基于神经网络的区域生态环境分类方法研究

如何利用智能化信息提取技术,进行区域生态环境自动分类,一直是一种前沿性研究。该文在分析研究区自然景观特征的基础上,总结了影响区域生态环境的建模要素,基于神经网络技术,并根据生态环境的遥感探测机理,利用TM卫星遥感数据中的可见光、热红外、植被指数(NDVI)以及DEM数据,建立了基于BP神经网络的区域生态环境信息自动提取模型,形成了一种新的生态环境分类方法,其分类结果与实际情况完全一致。     

Leaf area index retrieval based on canopy reflectance and vegetation index in eastern China

The aim of this paper is to investigate the feasibility of using Landsat TM data to retrieve leaf area index (LAI). To get a LAI retrieval model based ground reflectance and vegetation index, detailed field data were collected in the study area of eastern China, dominated by bamboo, tea plant and greengage. Plant canopy reflectance of Landsat TM wavelength bands has been inversed using software of 6S. LAI is an important ecological parameter. In this paper, atmospheric corrected Landsat TM imagery was utilized to calculate different vegetation indices (VI), such as simple ratio vegetation index (SR), shortwave infrared modified simple ratio (MSR), and normalized difference vegetation index (NDVI). Data of 53 samples of LAI were measured by LAI-2000 (LI-COR) in the study area. LAI was modeled based on different reflectances of bands and different vegetation indices from Landsat TM and LAI samples data. There are certainly correlations between LAI and the reflectance of Tm3, TM4, TM5 and TM7. The best model through analyzing the results is LAI = 1.2097*MSR + 0.4741 using the method of regression analysis. The result shows that the correlation coefficient R2 is 0.5157, and average accuracy is 85.75%. However, whether the model of this paper is suitable for application in subtropics needs to be verified in the future.     

鄂 北 地 区 钻 头 优 选 探 讨

为适应鄂尔多斯塔巴庙区块勘探开发需要，利用区域测井资料进行钻头选型，并结合现场实践优化钻头类型和钻井参数，提高钻井效率。通过新型PDC钻头推广应用,单口井所需钻头数量减少3~4只，减少起下钻3回次以上，缩短钻井周期3~5天。     

基于随机森林特征选择的城市绿化乔木树种分类

城市绿化在改善空气、水和土壤质量,吸收和减少二氧化碳及各种污染物,缓解城市热岛和减少雨水径流等方面发挥着重要作用。及时准确地获取树种信息是城市规划与绿化管理的先决条件,对进一步改善城市生态环境也具有重要意义。基于遥感技术,使用高空间分辨率的WorldView-2卫星影像,采用光谱、纹理、指数以及几何等多种特征相结合的面向对象方法,并通过随机森林进行特征选择,对福州大学旗山校区北部的榕树、杧果、香樟、重阳木、羊蹄甲、垂叶榕以及木棉7种主要绿化乔木进行树种分类。实地验证结果表明：通过特征选择可以减少或规避数据冗余以及休斯效应的产生,该方法可以提高现有同类型树种分类的精度,当淘汰全部特征的20%,利用34个特征（包括15个光谱特征、6个纹理特征、8个指数特征和5个几何特征）进行分类时,总精度最高,可达74.95%,Kappa系数为0.67。其中,光谱平均值的特征重要性最高,而各波段的标准差的重要性较低。WorldView-2卫星影像的4个新增波段,特别是黄光和红边波段及其构建的指数特征重要性较高,也说明这些波段在植被遥感,特别是树种分类中极具应用前景。     

Automatic Sounding Generalization in Nautical Chart Considering Bathymetry Complexity Variations

Sounding acts as the main feature in a digital nautical chart as it describes the concerned marine topography for the safety of navigation. Unlike the geometry-oriented selection of point feature, the generalization of soundings for chart compiling is expected to be context-oriented, which means bathymetry complexity variations across the study region should be preserved in the sounding selection process. However, such variations are not explicitly accessible to automated systems. This paper proposes an approach that effectively analyzes and measures bathymetry complexity from sounding data, with a focus on topography variations among different regions. The presented approach first divides the exploring region into several subregions, by adopting techniques of computational geometry and graph theory. Then, the approach quantitatively measures the bathymetry complexity of the subregions from grid-based digital terrain model. Finally, a composite bathymetry complexity index integrating aspects of steepness and depth variation is developed to guide the operation of sounding selection in different subregions. Generally, when seafloor is rugged with steep slopes, the number of soundings is high. While in flatter areas, a smaller amount of soundings is retained. The potential of our approach is demonstrated by an application to a real data set.     

