概率神经网络与BP网络模型在遥感图像分类中的对比研究

通过分析概率神经网络(以下称PNN)的基本结构及其训练算法,建立了卫星图像分类的概率神经网络模型,并通过实例对比分析了概率神经网络与BP网络分类模型的分类效果。实验表明,PNN图像分类方法在分类精度上优于误差反向传播神经网络模型,且分类时间相当,是一种有效的图像分类方法。     

IMD法在多光谱图像分类中的应用

数学形态学着重于分析和处理图像的几何结构信息。根据这一原理，在图像分类预处理过程中，对各种地物区域的几何结构特点进行分析，构造相应的结构元素，然后对图像进行形态迭代分解法(IMD，Iterative Morphological Decompostion)变换。在变换结果中，地物区域的灰度信息进行了归一化处理，同时区域的几何结构特点和独立地物得到了有效保留。将多光谱图像的IMD变换结果进行分类实验的结果表明，该方法可以有效提高多光谱图像分类的精度和效率，具有较强的适用性。     

基于光谱空间密度分析的边缘提取

针对传统的边缘提取方法大部分不适应高光谱数据的特点，提出了基于光谱空间密度分析边缘提取的思想。在分组主分量变换提取第一主分量作为特征维的基础上，采用面向对象的二次判别边缘的方法，通过立体判决将光谱空间中低密度超椭球体集群视为真实边缘点集群。试验表明，此方法是合理可行的。     

数字地质编录中坡面展示影像图的制作研究

基于影像的数字地质编录是摄影测量和工程地质学科边缘交叉发展的技术成果之一．目前仍处于研究阶段。介绍了影像数字地质编录中坡面展示影像图的制作原理及其流程，重点阐述了畸变校正后像片坡面影像几何纠正的两种不同的处理方法。实践表明，两种处理方法的结合能够很好地满足数字地质编录中对展示影像图的生成及使用的要求。     

利用案例推理（CBR）方法对雷达图像进行土地利用分类

提出了基于案例推理 (CBR)的遥感分类的新方法。基于规则的专家系统被用来提高遥感分类的效率。但所涉及的规则可能多达上百或上千条 ,有的问题根本无法用规则来表达。CBR只是根据以往的案例进行推理 ,克服了基于规则的推理方法的不足 ,可以用来解决一些复杂的资源环境问题。利用CBR和模糊数学结合 ,并通过分层随机采样来控制案例在空间上的分布 ,以反映复杂环境所造成的光谱变化 ,由此解决遥感分类中的“同物异谱”现象。实验表明 ,所建立的案例库可以被重复多次使用 ,分类的效果比监督分类和非监督分类要好。     

The analysis of SPOT-5 characteristics on land cover Classification

<正>KnowledgeaboutlandcoverandlandusehasbecomeincreasinglyimportantastheNationplanstoovercometheproblemsofuncontrolleddevelopment,deterioratingenvironmentalquality,lossofprimeagriculturallandsetc.Landuseandlandcoverdataareneededintheanalysisofenvironmentalprocessesandproblemstoknowiflivingconditionsandstandardsaretobeimprovedormaintainedatcurrentlevels.     

In the Critical Zone: Geography at the U.S. Geological Survey

Geography is again becoming an integral part of the premier natural‐science agency of the federal government. Geographic research emphasizes the surface of the earth, a portion of the earth system that the U.S. Geological Survey (USGS) defines as the “critical zone.” Although geography was part of the USGS from the creation of the agency, in recent years geography in the agency has largely been limited to topographic mapping. Recently, the USGS and an advisory committee of the National Research Council (NRC) reviewed the role of geography at the Survey. The committee's report, along with ongoing decision‐making in the federal government, is likely to reshape geography in the USGS. The newly defined USGS has a regional structure and four disciplines: geology, hydrology, biology, and geography. The NRC report emphasizes the need for the creation of a spatial database called the National Map to replace the existing series of paper topographic maps. The report also outlines the need for geographic research in geographic information science (GIScience), nature‐society connections, and bridging of science to decision‐making. The NRC report has been briefed throughout the USGS, in the federal executive branch, and in Congress. The changing role for geography in the USGS requires change in the agency culture, revised budgetary decisions, and the establishment of a long‐term core agenda for research. Academic geographers will need to prepare a new generation of geographers for participation in the USGS and similar agencies.     

福建沿海土壤地球化学分类及基准值研究

利用多目标区域地球化学调查成果,探讨了福建沿海土壤地球化学分类的方法,提出了分类命名方案和诊断标准,将研究区土壤按SiO₂含量划分为铁铝土、硅铝土、铝硅土、硅土4个大类,其中硅铝土又分为一般硅铝土、铁质硅铝土、钾质硅铝土、硫铁质硅铝土4个亚类,铝硅土分为一般铝硅土和钾质铝硅土2个亚类;提出了在各种统计量中,中值比较客观地反映元素含量背景,适合作为基准值;给出了研究区各类土壤的分布图和52种元素及pH的基准值,分析了其成因和农业利用情况。     

数学地质在矿山研究中的应用--判别分析归类矿体属性实例

数学地质方法为宏观地质研究提供了定量的可能。判别分析对研究未知属性矿体的归属有着重要的意义。苏州西部地区通安——潭山多金属成矿带中，小茅山铜铅锌矿段，潭山铅锌银铁矿段位于成矿带的两端，属性已知。该成矿带中有一未知属性的铜铅锌银迂里矿段，用判别分析方法对其归类。研究结果表明，未知属性的迂里矿段归属潭山多金属硫化物矿床类型，即高—中温多金属硫化物矿床类型。     

A size classification for debris flows

A 10-fold classification for debris flow size is proposed based on total volume, peak discharge and area inundated by debris. Size classes can be used for regional overview studies where detailed site investigations are either unnecessary, too costly or where the highest hazard and risk creeks need to be identified for further study. They are also useful to compare the regional impact between affected areas and the effects of rainstorms, and they allow lay-people to obtain an understanding of debris flow magnitude and consequences. Finally, different size classes allow the estimation of travel times to points of interest based on empirically derived equations. It is proposed that agencies concerned with debris flows should establish a documentation of debris flow size according to this classification, which serves as a data base for hazard and risk planning.