Feature pruning by upstream drainage area to support automated generalization of the United States National Hydrography Dataset
Feature pruning by upstream drainage area to support automated generalization of the United States National Hydrography Dataset
复制标题
DOI：
10.1016/j.compenvurbsys.2009.07.004
复制
发表时间：
2009-09-01
影响因子：
6.8
通讯作者：
Stanislawski, Lawrence V.
中科院分区：
文献类型：
--
作者：
Stanislawski, Lawrence V.
美国地质调查局一直在研究综合方法，以实现地理数据的多尺度显示和交付。本文提出了自动修剪美国高分辨率国家水文数据集(NHD)的网络和面要素以降低分辨率的方法。要素修剪规则、数据丰富和划分源自地表水、NHD模型和相关要素规范标准的知识。从上游流域面积(UDA)估计网络特征的相对显著程度。网络和面要素通过UDA和NHD REACH代码进行修剪，以获得适用于任何不太详细的地图比例的排水密度。数据分区保持了表征地形特征的局部排水密度变化。作为演示，48个子流域区域的1：24000 NHD被修剪为1：10万比例尺(100K)，并与基准的100K NHD进行比较。线路对应系数(CLC)用于评估修剪后的网络特征与基准网络的匹配程度。CLC值为0.82和0.77分别是在有分区和没有分区的情况下进行修剪的结果。修剪后剩余的多边形数约为基准的七倍，但修剪后剩余的多边形所覆盖的面积仅比基准多边形所覆盖的面积大10%左右。(C)爱思唯尔有限公司出版的2009年。
The United States Geological Survey has been researching generalization approaches to enable multiple-scale display and delivery of geographic data. This paper presents automated methods to prune network and polygon features of the United States high-resolution National Hydrography Dataset (NHD) to lower resolutions. Feature-pruning rules, data enrichment, and partitioning are derived from knowledge of surface water, the NHD model, and associated feature specification standards. Relative prominence of network features is estimated from upstream drainage area (UDA). Network and polygon features are pruned by UDA and NHD reach code to achieve a drainage density appropriate for any less detailed map scale. Data partitioning maintains local drainage density variations that characterize the terrain. For demonstration, a 48 subbasin area of 1:24 000-scale NHD was pruned to 1: 100 000-scale (100 K) and compared to a benchmark, the 100 K NHD. The coefficient of line correspondence (CLC) is used to evaluate how well pruned network features match the benchmark network. CLC values of 0.82 and 0.77 result from pruning with and without partitioning, respectively. The number of polygons that remain after pruning is about seven times that of the benchmark, but the area covered by the polygons that remain after pruning is only about 10% greater than the area covered by benchmark polygons. (C) 2009 Published by Elsevier Ltd.