Improved wetland remote sensing in Yellowstone National Park using classification trees to combine TM imagery and ancillary environmental data
Improved wetland remote sensing in Yellowstone National Park using classification trees to combine TM imagery and ancillary environmental data
复制标题
DOI：
10.1016/j.rse.2006.10.019
复制
发表时间：
2007-04
影响因子：
13.5
通讯作者：
C. Wright;A. Gallant
中科院分区：
文献类型：
--
作者：
C. Wright;A. Gallant
美国鱼类和野生动物管理局使用术语沼泽湿地来描述传统上被识别为沼泽，沼泽，沼泽，沼泽或湿草甸的植被湿地。Landsat TM图像与图像纹理和辅助环境数据相结合，利用分类树对黄石国家公园沼泽湿地出现的概率进行建模。模型的培训和测试的位置确定从国家湿地清单地图，分类树建立了七年的范围内的年降水量。在粗层次上，沼泽湿地与高地是分离的。在更细的层面上，区分了五种沼泽湿地类型：水生床（PAB）、新兴（PEM）、森林（PFO）、灌丛-灌木（PSS）和松散海岸（PUS）。TM衍生的变量单独相对准确的湿地从高地分离，但模型的错误率逐渐下降，图像纹理，DEM衍生的地形变量，和其他辅助GIS层添加。对于分类树，利用所有可用的预测，平均整体测试误差率为7.8%的沼泽湿地/高地模型和17.0%的沼泽湿地型模型，多年来一致的准确性。然而，模型容易对湿地进行过度预测。虽然主要的PEM类被分类为遗漏和佣金错误率小于14%，但我们很难识别PAB和PSS类。辅助植被信息大大提高了PSS分类和适度提高PFO的歧视。协会与地热区区分PUS湿地。湿地过度预测加剧了类的不平衡，可能与TM传感器的空间和光谱限制相结合。湿地概率表面可能比硬分类信息更多，并出现气候驱动的湿地变化。所开发的方法具有可移植性，相对容易实现，并应适用于其他设置和更大的范围。
The U.S. Fish and Wildlife Service uses the term palustrine wetland to describe vegetated wetlands traditionally identified as marsh, bog, fen, swamp, or wet meadow. Landsat TM imagery was combined with image texture and ancillary environmental data to model probabilities of palustrine wetland occurrence in Yellowstone National Park using classification trees. Model training and test locations were identified from National Wetlands Inventory maps, and classification trees were built for seven years spanning a range of annual precipitation. At a coarse level, palustrine wetland was separated from upland. At a finer level, five palustrine wetland types were discriminated: aquatic bed (PAB), emergent (PEM), forested (PFO), scrub–shrub (PSS), and unconsolidated shore (PUS). TM-derived variables alone were relatively accurate at separating wetland from upland, but model error rates dropped incrementally as image texture, DEM-derived terrain variables, and other ancillary GIS layers were added. For classification trees making use of all available predictors, average overall test error rates were 7.8% for palustrine wetland/upland models and 17.0% for palustrine wetland type models, with consistent accuracies across years. However, models were prone to wetland over-prediction. While the predominant PEM class was classified with omission and commission error rates less than 14%, we had difficulty identifying the PAB and PSS classes. Ancillary vegetation information greatly improved PSS classification and moderately improved PFO discrimination. Association with geothermal areas distinguished PUS wetlands. Wetland over-prediction was exacerbated by class imbalance in likely combination with spatial and spectral limitations of the TM sensor. Wetland probability surfaces may be more informative than hard classification, and appear to respond to climate-driven wetland variability. The developed method is portable, relatively easy to implement, and should be applicable in other settings and over larger extents.