...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Estuarine Coastal and Shelf Science >Improving salt marsh digital elevation model accuracy with full- waveform lidar and nonparametric predictive modeling
【24h】

Improving salt marsh digital elevation model accuracy with full- waveform lidar and nonparametric predictive modeling

机译：利用全波形激光雷达和非参数预测模型提高盐沼数字高程模型的准确性

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Salt marsh vegetation tends to increase vertical uncertainty in light detection and ranging (lidar) derived elevation data, often causing the data to become ineffective for analysis of topographic features governing tidal inundation or vegetation zonation. Previous attempts at improving lidar data collected in salt marsh environments range from simply computing and subtracting the global elevation bias to more complex methods such as computing vegetation-specific, constant correction factors. The vegetation specific corrections can be used along with an existing habitat map to apply separate corrections to different areas within a study site. It is hypothesized here that correcting salt marsh lidar data by applying location-specific, point-by-point corrections, which are computed from lidar waveform-derived features, tidal-datum based elevation, distance from shoreline and other lidar digital elevation model based variables, using nonparametric regression will produce better results. The methods were developed and tested using full-waveform lidar and ground truth for three marshes in Cape Cod, Massachusetts, U.S.A. Five different model algorithms for nonparametric regression were evaluated, with TreeNet's stochastic gradient boosting algorithm consistently producing better regression and classification results. Additionally, models were constructed to predict the vegetative zone (high marsh and low marsh). The predictive modeling methods used in this study estimated ground elevation with a mean bias of 0.00 m and a standard deviation of 0.07 m (0.07 m root mean square error). These methods appear very promising for correction of salt marsh lidar data and, importantly, do not require an existing habitat map, biomass measurements, or image based remote sensing data such as multi/hyperspectral imagery. (C) 2017 Published by Elsevier Ltd.
机译：盐沼植被倾向于增加光探测和测距（激光）导出的高程数据的垂直不确定性，通常导致该数据对于分析控制潮汐淹没或植被分区的地形特征变得无效。以前在盐沼环境中改善激光雷达数据的尝试包括简单地计算和减去全球海拔偏差，再到更复杂的方法，例如计算特定于植被的恒定校正因子。特定于植被的校正可以与现有的栖息地地图一起使用，以将单独的校正应用于研究地点内的不同区域。这里假设通过应用特定位置的逐点校正来校正盐沼激光雷达数据，这些校正是从激光雷达波形衍生的要素，基于潮汐基准的海拔，距海岸线的距离以及其他基于激光雷达数字高程模型的变量计算得出的，使用非参数回归将产生更好的结果。该方法是在美国马萨诸塞州科德角的三个沼泽中使用全波形激光雷达和地面真相开发和测试的。评估了五种不同的非参数回归模型算法，TreeNet的随机梯度增强算法始终可产生更好的回归和分类结果。此外，还建立了预测营养区（高沼泽地和低沼泽地）的模型。本研究中使用的预测建模方法估算的地面标高为0.00 m，平均偏差为0.07 m（均方根误差为0.07 m）。这些方法看来对盐沼激光雷达数据的校正非常有前途，而且重要的是，不需要现有的栖息地图，生物量测量值或基于图像的遥感数据（例如多/高光谱图像）。 （C）2017由Elsevier Ltd.发布

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号