Remote estimation of terrestrial evapotranspiration by Landsat 5 TM and the SEBAL model in cold and high‐altitude regions: a case study of the upper reach of the Shule River Basin,China

Evapotranspiration (ET) is an important expenditure in water and energy balances, especially on cold and high‐altitude land surfaces. Daily ET of the upper reach of the Shule River Basin was estimated using Landsat 5 TM data and the Surface Energy Balance Algorithm for Land (SEBAL) model. Based on observations made at the Suli station, the algorithms of land surface temperature and soil heat flux in SEBAL were modified. Land surface temperature was retrieved and compared with ground truth via three methods: the radiative transfer equation method, the mono‐window algorithm, and the single‐channel method. We selected the best of these methods, mono‐window algorithm, for estimating ET. The average error of daily ET estimated by the modified SEBAL model and measured by the eddy covariance system was 16.4%, with a root‐mean‐square error of 0.52 mm d^?1. The estimated ET means were 3.09, 2.48, and 1.48 mm d^?1 on June 9 (DOY 160), June 25 (DOY 176), and July 27 (DOY 208) of the year 2010, respectively. The average estimated ET on the glacier surface of all days was more than 3 mm d^?1, a measurement that is difficult to capture in‐situ and has rarely been reported. This study will improve the understanding of water balance in cold, high‐altitude regions. Copyright © 2016 John Wiley & Sons, Ltd.     

多尺度邻域特征下的机载LiDAR点云电力线分类

利用机载激光雷达技术三维测量精度高且获取快速的优点进行电力线自动分类提取已成为点云数据处理与电力应用的重要领域。针对电力线分类模型的自动化和高精度需求，本文提出了基于三维多尺度邻域特征的机载LiDAR点云电力线分类提取模型框架，主要包括4个步骤：电力线候选点滤波、多尺度邻域类型选取、形状结构特征提取和支持向量机分类。通过对2个复杂城市区域的试验数据集和8种不同邻域类型的详细结果对比分析，发现基于多尺度圆球邻域形状结构特征的分类模型结果准确率、召回率和质量分别达到97%、94%和93%，同时整体处理时间在2个试验数据中分别从366、256 s减少到274、160 s。试验结果表明，该方法在多种复杂城市场景中能够实现机载LiDAR数据的电力线较高精度分类提取。     

南海北部海域油气勘探保障建设选址适宜性研究

为分析南海北部海域油气勘探保障建设选址的适宜性,在广泛研究备选区特征资料的基础上,基于层次分析法(Analytic Hierarchy Process, AHP)原理,以自然环境因素、开发环境因素、基础设施与投资情况以及其他因素作为一级评判准则,建立了包括12项二级评判准则的递进层次结构模型,并以永兴岛、赵述岛和晋卿岛作为3个假定备选区,来验证分析评价模型的有效性和可靠性。AHP评判结果显示,3个备选区的整体优劣指数依次为0.587 1, 0.212 1, 0.200 8;AHP模型的一致性比例CR值为0.020 3。通过分析和筛选影响远海油气勘探保障建设的选址因子,构建基于AHP原理的选址评价模型,可用于分析评价南海北部岛礁油气勘探保障建设选址的适宜性。     

中国企业R&D国际化:时空格局与区位选择影响因素

基于中国企业海外R&D投资数据和零断尾负二项回归分析方法,探讨了1998—2015年中国企业R&D国际化的时空格局特征,并从东道国角度分析影响其区位选择的主要因素。结果表明：研究期内中国新建海外R&D机构数量快速扩张;海外R&D投资区域分布广泛,呈现分散和集聚并存的特征;以华为为例分析了典型中国企业海外R&D投资的空间布局特征,认为目前华为海外R&D投资呈现集中布局在欧洲,零散分布在亚洲、美洲、非洲的空间特征,主要是由其以全球技术升级和满足多样化的市场需求等R&D国际化的战略动机所决定。回归分析结果表明,中国企业对发达国家和发展中国家进行R&D投资的影响因素有共同点但也存在一定的差异：① 现阶段东道国的R&D需求不是影响中国企业对其进行R&D投资的主要因素;② 代表中国与东道国经济往来密切程度的关联要素是影响中国企业R&D投资的重要决策因素;③ 发达国家吸引中国企业对其进行R&D投资主要是因其创新能力强、R&D资源数量多,而政策及制度供给是影响中国企业对发展中国家进行R&D投资的主要因素;④ 地理距离对中国企业R&D“走出去”的阻碍作用主要体现在对发展中国家的R&D投资中。     

运用ENVI实现SPOT-5卫星影像的RVI提取

运用ENVI软件处理长沙地区的SPOT-5影像,将全色影像和多波段影像进行融合,分析融合后的影像,再选择感兴趣区域进行影像裁剪;采用ENVI的波段运算(Band3/Band2)提取该地区比值植被指数并进行分析。结果表明:比值植被指数对植被覆盖率较高的区域有非常高的敏感度;在植被覆盖率小于50%的时候,其敏感度明显降低,在绿色植被覆盖区域的比值植被指数远大于1,在裸露地表、建筑物、水体等没有植被覆盖区域的比值植被指数则在1附近,而比值植被指数大于2的则出现在高覆盖健康绿色植被上。