基于GF-1号影像的南方水稻种植信息提取

针对南方复杂地区水稻遥感信息提取研究中机器自动学习分类研究较少、分类精度不高的问题,以福建省三明市建宁县溪口镇为研究区,基于GF-1号卫星影像,采用面向对象的随机森林遥感分类算法对研究区内水稻田信息进行提取。首先通过优化面向对象分割参数和随机森林分类模型参数,提取并调用了影像中的多种特征;再对光谱特征、植被指数特征、纹理特征、几何特征进行特征空间优选;最后通过设置4种特征优选试验进行对比,得到最优分类模型。实验结果显示,基于特征空间优选的面向对象随机森林分类算法的水稻提取精度高达90%,分类总体精度可达87%,Kappa系数为0.85;与其他试验结果相比,漏分和误分现象较少,实现了南方地区水稻信息高精度自动识别。该方法计算特征少、实现简便,对于国产高分卫星影像在南方复杂地区作物自动提取中的应用具有参考性。     

松辽盆地南部油气田钻井取心关键技术

为有效解决松辽盆地南部油气田储集层取心钻头选型困难、机械钻速低和岩心收获率不稳定等难题,在分析取心井段地质特征、XRD元素组分占比、地层可钻性的基础上,开展了取心筒和岩心爪比选、取心钻头选型和个性化取心钻头的研制,同时优选取心钻具组合和优化取心参数,完善不同储集层取心工艺技术配套。比选后的取心工具配合新型取心钻头在多口井的取心实践中,取得了平均岩心收获率>98.98%、最高机械钻速达到6.03 m/h的效果。系列取心钻头优选和配套关键技术的应用解决了目前松辽盆地南部储集层取心的技术难题,可为后续取心提供可靠的参考和技术支持。     

贞丰烂泥沟金矿井下钻探施工工艺探讨

以贵州锦丰矿业有限公司贞丰烂泥沟金矿井下金刚石钻探工程施工过程为依托,对井下钻探施工中遇到的设备选型、内管输送、孔斜控制、封孔灌注等一系列技术问题,通过调整相应的钻进工艺方法和参数,取得了良好的施工效果。总结和探讨了适合贞丰烂泥沟金矿井下钻探施工的技术工艺,可为类似地层条件下的井下坑道钻探提供借鉴。     

特征筛选方法在高分辨率遥感影像建筑物提取中的应用

城市建筑物信息的自动提取是城市遥感的关键技术之一,由于阴影、下垫面等多因素干扰,建筑物信息提取精度往往不稳定。本文以Pleiades卫星影像为数据源,通过改进Relief F特征筛选方法,探讨建筑物信息提取精度提高的可行性。首先构建高分辨率遥感影像建筑物基础特征空间,然后利用改进型Relief F算法分析特征对象的权重并筛选出最优特征,最后用监督分类、无特征筛选分类和基于改进型Relief F特征筛选等3种方法分别提取研究区建筑物信息,并结合实地调查数据进行精度验证。结果表明,基于改进型Relief F特征筛选的分类方法提取精度能够达到91.34%,较其他两种方法提取精度分别提高了34.31%和5.62%,且运算速度快,自动识别效率高。     

中国援助柬埔寨乡村供水项目水井施工工艺及解决问题的措施

本文主要介绍了中国援助柬埔寨乡村供水井项目概况,针对项目施工难点从水井结构、设备选型、施工工序等方面进行了项目水井施工工艺设计,就施工难点和前期施工中遇到的问题提出了解决措施,取得了较好的效果。     

地质勘探用膨胀波纹管截面设计与选择

膨胀波纹管技术是将圆管制成异形截面管,下入孔内后胀圆维护孔壁稳定的一种新兴钻探技术。针对地质勘探的行业需求,提出了一套膨胀波纹管截面形状的设计理论,系统地阐述了膨胀波纹管截面设计的相关步骤和细节,设计出了6种花形不同尺寸的膨胀波纹管截面设计图。在此基础上,利用ANSYS14.0数值模拟软件对不同的设计截面进行了对比分析,得出了膨胀波纹管选择的3条原则：六瓣梅花形是最佳截面形式;设计截面的波峰和波谷的半径、弧度应尽量接近;在满足护壁压力要求的情况,壁厚应尽量的小。     

An experimental approach for selection/elimination in stream network generalization using support vector machines

Multi-representation databases (MRDB) are used in several Geographical Information System applications for different purposes. MRDB are mainly obtained through model and cartographic generalizations. The model generalization is essentially achieved with the selection/elimination process in which a decision must be made to include or exclude the object at the target level. In this study, support vector machines (SVM) was, for the first time, used for the selection/elimination process in stream network generalization. Within this context, the attributes to be used as input data in the SVM method were determined and weighted according to the associations determined in a chi-squared independence test. 1:100,000-scale (medium resolution) stream networks were derived from two 1:24,000-scale (high resolution) stream networks with different patterns in the United States Geological Survey National Hydrography Data-sets. The derived stream networks were quite similar to the 1:100,000-scale original stream networks in both qualitative and visual aspects.     

