Knowledge Recovery for Continental-Scale Mineral Exploration by Neural Networks

This study is concerned with understanding of the formation of ore deposits (precious and base metals) and contributes to the exploration and discovery of new occurrences using artificial neural networks. From the different digital data sets available in BRGM's GIS Andes (a comprehensive metallogenic continental-scale Geographic Information System) 25 attributes are identified as known factors or potential factors controlling the formation of gold deposits in the Andes Cordillera. Various multilayer perceptrons were applied to discriminate possible ore deposits from barren sites. Subsequently, because artificial neural networks can be used to construct a revised model for knowledge extraction, the optimal brain damage algorithm by LeCun was applied to order the 25 attributes by their relevance to the classification. The approach demonstrates how neural networks can be used efficiently in a practical problem of mineral exploration, where general domain knowledge alone is insufficient to satisfactorily model the potential controls on deposit formation using the available information in continent-scale information systems.     

变形监测网的整体与局部灵敏度标准

本文根据监测网灵敏度的定义，重点讨论了整体灵敏度与局部灵敏度的区别和应用的条件，分析了灵敏度标准与精度标准的 关系，并用算例加以试算分析，其结果可应用于监测网的质量评价和最优设计。     

Cross-border conservation in East Central Europe: The Danube-Carpathian complex and the contribution of the World Wide Fund for Nature

Cross-border cooperation in environmental matters has become much more evident since 1989 because open frontiers facilitate contact while common tasks emerge as protected areas in frontier zones lose their isolation. Pollution hazards have been discussed more openly since 1989 while further stimuli arise from the harmonisation process in the run-up to EU enlargement and the finance available from Brussels and other international donors to solve pollution problems and create international ecological networks. The paper examines the progress made in the Danube Valley and the Carpathians which together constitute the core of East Central Europe. Particular attention is paid to the role of environmental non-governmental organisations (ENGOs) – and especially the World Wide Fund for Nature (WWF) – in the progress of conservation. Along with the World Conservation Union (IUCN), WWF has demonstrated the value of floodplain wetlands and ensured that wetland restoration is an important part of the Strategic Action Plan for the Danube. And by involving local ENGOs in specific projects the role of the non-governmental sector in environment matters is enhanced. Also, with momentum growing for a pan-European ecological network ('Natura 2000'), WWF has attracted the support of international donors for a ecoregion-based conservation (ERBC) in the Carpathians where priority areas have now been identified. Ecological and diplomatic capacities are thus deployed to maximise the scope for biodiversity conservation commensurate with sustainable socio-economic development. This revised version was published online in July 2006 with corrections to the Cover Date.     

Competitive Adjustment and Advancement in Global Commodity Chains: I. Firm Strategies and Trajectories in the East Asian Apparel Industry

Globalisation discourses increasingly depart from a network‐centred view of the world, and focus on the possibilities of leveraging economic globalisation – through incorporation in international production networks and global commodity chains (GCCs)– as a strategy for less developed countries (LDCs) to industrialise and advance their position in the world economy. This article goes beyond the question of incorporation and addresses the issue of sustaining positions, upgrading to more rewarding roles, and advancing to less dependent positions within production networks and GCCs. Drawing on experiences in the East Asian apparel industry, we present a framework for analysing such processes at both the firm and industry levels. We demonstrate that the East Asian experience provides a rather positive picture, despite a decline in the region's share of world trade. The present paper is a preliminary contribution; further research, using the framework presented, would enhance insights into competitive adjustment and advancement in GCCs, specifically, the forces underlying success or failure.     

山西晋祠泉复流时间的人工神经网络预测

由于岩溶地下水的长期过量，晋祠泉自1994年出现断流至今，目前正在兴建中的万家寨引黄工程将使晋祠泉域的地下水得到一定程度的涵养，因此晋祠泉能与与何时复流已经成为许多人关心的问题。地对上述问题，本文应用一种改进的人工神经网络的方法来分析预测晋祠泉的流量变化态势，并大致给出了复流时间。     

黄土高原分形沟网研究

推测认为黄土高源沟网具有分形性。根据Hoton定律推导沟网分维计算式，确定沟网分形结构，分形理论求算得小流域沟网的分维D＝1．9接近于平面空间时的D＝2理论值。统计分析发现流域边界周长、长轴、短轴、长短轴比、汇合角等地貌指标随流域面积的变化。从而证明黄土高源流域的自相似性。     

天然气水合物研究中的几个重要问题

综述了当前关于天然气水合物研究中的几个重要问题，提出了今后的主要研究方向，全球大约有10^19g碳以天然气水合物的形式储存在沉积物中，大约是其它所有化石燃料沉积物形式储存量的2倍多，因此，天然气水合物被认为是21世纪具有商业开发无景的潜在的战略资源，天然气水合物是一种亚稳态物质，极易受到温度和压力条件的影响，海底天然气水合物的分解将会影响沉积物的物理化学性质（如剪切强度和流变性等），地球物理性质（如地震波速和电导性），以及地球化学性质（如孔隙流体成分）的明显变化，导致诸如海底滑塌等地质灾害的发生，天然气水合物的分解会产生导致“温室效应”的甲烷气体，该气体进入大气圈中会引起全球气候和环境的变化。     

人工神经网络在灌浆加固工程中的应用

提出灌浆加固工程中预测单位深度吸浆量的人工神经网络模型，详细介绍了该模型的建模过程，北结合工程实例，验证预测结果和实际数据有较好吻合性，同时表明在复杂地质条件下，灌浆加固工程中利用这一模型进行单位深度吸浆量预测是有效的。     

流域产流产沙BP网络预报模型的初步研究

运用BP神经网络模型的基本原理,以流域降水条件为基本因子,建立了流域产流产沙BP网络预报模型.该模型能用于定量分析流域人类活动因素对流域产流产沙的影响.西汉水、大通江、香溪河流域资料验证表明,模型基本合理、可靠.     

基于差分法及神经网络的硐室围岩力学参数反分析

结合现场实践,基于差分法和人工神经网络建立了新的围岩力学参数反分析方法。进行了硐室模型简化;针对不同力学参数,用FLAC差分程序进行求解,得出相应的神经网络分析样本;用人工神经网络对围岩力学参数进行了学习训练,并进行了网络结构及参数优化;利用现场实测位移值,对围岩力学参数进行了反分析,与现场实测值对比表明其满足误差精度要求,证实了反分析方法的正确性和可靠性。