The Norwegian Nature Index – conceptual framework and methodology

The Norwegian Nature Index (NI) is a general, integrated framework developed to synthesize and communicate the current knowledge of the state and development of biodiversity. It is designed to make the most of the available knowledge in the ecological research community, including expert judgment. The authors present the basic concepts and definitions of the NI, the associated quantitative expressions, and the practical implementation of data collection and integration of expert judgment and data on biodiversity in Norway. The NI can be implemented in data-rich and data-poor areas, it contains information on both the state of biodiversity and the state of knowledge, and it can be aggregated or disaggregated to address specific management themes, which gives the framework the potential to become an efficient management tool.     

论地图设计中的形象思维问题

形象思维与抽象思维的有机结合是地图设计专家思维的主要特征，形象思维在地图设计中具有重要的作用。本文介绍了形象思维与抽象思维的基本概念，探讨了形象思维在地图设计中的作用、地图设计的形象思维工具和地图设计中的形象思维过程。通过对形象思维与地图设计专家系统关系的初步探讨，认为对形象思维的研究有助于地图设计专家系统的研制。     

基于专家知识的地质体制图综合方法研究

传统数字地质编图的地质体处理过程中存在重复操作多、制图周期长等缺点,极大地限制了地质编图的工作效率.为提高工作效率,笔者提出以地质专家知识驱动的地质体制图综合方法,主要包括地质体合并(自动同属性合并、交互式合并)、消除微小地质体、地质体夸大、地质体圆滑等.该方法以地质专家总结的地质演化关系知识为主线,采用GI S组件、...     

基岩裂隙水寻找与开发的专家系统建立

由于地裂隙水埋藏分布规律的复杂怀，致使裂隙水的开发利用十分困难。因此，获取和利用理论水平高、实践经验丰富的基岩裂隙水专家的知识，通过计算机技术形成具有智能功效和的专家系统，就具十分重要的理论和实际意义。本文详细介绍了基岩裂隙水七开发专家系统（ＢＦＷＰ）的建立过程，包括系统的知识库建造，推理机设计，以及系统的图形功能     

A NEW APPROACH TO THE DESIGN OF A SYSTEM FOR FEATURE EXTRACTION BASED ON HUMAN-COMPUTER COLLABORATIVE TACTIC

We are involved in an embarrassing situation that the limited capa-bility of automated feature extraction in digital photogrammetric systems cannotsatisfy the increasing needs for rapid acquisition of semantic information for appli-cations.Facing this challenge,a new tactic,Human-Computer Collaborative（HCC）tactic,and a corresponding new method,Operator-Object Directed（OOD）method,are proposed for the design of a system for feature extractionfrom large scale aerial images.We hold that in almost all technical complex sys-tems,full automation will be neither technically feasible nor socially acceptable.The system should be designed to optimize through the cooperative operation withtwo agents in the system:the human and the computer.     

Machine Learning of Weather Forecasting Rules from Large Meteorological Data Bases

Discovery of useful forecasting rules from observational weather data is an outstanding interesting topic.The traditional methods of acquiring forecasting knowledge are manual analysis and investigation performed by human scientists.This paper presents the experimental results of an automatic machine learning system which derives forecasting rules from real observational data.We tested the system on the two large real data sets from the areas of centra! China and Victoria of Australia.The experimental results show that the forecasting rules discovered by the system are very competitive to human experts.The forecasting accuracy rates are 86.4% and 78% of the two data sets respectively     

金矿综合信息预测知识抽取机制

论述了金矿综合信息预测知识库建造中所使用的知识抽取机制，即从专家知识源获取知识，表示为知识库形式的过程和方法。知识抽取是一个多任务过程，不仅要分析领域知识的特点及知识库的形式，而且还要进行相应的知识抽取任务分析及方法研究。本文章给出了一种抽取方法，为知识工程师对专家知识的抽取提供了良好的结构，并使所抽取的知识更有意义。该方法对分类型知识的获取具有一定的适用性。     

Use of LIDAR‐derived images for mapping old landslides under forest

Large, deep‐seated landslides are common features in the Flemish Ardennes (Belgium). As most of these old (>100 years) landslides are located under forest in this hilly region, aerial photograph interpretation is not an appropriate landslide mapping method. This study tested the potential of LIDAR (Light Detection and Ranging) images for mapping old landslides under forest. Landslide inventory maps were created for a 125 km² area by applying the expert knowledge of seven geomorphologists to LIDAR‐derived hillshade, slope and contour line maps in a GIS environment. Each of the seven LIDAR‐based landslide inventories was compared (i) with the other six, (ii) with a detailed field survey‐based inventory, and (iii) with a comparable study in which topographic data were extracted from a topographical map. The combination of the percentage of field landslides indicated by an expert and the percentage of positional discrepancies (expressed in terms of positional mismatch) were used to evaluate the quality of the LIDAR‐based inventory maps. High‐quality LIDAR‐derived landslide inventory maps contain more than 70 per cent of the landslides mapped during the field survey, and have positional discrepancies smaller than 70 per cent when compared with the field survey‐based inventory map. Four experts and the combination map of all experts satisfied these criteria. Together the seven experts indicated all landslides mapped in the field. Importantly, LIDAR enabled the experts to find ten new landslides and to correct the boundaries of eleven (of the 77) landslides mapped during the field survey. Hence, this study showed that large‐scale LIDAR‐derived maps analysed by experienced geomorphologists can significantly improve field survey‐based inventories of landslides with a subdued morphology in hilly regions. Copyright © 2006 John Wiley & Sons, Ltd.     

滑坡灾害预测专家系统LPES

本文运用面向对象系统分析方法，逻辑与面向对象相结合的程序设计方法和知识表达，精确推理与非精推进相结合的推进机制，建立滑坡灾害预测专家系统ＬＰＥＳ。并用长江三峡地区的滑坡实例验证ＬＰＥＳ的实用性和正确性。     

神经网络专家系统在大坝变形预测中的应用

探讨了将人工神经网络专家系统用于大坝变形预测的方法，给出了系统功能结构框图，并对各模块的功能进行了分析。