保持空间分布特征的散列式居民地综合选取方法

中小比例尺地形图上存在大量由不依比例尺"房屋群"构成的散列式居民地,综合选取时除考虑单个房屋专题重要性外,还要保持各房屋群的分布特征。将基于Vorinoi图模型的点群化简算法应用到散列式居民地选取中,在综合选取的两个主要过程(选取定额模型和结构化选取方法)中综合考虑分布密度、分布范围等分布结构信息和专题属性信息。实验分析表明,该方法保留重要居民地的同时,能够较好地保持原有的空间分布特征。     

On the advantage of sharing a holdfast: effects of density and occurrence of kin aggregation in the kelp Lessonia berteroana

We investigated the density‐dependent and genetic relatedness that regulate the occurrence of inter‐individual (genet) fusion forming plurigenotypic organisms in the brown alga Lessonia berteroana. Recruitment generally occurs at high densities in the inter‐tidal, allowing contact of neighbouring holdfasts as they grow and expand on the substrate. Algal density, by contrast, is regulated by the effects of herbivory and wave impact, which often lead to low holdfast density. Herein, we investigated whether the occurrence of plurigenotypic organisms and their genotypic composition (number of genotypes per plurigenotypic organism) are density dependent and affected by kin selection in the inter‐tidal kelp L. berteroana. Four microsatellite loci were used to analyse DNA from 260 samples obtained from shared and non‐shared holdfasts, at two sites with high and two site with low holdfast density. Analyses showed that fusions forming plurigenotypic organisms are extremely common. Interestingly, the frequency of fusions was higher in low‐density sites, in which 100% of the plants had at least two genotypes and the average was 3.5. In high‐density sites, 62% of plants were plurigenotypic, with an average of 2.8 genotypes per plant. Additionally, we found that genotypes that shared a holdfast had a significantly higher genetic relatedness than the average in the population, compatible with a kin structure. Density dependence and kin structure suggest that the occurrence of plurigenotypic organisms is linked to environmental quality, and that kin or multilevel selection may be favouring the fusion of genetically related genets.     

基于混合式特征选择的高分五号影像农田识别

精准农田识别是农作物估产和粮食安全评估的基础。遥感数据作为农田识别的重要数据源,可提供动态、快速的监测结果。高光谱数据在农田识别分类方面具有巨大的应用潜力,但其中的冗余波段影响了分类效率和分类精度。因此,本研究提出了一种适用于高光谱数据农田分类的混合式特征选择算法。首先,基于变量的重要性排序或约束程度,按步长逐步进行降维;其次,寻找分类精度骤减的转折点,并将其对应的变量作为特征子集;最后,利用序列后向选择SBS（Sequential Backward Selection）方法搜索最优分类特征子集。本研究利用GF-5高光谱数据,共研究了3种降维方法（随机森林RF（Random Forest）、互信息MI（Multi-Information）和L1正则化（L1 regularization））和3种分类算法（随机森林、支持向量机SVM（Support Vector Machine）和K近邻KNN（K-Nearest Neighbor））的组合在农田分类中的表现。结果表明,基于L1正则化法得到的特征子集自相关性较低,并且包含的红边和近红外波段有效提高了农田、森林和裸土的区分度。在不同分类模型比较中发现,SVM在高维空间中表现出非常好的抗噪能力,分类精度高于RF和KNN。而RF在低维空间中的泛化能力要高于SVM和KNN。相比于第一步降维得到的特征子集,使用SBS搜索得到的最优特征子集均提高了分类精度。最终,具有23维输入的L1-SVM-SBS分类模型得到了最高的总体分类精度（94.64%）和农田召回率（95.83%）。本研究为高光谱数据特征优选提供了一种新思路,筛选出了更具代表性的特征波段,提高了农田分类精度,对高光谱遥感分类研究具有参考价值。