前馈神经网络隐性单调与泛化能力

应用前馈人工神经网络对广域单调的两组样本进行了模拟反演，引入单调前馈网络的概念对其权值和阈值定解问题和泛化能力进行了较诉研究。表明前馈人工神经网络是一个表达形式简单的复杂系统，其单调特征是隐性的，而且训练网络的成熟性对样本数量和样本内在规律性有一定依赖。强调了前馈人工神经网络的应用效果，指出单调与复合问题还需进一步深入研究。     

River flow mass exponents with fractal channel networks and rainfall

An important problem in hydrologic science is understanding how river flow is influenced by rainfall properties and drainage basin characteristics. In this paper we consider one approach, the use of mass exponents, in examining the relation of river flow to rainfall and the channel network, which provides the primary conduit for transport of water to the outlet in a large basin. Mass exponents, which characterize the power-law behavior of moments as a function of scale, are ideally suited for defining scaling behavior of processes that exhibit a high degree of variability or intermittency. The main result in this paper is an expression relating the mass exponent of flow resulting from an instantaneous burst of rainfall to the mass exponents of spatial rainfall and that of the network width function. Spatial rainfall is modeled as a random multiplicative cascade and the channel network as a recursive replacement tree; these fractal models reproduce certain types of self-similar behavior seen in actual rainfall and networks. It is shown that under these modeling assumptions the scaling behavior of flow mirrors that of rainfall if rainfall is highly variable in space, and on the other hand flow mirrors the structure of the network if rainfall is not so highly variable.     

监测网优化设计的必要性及内容

本文详细分析了监测网优化设计的必要性，并针对监测网的特点，叙述了监测网设计的有关问题。     

航空遥感影像中道路的半自动提取

为了达到各种信息融合的目的，针对不同的情况，提出了多种信息约束下的道路提取方法。为了对提出的方法进行检验，给出了航空影像中不同类型的道路提取的例子     

用人工神经网络实现地震记录中的废道自动切除

切除废道（即道编辑）的工作是地震信号处理中重要而又工作量巨大的一步.本文提出了一种用人工神经网络实现的自动切除方法,所用的神经网络模型为新奇滤波器模型,方法简单实用,切除效果令人满意.文中介绍了方法的原理并给出了几个实验结果.     

用地震折射法探测沥青路面的季节融化深度及其变化

试验结果表明,用经过数字化改造后的地震仪测出的路心融化深度,与钻孔测温确定的融化深度相比,其解释误差小于7％。路基和涵洞横剖面的探测结果能反映出融化层变化的主要趋势。不同路堤高度的路基形成的融化横剖面均呈下凹形,而涵洞下形成的融化横剖面则是涵洞中心的融化深度小于两端洞口处的融化深度。因此,地震折射法将为多年冻土地区路基的修筑和稳定性研究提供一种简捷、可靠的探测手段。     

监测网的可区分测度

监测网的设计阶段，变形体的变形特性不是完全清楚的情况下，须考虑监测网的可区分测度．本文详细讨论了监测网的可区分问题，导出了有关的公式，并以算例加以分析和说明，最后论述了监测网设计的可区分准则．     

黄土孔隙性分类判别的人工神经网络方法

运用人工神经网络的一典型模型——“反向传播”神经网络,对洛川黄土孔隙性的实测数据进行了分析,建立了洛川黄土孔隙性预测的计算机智能专家系统。结果表明,神经网络方法性能良好,可望成为黄土孔隙性分类、判别的有效辅助手段。     

Topological properties of disjoint channel networks within enclosed regions

Enclosure of some portion of one or more natural stream-drainage basins by superposition of a rectangle on a map of drainage network results in fragmentation of the natural basins into a set of disjoint channel networks. Each of these may have some channel links and forks of the natural network plus truncated links intersected by the enclosure boundary. The topological properties of the network elements in the enclosure are used to set up a model of random network patterns, in which the number of disjoint channel networks is expressed as a function of the number of links and forks in the enclosures. This function is shown to be a multiplicative constant times the square root of the number of links or forks. Empirical data on square and rectangular enclosures of several sizes from the Inez (Kentucky)Quadrangle map showed that the predicted multiplicative constants do not agree with observation, but that the square-root relation seems to hold at least to a first approximation. The models thus can be used as a norm against which deviations of real-world enclosures from network pattern randomness can be studied.     

高密度电法勘探技术及其应用

简述了高密度电法勘探技术的基本原理。从电极排列、数据预处理及反演处理方法等方面介绍了该技术在应用中应注意的关键技术问题及其处理方法,并通过在长-邵高速公路勘察的应用实例,来说明高密度电法勘探技术在岩溶洞穴、地质灾害等探测领域具有较好的探测效果。