高分六号遥感卫星新增波段下的树种分类精度分析     

张沁雨  李哲  夏朝宗  陈健  彭道黎 《地球信息科学学报》2019,21(10):1619-1628

高分六号卫星具有覆盖广、多种分辨率、波段多的优势,能为遥感解译提供更丰富的信息。为探究高分六号卫星新增波段在森林树种识别上的应用,本文以覆盖根河市阿龙山林业局的一期高分六号宽幅影像为数据源,基于特征优化空间算法（Feature Space Optimization,FSO）和最大似然分类法,分别利用高分六号的前4个波段和所有波段（8波段）的光谱、纹理等特征进行了森林树种分类,并逐一添加新增波段特征确定了各波段的贡献率排名。结果表明：在加入了优选出的均匀性纹理、均值纹理和角二阶矩纹理3种纹理特征后,前4波段和8波段的分类精度比只基于光谱特征时的精度分别高出13.23%和24.63%;利用8波段信息比只利用前4波段在基于光谱特征上的精度高11.88%,在基于光谱+纹理特征上则高23.24%;基于8波段光谱+纹理特征的树种分类精度最高,达到68.74%,新增4波段的贡献率排名为B6>B5>B8>B7,说明新增红边波段对于本次树种分类试验的贡献率最高,能为北方树种识别提供有效帮助。  相似文献   

青藏高原上中尺度对流系统东移传播成因   总被引：6，自引：0，他引：6  

过仲阳  林珲  江吉喜  黄签  方兆宝 《地球信息科学学报》2003,5(1):5-10

运用1998年夏季日本静止气象卫星探测反演出的红外辐射亮温资料,对青藏高原上的中尺度对流系统(MCSs)进行了自动追踪,进而对移出高原的MCSs进行了分类,在此基础上,运用空间数据挖掘中的决策树方法得到了东移出高原的MCSs与其环境物理量场之间的关系,结果表明,在400hPa上,当MCSs的中心位置位于100°E附近时,移出高原且向东南方向移动的MCSs仅与该等压面上的高度和温度有关;而向东北方向移动的MCSs仅与高度和假相当位温有关;此外,移出高原且方向向东的MCSs主要决定于等压面高度、散度、涡度和假相当位温这4个物理量值。在500hPa上,位于东经104°E以西且最终移出高原的MCSs,决定其是否移向东北方向的环境物理量因素为K指数和水汽通量散度,而影响其向东南及东方向移动的因素则较多。  相似文献   

城镇-农业-生态空间划定的多情景模拟     

柯新利  肖邦勇  郑伟伟  马艳春  李红艳 《地球信息科学学报》2020,22(3):580-591

城镇-农业-生态空间划定(简称"三区"划定)是国土空间规划的核心内容,对于科学合理地规划、利用有限的国土资源具有重要的意义。已有研究主要根据区域内土地利用与社会经济发展现状构建指标体系进行"三区"划定,较少将未来土地利用变化纳入"三区"划定过程中,使得划定结果在指导实践过程中缺乏前瞻性。针对这一问题,本文提出一种基于土地利用情景模拟,结合指标体系评价与决策树特征挖掘的"三区"划定方法,并以武汉市2015年土地利用现状为基础,在土地利用变化情景模拟的基础上进行"三区"划定。通过对比,验证了本文提出方法的合理性。研究发现:①不同情景下的"三区"空间在规模、空间分布上具有明显差异,将未来土地利用变化纳入"三区"划定过程中确有必要;②不同土地利用情景下"三区"空间的差异主要出现在三类空间的交界区域,这些区域是国土空间规划应该关注的重点区域。  相似文献   

一种基于机器学习算法的岩性填图方法     

冀全伟  王文磊  刘治博  祝茂强  袁长江 《地质力学学报》2021,27(3):339-349

通过野外地质调查与机器学习方法的有机融合,提出了一种基于梯度提升决策树算法的岩性单元填图方法.研究以多龙矿集区为模型试验区,选择1:5万勘查地球化学数据为基础预测数据,以1:5万区域地质图为参考,进行基于梯度提升决策树算法的岩性预测填图模型试验.首先选择研究区内小范围空白区开展野外填图,建立原始数据集并初步构建岩性单元...  相似文献   

Classifier ensembles for land cover mapping using multitemporal SAR imagery   总被引：3，自引：0，他引：3  

Bjrn Waske  Matthias Braun 《ISPRS Journal of Photogrammetry and Remote Sensing》2009,64(5):450-457

SAR data are almost independent from weather conditions, and thus are well suited for mapping of seasonally changing variables such as land cover. In regard to recent and upcoming missions, multitemporal and multi-frequency approaches become even more attractive. In the present study, classifier ensembles (i.e., boosted decision tree and random forests) are applied to multi-temporal C-band SAR data, from different study sites and years. A detailed accuracy assessment shows that classifier ensembles, in particularly random forests, outperform standard approaches like a single decision tree and a conventional maximum likelihood classifier by more than 10% independently from the site and year. They reach up to almost 84% of overall accuracy in rural areas with large plots. Visual interpretation confirms the statistical accuracy assessment and reveals that also typical random noise is considerably reduced. In addition the results demonstrate that random forests are less sensitive to the number of training samples and perform well even with only a small number. Random forests are computationally highly efficient and are hence considered very well suited for land cover classifications of future multifrequency and multitemporal stacks of SAR imagery.  相似文献   

