

基于野外Vis-NIR光谱的土壤有机质预测与制图

利用野外实时快速获取的土壤光谱进行土壤有机质(SOM)预测与制图是精确农业与土壤遥感制图的必然需要,利用ASD FieldSpec Pro FR野外型光谱仪实时快速获取的光谱数据,去除噪声较大的边缘波段后,进行倒数的对数转换(Log(1/R))为吸收光谱。在分析吸收光谱和光谱指数与SOM关系的基础上,采用偏最小二乘回归法进行SOM的建模预测并借助地统计学方法进行SOM空间变异制图研究。结果表明,建模效果好的指标分别为特征波段(R2=0.91,RPD=3.28),归一化光谱指数(R2=0.90,RPD=3.08),特征波段与3个光谱指数组合(R2=0.87,RPD=2.67),全波段(R2=0.95,RPD=4.36)。光谱指标的克里格制图与实测SOM制图表现出相同的空间变异趋势,不同的指标均达到了较好的预测效果。     

A geostatistical approach for dynamic life tables: The effect of mortality on remaining lifetime and annuities

Dynamic life tables arise as an alternative to the standard (static) life table, with the aim of incorporating the evolution of mortality over time. The parametric model introduced by Lee and Carter in 1992 for projected mortality rates in the US is one of the most outstanding and has been used a great deal since then. Different versions of the model have been developed but all of them, together with other parametric models, consider the observed mortality rates as independent observations. This is a difficult hypothesis to justify when looking at the graph of the residuals obtained with any of these methods.Methods of adjustment and prediction based on geostatistical techniques which exploit the dependence structure existing among the residuals are an alternative to classical methods. Dynamic life tables can be considered as two-way tables on a grid equally spaced in either the vertical (age) or horizontal (year) direction, and the data can be decomposed into a deterministic large-scale variation (trend) plus a stochastic small-scale variation (residuals).Our contribution consists of applying geostatistical techniques for estimating the dependence structure of the mortality data and for prediction purposes, also including the influence of the year of birth (cohort). We compare the performance of this new approach with different versions of the Lee-Carter model. Additionally, we obtain bootstrap confidence intervals for predicted q_xt resulting from applying both methodologies, and we study their influence on the predictions of e_65t and a_65t.     

Co-kriging for stochastic flow models

Co-kriging equations for log-transmissivity and heads are derived for a two-dimensional stochastic model. The behavior of the weights as a function of the unknown value of mean hydraulic gradient J are discussed and the procedure is illustrated by studying the screening effects of adjacent measurements and added head measurements. In addition, the bias of the estimator for head values is studied when J is also estimated.     

基于地统计学与支持向量回归的QSAR建模

基于主成分分析(PCA)、地统计学(GS)和支持向量回归(SVR), 提出了一种新的定量构效关系(QSAR)个体化预测方法——Weight-PCA-GS-SVR. 其基本思路是: 先以PCA降维并消除自变量间的信息冗余, 继以SVR经非线性主成分筛选去除与因变量无关的主成分, 再以保留主成分计算样本间的加权距离, 然后以高维GS确定公用变程; 每一个待测样本都以自身为中心从训练集中找出加权距离小于公用变程的私有k个近邻, 以SVR训练建模完成个体化预测. Weight-PCA-GS-SVR从行、列两个方向对模型进行了优化, 为自变量提供了一种新的加权方法, 为解决最优k近邻选择难题提供了新的思路, 并具有SVR原来的优点. 经3个化合物活性实例数据集验证, 新方法在所有参比模型中预测精度最高, 且明显优于文献报道结果, Weight-PCA-GS-SVR在QSAR等回归预测领域有较广泛的应用前景.