基于RBF神经网络的遥感影像分类算法研究

提出了运用径向基函数神经网络和K均值法进行遥感影像分类的算法，以实际的遥感影像分类为例，通过与传统的最小距离法进行比较，对RBF神经网络分类器的优点进行了归纳，并就算法实施中的一些问题进行了探讨。分析结果表明，RBF神经网络是一种有效的图像分类器。     

千兆网支持下的城市公众GIS

当前GIS技术的发展已经进入到一个新的阶段,呈现出网络化、专业化、智能化、大众化等特点。公众GIS是近年来新兴的GIS应用领域,它主要的目的是面向公众提供信息服务。介绍了城市公众GIS的基本概念、特点和系统功能,在分析了当前公众GIS存在的问题之后,继而提出一种适合宽带网络(千兆以太网)支持下的公众GIS系统结构,并进一步分析了它的功能和用途。     

苏州市轻轨精密工程控制网的建立

根据精密工程控制网的高精度要求，结合沉降地区的特点，进行GPS、精密水准作业中误差分析及精度控制分析，提出满足轻轨工程施工的控制方案。     

Digital model of corrected accumulated flow for peak discharge data acquisition and drainage system design

The design of a drainage system for a roofing slate quarry was implemented by the enhancement of discharge peak estimation, and the uncertainty inevitably associated with the engineering model was reduced.

The development of a topographical, geological, and vegetation cover database developed from a Geographical Information System (GIS) allowed for the definition of the drainage network for a hydraulic system, along with the calculation of the runoff coefficient. This is applied to the digital model of accumulated flow (DMF) as a weight correction coefficient, using a matrix-based model at 5×5 m resolution. The new digital model of corrected accumulated flow (DMCF) is the result of combining the thematic maps with the map of slope <3%, which was previously created from the slope model. It is demonstrated that this new model allows to apply the “Rational Method” on cartographic units defined by the GIS.

The DMCF is compared with other traditional applications of the Rational Method based on the calculation of the discharge peak considering: (1) the drainage basin as a single watershed or (2) defining an average runoff coefficient in each sub-watershed. Both approaches have bigger discharge peaks than those obtained by the DMCF since the slope, lithology, and vegetation cover have average values, and the runoff coefficient is poorly defined, increasing the uncertainty in the discharge peak.     

Application of visual,statistical and artificial neural network methods in the differentiation of water from the exploited aquifers in Kuwait

The ability of artificial neural network to differentiate water samples from the two aquifers of Kuwait on the basis of their major ion chemistry has been demonstrated. The major ion concentration distribution in the groundwater of the Kuwait Group and the Dammam Formation aquifers of Kuwait appears very similar. Cross-plots, supported by the discriminant function analysis of the data, however, suggest that there are some subtle differences in the overall composition of the water from the two aquifers that make it possible to differentiate the water from the two aquifers in almost 80% of the cases. An artificial neural network improved the differentiation capability to 90% of the cases. It is also possible to estimate the fraction of Kuwait Group water in the flow stream of dually completed wells with the help of an artificial neural network developed for this purpose. Electronic Publication     

小湾电站高边坡系统锚固与排水的优化设计方法

据小湾电站地下厂房进水口开挖高边坡的岩体结构与工程地质特征,采用基于结构面网络模拟的随机楔体稳定分析方法对边坡的稳定性进行了三维分析。进一步运用风险分析理论对边坡系统锚杆与预应力锚索的布置进行了优化设计,最后运用结构面网络模拟理论对排水方案进行了优化设计。     

土钉支护结构的优化设计

根据复形优化原理,提出了基于Bishop法的土钉支护结构的优化分析方法,编写了优化分析程序。工程实例计算表明,该方法是进行土钉优化设计的有效方法。     

BP神经网络模型在重庆伏旱预测中的应用研究

采用气象要素定义伏旱指数，利用小波分析等方法分析重庆地区伏旱变化特征，最后采用BP神经网络模型对伏旱进行预测试验，结果表明，重庆伏旱变化具有明显的阶段性特征，而基于BP神经网络模型的伏旱预测模型预测效果良好，可以应用于实际预测。     

论我国大地测量基础建设

概述了我国大地控制网、高程控制网和地球重力场等基础建设的基本情况、需求分析与任务建议。提出我国空间大地网应由连续运行参考站、一级网、二级网和三级网组成 ;一、二等水准网复测和高程基准再定义 ;为精化大地水准面 ,要补测重力点和加测GPS/水准点。     

控制网优化设计中的蒙特卡罗法

介绍了蒙特卡罗法的基本步骤以及伪随机数的检验方法；结合工程控制网的设计给出了一个实际算例，算例的结果表明该方法切实有效。