湖北省保康磷矿区开采面及固体废弃物遥感信息提取方法研究     

杨强  张志 《国土资源遥感》2009,(2):87-90

统计分析了湖北保康磷矿区有关目标地物(道路、建筑物、坡耕地、植被、水体及阴影等)的SPOT 5影像特征,认为它们具有一定相似性和差异性,依赖单一的遥感分类方法难以实现对矿区开采面及固体废弃物信息的准确提取.采用决策树分类方法,设置一定的分类规则,结合数字高程模型和含矿地层等相关辅助数据,逐一对矿区相关地物进行分类,经分类结果后处理,分类精度达83.4%.  相似文献   

基于遥感影像的城市森林分类提取及生态价值估算研究   总被引：2，自引：1，他引：1  

柳晶辉  邵芸  黄初冬 《地理与地理信息科学》2007,23(4):33-36

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.  相似文献   

Modelling and observation of hedgerow transpiration effect on water balance components at the hillslope scale in Brittany     

Z. Thomas  R. Ghazavi  P. Merot  A. Granier 《水文研究》2012,26(26):4001-4014

Vegetation has a major influence on the water and energy balance of the earth's surface. In the last century, human activities have modified land use, inducing a consequent change in albedo and potential evapotranspiration. Linear vegetation structures (hedgerows, shelterbelts, open woodland, etc) were particularly abundant but have declined considerably over the past several decades. In this context, it is important to quantify their effect on water and energy balance both on a global scale (climate change and weather prediction) and on a local scale (soil column, hillslope and watershed). The main objective of this study was to quantify the effect of hedgerows on the water cycle by evaluating spatial and temporal variations of water balance components of a hillslope crossed by a hedgerow. Water flow simulation was performed using Hydrus‐2D to emphasize the importance of transpiration in the water balance and to evaluate water extraction from groundwater. Model validation was performed by comparing simulated and observed soil matrix potentials and groundwater levels. Hedgerow transpiration was calculated from sap flow measurements of four trees. Water balance components calculated with a one‐dimensional water balance equation were compared with simulations. Simulation runs with and without tree root uptake underlined the effect of hedgerow transpiration, increasing capillary rise and decreasing drainage. Results demonstrated that the spatial and temporal variability of water balance components was related to the hedgerow presence as well as to the meteorological context. The relations between transpiration, groundwater proximity and soil‐water availability determined the way in which water balance components were affected. Increased capillary rise and decreased drainage near hedges were related to the high transpiration of trees identified in this study. Transpiration reached twice the potential evapotranspiration when groundwater level and precipitation amounts were high. Water balance analysis showed that transpiration was a substantial component, representing 40% of total water output. These results may offer support for improving hydrological models by including the effect of land use and land cover on hydrological processes. Copyright © 2012 John Wiley & Sons, Ltd.  相似文献   

地图数据库中的结构化河网及其自动建立   总被引：3，自引：0，他引：3  

杜清运 《武汉大学学报(信息科学版)》1988,(2)

本文提出了一种基于河段的结构化河网,讨论了这种结构化河网的自动建立过程,主要包括两个结构索引即线索树结构索引及层次结构索引的自动产生;根据包含以上两个索引的结构化河网,提供了若干检索函数,作为地图数据库中结构处理时结构信息的提取手段。  相似文献   

Influence of multipurpose trees on agricultural crops in arid regions of Haryana, India   总被引：2，自引：0，他引：2  

Sunil Puri  Bangarwa K. S.  Shambhu Singh 《Journal of Arid Environments》1995,30(4)

The effects of multipurpose trees on the productivity of agricultural crops were studied in the arid regions of Haryana. In one of the experiments, wheat was grown on irrigated farms having scattered trees ofDalbergia sissoo, Azadirachta indica, Prosopis cinerariaandAcacia nilotica. Data of wheat yield for each tree species at different distances (1, 3, 5, and 7 m) and four directions (East, West, North and South) from the tree bases and control (no trees) were collected. Results indicate thatAzadirachta indicaandProsopis cinerariadid not produce any significant difference in the wheat yield while the other two species (Dalbergia sissooandAcacia nilotica) gave a reduction in yield.A. niloticahad a more significant and prominent effect and a reduction of 40 to 60 % wheat yield was observed.Dalbergia sissooreduced yield by 4 to 30 % but the reduction was only up to a distance of 3 m. In general, the impact of trees on productivity was observed up to 3 m distance and there was little, if any, impact up to 5 m and almost no impact at 7 m.In another experiment,D. sissoo(18-years-old) was raised as windbreak and productivity of cotton was assessed. The tree belt reduced the wind speed by 15 to 45 %, depending on season and wind speed. The influence of trees on cotton yield was observed to be negative up to 2H (36 m), where H is tree height, i.e. 18 m. Cotton productivity was observed to be maximum between 2H and 5H. Depending upon orientation of tree belt, the increase in cotton yield was found to be 4 to 10 %.  相似文献