基于BP神经网络的遥感影像分类研究

BP神经网络具有收敛速度快和自学习、自适应功能强的特点,能最大限度地利用样本集的先验知识,自动提取合理的模型。本文采用Landsat TM遥感图像作为数据源,以山西省定襄县为研究区,通过主成分分析方法来压缩输入数据,并结合NDVI和纹理特征来建立BP神经网络的土地利用分类模型,将分类结果与基于光谱单元信息的神经网络分类和基于纹理特征的神经网络分类结果进行定性和定量比较分析。结果表明:该方法总精度达到了80.50%,分别比基于光谱单元信息的神经网络分类和基于纹理特征的神经网络分类提高了18.89%和6.23%,能够有效地解决地物光谱混淆、分类精度不高等问题。     

CAN总线通信接口设计

提出了一种用单片机STC89C52及SJA1000总线控制器组成CAN总线智能节点的设计方案,给出了硬件电路,并详细介绍了SJA1000初始化、接收及发送数据程序的框图及程序设计.设计中程序均已通过调试,介绍的设计方法易于掌握且具有较强的灵活性和通用性,方便使用者学习和掌握.     

基于多属性数据体的三维地震相体分析技术

基于三维多属性数据体的地震相体分析技术,是继地震相剖面划相、平面划相后发展起来的一项体划相技术,它实现了纵向和横向的地震相同时划相。地震相数据体为了解岩相、沉积相、地层和储层特征的三维分布特征提供了依据。这里介绍了采用主分量分析(PCA)等聚类分析技术,进行地震相体分析的方法、流程和实际应用效果,并对体划相技术的方法特点进行了分析,地震相体分析技术能够用来刻画储层内部及地质体,例如碳酸盐沉积环境生物礁等。     

用群落调查及光谱观测数据的主成分分析方法研究草场各生物参数之间的关系

以内蒙古锡林河流域典型草原为研究对象,在群落调查和光谱观测数据的基础上,引入主成分分析方法(PCA)研究了与草场健康有关的各生物参数间关系,提出一种草场健康状况监测的新方法:(1)从包含12个反映群落各方面信息的变量中提取出3个有特定生态学意义的主成分,并进一步对其进行分析组合,得出一个能比较敏感、全面反映群落健康状况的新指标—草场健康指数(GHI);其意义在于:它不仅可以反映草场的生物量信息,而且可以反映群落的结构组成信息。(2)从6波段的植被光谱反射数据中提取出2个主成分:可见光因子和红外光因子,它们可以较好反映植被信息。(3)表征群落总量、放牧退化的主成分和GHI与植被光谱反射值有相当的相关性,由此得到GHI与可见光、红外光因子的回归模型。此模型可利用植被光谱较好地反映草场健康状况。     

气团客观分类实施方案研究

本文提出了一种基于天气气候学途径的气团客观分类实施方案。该方案通过主成份分析对多元气象变量进行空间降维后，由模糊聚类法对样本进行归类，用淮阴市常规地面观测资料对方案进行的试验表明，该方案能够将不易区分的天气系统分成鲜明天气特征的气团差别。方案本身的综合、客观和实用性显示出基于天气气候学途径的气团客观分类方案不仅在天气气候分析领域，而且在有关环境、生物、地理等研究中都具有广阔的应用前景。     

Plant functional types in Lake Nubia in relation to physicogeographic factors

The shoreline vegetation of Lake Nubia in Sudan was studied by means of morphological characteristics and functional traits of plants established-phase as published in literature reviews. The 57 species recorded in 83 sampling sites were classified according to 15 morphological traits into six Plant Functional Types (PFTs), using Two Way Indicator Species Analysis (TWINSPAN). Principal component analysis (PCA) was used to evaluate the homogeneity of these groups in terms of their traits. The resulting PFTs were related to the physicogeographical variables measured (soil texture, soil moisture, soil thickness and elevation) using canonical correspondence analysis (CCA). The ratios in occurrences of the functional types were calculated per each moisture segment, and can be used as an indicator of the shoreline dynamics.     

Improved Geological Interpretation Using Landsat TM Data in Lancang-Jinghong Area, Yunnan Province, China

Landsat TM digital spectral data of Lancang-Jinghong area (Yunnan Province) has been used for the purpose of geological interpretation. To meet this object, different image processing tech-niques including selected band color composites, principal component analysis and IHS decorrelation stretching are used to improve the discrimination of different lithologicai and structural features in the area. It was found that IHS decorrelation stretching images obtained from the transformation of false color composite 741 (in red, green and blue) provided the best results based on the original data. By combining the characteristics of images produced by different approaches and other canonically trans-formed images with available geological data and surface observations, the geological interpretation could be done with satisfactory degree of accuracy.     

利用NOAA AVHRR植被指数数据集分析黑河流域季候特征

利用 NOAA AVHRR的全球归一化植被指数（NDVI）的高时间分辨率数据集，建立了黑河流域 1992-1993和1995-1996两个年度的NDVI数据，范围在96．45°～102．8 °E，35．4°～43．5°N之间。对此数据进行主成分分析（PCA）．提取了前4个主成分分量，分析了黑河流域季候变化特征。结果表明，第一主成分展示了黑河流域NDVI值在分析时段内的综合空间分布结构、累积状况以及地域差异；第二主成分反映黑河流域的NDVI变化不但具有明显的年周期，而且表现出强烈的季节性，是冬夏分明的季节因素所导致；第三主成分主要指征了平原人工绿洲区显著的农作物生长期；第四主成分反映出山区自然植被与平原人工绿洲植被具有明显不同的生长期和物候特征，该成分可以被用于区分不同的地表覆盖类型。     

Assessment of Primary Production by Statistical Analysis of Water‐quality Data

Time series of weekly water‐quality data at Schnackenburg on the Elbe River (1985—2000) were subjected to principal component analysis (PCA). Considering the amplitudes of composite patterns of variables is a step towards a process‐oriented interpretation of waterquality data. One specific objective was to investigate the impact of improved water quality after the German reunification in 1990 on primary production and the oxygen budget. To discriminate anthropogenic signals from natural fluctuations a separation of the impact of discharge was attempted based on a linear regression approach. A dominant pattern of co‐variation in the residual data could be attributed to biological activity (primary production). The most relevant variables of this 'biomode' are oxygen saturation, pH, and orthophosphate. We conclude that multivariate statistical analysis of water‐quality data can help to estimate primary production when direct observations of algal concentrations are missing. In the years from 1998—2000 the trend of the ‘biomode’ indicates an increased load of oxygen consuming biomass caused by enhanced primary production in the middle stretches of the Elbe River which corresponds with the observation of more severe oxygen deficits in the tidal section of the river.     

西藏尼洋河水环境特征多元统计分析

自2008年11月到2009年10月按照月份监测西藏林芝地区尼洋河水环境特征.结果显示,根据Pearson相关性矩阵,可将尼洋河26项理化指标分为3大类,分别是低度相关性理化指标、中度相关性理化指标和高度相关性理化因子.析因分析显示,可将26项理化指标分为4大类,第1类为尼洋河水体常规的理化指标、第2类为尼洋河水体硬度相关指标、第3类为海拔及第4类为影响水生生物生长的水质理化指标.PCA分析发现,平水期、丰水期以及枯水期水环境特征明显不同,以上3期各自聚为一类,而尼洋河沿程方面,水环境特征则不存在差异.构建了尼洋河海拔、底层水温与相关理化因子的一元回归方程.建议加强对尼洋河水环境的监测工作,积极推进尼洋河水域生态环境的可持续发展进程.