证据推理应用于多源信息融合分析

运用证据理论合并来自不同数据源的证据,以实现各种数据所含信息融合的原理和方法。该方法的最大特点是将数据源中存在的不确定性引入数据分析过程。另外,利用证据推理,可以在数据分析过程中方便地引入专家解译图解的经验和知识。最后通过利用ＥＲＳ ＳＡＲ数据和ＴＭ影像进行融合分析,证明该方法在遥感图解自动分类中有很好的应用前景。     

遥感图像在土地利用更新中的应用研究——以里下河地区防汛信息系统(LXFPGIS)为例

以里下河地区防汛信息系统为例 ,阐述了利用 TM遥感图像进行 GIS土地利用更新的试验研究。采用了最大似然分类法和模糊分类法两种监督分类方法进行分类试验。提出了两种提高训练区采样效率的基于 GIS本底数据的采样方法 ,即半人工采样方法和全自动分类区直方图提取法。对上述方法分别做了土地利用分类试验 ,对分类结果进行了分析比较 ,并作出了相应的结论。     

基于遥感影像的城市森林分类提取及生态价值估算研究

以北京通州新城区城市森林为研究对象,提出一种基于信息论的决策树分类方法,以提取Aster遥感影像中城市森林平面量,改善传统分类方法仅利用影像光谱特征信息的不足,高分辨率影像和地面调查数据验证显示其分类精度达84.6%.结合分类影像图,引入城市森林生态价值评估模型(CITYgreen模型)估算出通州新城区森林的生态价值约为598.87万美元.研究表明,该方法适合大面积区域的城市森林分类提取及其生态价值估算.     

北半球冬季亚澳振荡与亚澳地区气候的关系

再分析资料的EOF结果揭示出,冬季亚澳季风区对流层上层位势高度场存在着南北反相变化的振荡—亚澳振荡（AAD）,并定义亚澳振荡强度指数（AADI）。通过相关和合成分析,结果表明,冬季亚澳振荡与同期北半球冬季亚澳地区天气、气候之间存在显著相关。在年际尺度和年代际尺度上,AAD与同期北半球冬季亚澳地区气温、降水的异常显著相关,在年际信号上叠加年代际信号后,该指数与亚澳地区的气温和降水的相关更为显著。冬季亚澳振荡强年对应着同期冬季鄂霍次克海高压（阿留申低压）,东亚大槽和阿拉斯加脊以及极锋急流偏强;高低纬度之间的经向环流增强,副热带急流偏南偏强。这种关系本质上反映出了亚澳季风系统不仅是海陆温差的产物,也受到对流层上层温度南北差异的强迫。     

山区遥感图像的特征选择与检索研究

针对遥感图像特征存在冗余及图像检索效率低的问题,提出一种基于贡献值的有效特征选择及其分类检索方法。对高分一号(GF-1)河北省阳原地区的村落、山脊、水体遥感图像,对比Hu矩、小波分解和灰度共生矩阵特征,发现使用Hu矩较适用于识别村落,而对山脊和水体的识别率低;引入区分山脊和水体的颜色特征,并与Hu矩构成特征空间,实现山区遥感图像分类和检索。实验结果表明,该方法能够选取出图像特征中的主要分量,具有高效、实用、方便的特点,检索查准率达到92%,查全率达到88%。     

Taxonomic Studies on a New Marine Ciliate, Apocoleps magnus gen. nov., spec. nov. （Ciliophora, Colepidae）, Isolated from Qingdao, China

The morphology and infraciliature of a new marine colepid ciliate, Apocoleps magnus gen. nov., spec. nov., are described based on living observations and silver impregnations. The new genus Apocoleps is characterized by having 8 (vs. 6 in most other related genera) armour tiers, spines at both ends of the cell, 3 adoral organelles and plates with 4 reniform uni-windows. Apocoleps magnus spec. nov. is defined by the following features: body elongated and slightly curved, about 100–120μm× 35–45 μm in vivo; an...     

Extending self-organizing maps for supervised classification of remotely sensed data

An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the input layer depends on the dimensionality of input patterns. The number of neurons in the output layer equals the number of the desired classes. The number of neurons in the Kohonen layer may be a few to several thousands, which depends on the complexity of classification problems and the classification precision. Each training sample is expressed by a pair of vectors ： an input vector and a class codebook vector. When a training sample is input into the model, Kohonen＇s competitive learning rule is applied to selecting the winning neuron from the Kohouen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector, and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector. If the number of training sam- ples is sufficiently large and the learning epochs iterate enough times, the model will be able to serve as a supervised classifier. The model has been tentatively applied to the supervised classification of multispectral remotely sensed data. The author compared the performances of the extended SOM and BPN in remotely sensed data classification. The investigation manifests that the extended SOM is feasible for supervised classification.