基于PSR-WSVM模型的边坡位移预测

为建立高精度的边坡位移预测模型，采用相空间重构（PSR）将边坡位移时间序列数据转换为多维数据，同时构造小波核函数改进的支持向量机模型，建立PSR-WSVM模型并应用于边坡位移预测。将PSR-WSVM模型预测结果与传统支持向量机（SVM）模型、小波支持向量机（WSVM）模型和基于相空间重构的支持向量机（PSR-SVM）模型预测结果进行对比，通过平均绝对误差（MAE）、平均绝对误差百分比（MAPE）和均方根误差（RMSE）3个精度评价指标验证PSR-WSVM模型的可行性。工程实例结果表明，PSR-WSVM模型预测结果的3个精度评价指标都优于另外3种模型，边坡位移预测的精度明显提升。     

昆仑山口大地震与地形变异常的讨论

针对昆仑山口大地震，总结了多种地形变（大地测量）手段所显示的异常变化及其时空分布，结果显示：8．1级大震前存在空间尺度大，时间尺度的地形变前兆异常，简要介绍了相关的异常图像，给出了初步解释，并对未来震情的发展进行了探讨，认为近期内强震活动向华北迁移的可能性不大。     

Prediction of Stellar Atmospheric Parameters using Instance-Based Machine Learning and Genetic Algorithms

In this article we present a method for the automated prediction of stellar atmospheric parameters from spectral indices. This method uses a genetic algorithm (GA) for the selection of relevant spectral indices and prototypical stars and predicts their properties, using the k-nearest neighbors method (KNN). We have applied the method to predict the effective temperature, surface gravity, metallicity, luminosity class and spectral class of stars from spectral indices. Our experimental results show that the feature selection performed by the genetic algorithm reduces the running time of KNN up to 92%, and the predictive accuracy error up to 35%. This revised version was published online in July 2006 with corrections to the Cover Date.     

成都市冬季重污染日气象条件成因分析及预报

本文通过对成都10个重污染日进行天气学分析,将污染浓度与气象要素进行聚类、研究了重污染日形成原因及污染浓度与气象要素的关系。在此基础上,建立了SO_2、TSP日平均浓度分级预报方程。     

基于AGA的SVM需水预测模型研究

需水预测是一个由城市人口、工业水平、社会经济水平共同作用的多因素、多层次的复杂非线性系统.其结果将直接影响受区域水资源承载力约束的产业结构、布局形态等决策.作为一种集中参数预报方法,支持向量机方法具有对未来样本的较好的泛化性能,对于这类资料缺乏、系统结构尚欠清晰的问题可以取得较好的模拟和预测结果.基于此,本文将支持向量机方法引入需水预测领域,建立了需水预测支持向量机模型.同时,本文将加速遗传算法和支持向量机方法耦合起来,构造了支持向量机模型参数的自适应优化算法.模型在珠海市的应用实例表明:与简单遗传算法比较,AGA的模型参数寻优效率更高;与BP神经网络模型相比,SVM模型较好地解决了小样本、经验性等问题,并取得了较高的预测精度.     

烟威渔场盐度预报及分析

本文以我国北黄海的烟威渔场为研究对象,采用优选因子场预报模式,对盐度的时空变化进行预报试验。文中对所采用的统计预报方法,作了简要介绍。对影响本海区盐度变化的显著因子及预报结果作了初步分析。预报试验表明:预报的总体平均绝对误差为0.27‰,预报相对误差在18％左右,预报误差小于0.5‰的站数占总站数的85％,预报趋势与实测资料基本一致。     

Siltation Prediction for Navigation Channels and Harbour Basins on Muddy Beach

- This paper, after briefly reviewing the experimental research on sediment transport on muddy beach since the 1950s, improves and perfects the method for forecasting siltation in navigation channels and harbour basins which was first put forward in China by the authors. In consideration of silty sediment and sand, some factors in forecasting methods have been changed and modified. Consequently, the modified methods can be used either to compute siltation in navigation channels and harbour basins on muddy beach or to compute siltation and scouring in navigation channels and harbour basins on both silty beach and sandy beach. The verification of field data from eleven large, medium and small natural harbours shows a good agreement between the forecasting by the modified method and the natural conditions. Finally, the paper deals with the rational utilization of water area after the construction of the West Dyke in Lianyungang, the maintenance of water depth of the navigation channel at the entrance, siltation distribution, siltation in the navigation channel and harbour basin for ships of 100 thousand tonnnage. Results once again prove that the prospect of constructing Lianyungang Harbour into a deepwater harbour is bright.     

松辽盆地西部张裂缝预测的应力场方法

以松辽盆地地质资料为基础，介绍了应力场和张裂缝预测的计算方法。通过了各种岩性的张破裂概率隶属函数，预测松辽盆地酉部张裂缝区的分布。据此，为今后的油气勘探提出了几点认识和建议。     

Pressure prediction in the Bullwinkle Basin through petrophysics and flow modeling (Green Canyon 65, Gulf of Mexico)

Reservoir pressures within the Bullwinkle minibasin (Green Canyon 65, Gulf of Mexico continental slope) increase at a hydrostatic gradient whereas pressures predicted from porosity within mudstones bounding these reservoirs increase at a lithostatic gradient: they are equal at a depth 1/3 of the way down from the crest of the structure. Two- and three-dimensional steady-state flow models demonstrate that bowl-shaped structures will have lower pressures than equivalent two-dimensional structures and that if a low permeability salt layer underlies the basin, the pressure is reduced. We conclude that at Bullwinkle, pressure is reduced due to an underlying salt body and the bowl-shape of the basin. A geometric approach to predict sandstone pressure is to assume that the reservoir pressure equals the area-weighted average of the mudstone pressure. When the mudstone pressure gradient is constant, as at Bullwinkle, the reservoir pressure equals the mudstone pressure at the average depth (centroid) of the reservoir.     

Filters for linear sea-wave prediction

Deterministic sea-wave prediction (DSWP) models are appearing in the literature designed for quiescent interval prediction in marine applications dominated by large swell seas. The approach has focused upon spectral methods which are straightforward and intuitively attractive. However, such methods have the disadvantage that while the sea is aperiodic in nature, the standard discrete spectral processing techniques force an absolutely periodic structure onto the resulting sea surface prediction models. As it is the shape of the sea surface that is important in such applications, particularly near the end of the domain which is important, the standard windowing techniques used in signal processing work to reduce leakage artifacts cannot be employed. This has necessitated the use of end matching methods that can be both inconvenient and may reduce the fraction of the time for which legitimate predictions are available. As a result, an investigation has been undertaken of the use of finite impulse response prediction filters to provide the necessary dispersive phase shifting required in DSWP systems. The present work examines the theoretical basis for such filters and explores their properties together with their application to both long and short crested swell seas. It is shown that wide band forms of such filters are only convergent in the sense of distributions having both infinite duration impulse responses and asymptotically divergent first derivatives. However, appropriate band limitation can produce useful finite impulse responses allowing implementation via standard discrete convolution methods. It is demonstrated that despite the prediction filters having a non-causal impulse response such filters can be used in practice due to a combination of the asymmetric nature of the impulse response and the fundamental nature of the prediction process. The findings are confirmed against actual sea-wave data.