The integration of optical, topographic, and radar data for wetland mapping in northern Minnesota
The integration of optical, topographic, and radar data for wetland mapping in northern Minnesota
复制标题
DOI：
10.5589/m11-067
复制
发表时间：
2011-10
影响因子：
2.6
通讯作者：
J. Corcoran;J. Knight;B. Brisco;S. Kaya;Andrew Cull;K. Murnaghan
中科院分区：
文献类型：
--
作者：
J. Corcoran;J. Knight;B. Brisco;S. Kaya;Andrew Cull;K. Murnaghan
准确和最新的湿地地图是水资源管理的重要工具，然而，许多现有的湿地地图是通过人工解释每个感兴趣地区的航空图像创建的。因此，这些地图本身并不包含有关湿地年内和年际水文循环的信息，而这些信息对于有效的湿地制图很重要。在本文中，遥感数据的几个来源将被整合和评估其适合映射在明尼苏达州北方森林地区的湿地。这些数据包括：一个生长季节两个不同时期的航空照片、国家高程数据集和坡度和曲率等地形衍生物以及多时相卫星合成孔径雷达图像和极化分解。我们确定了最重要的变量，准确地分类湿地从高地地区和明尼苏达州北部北方森林地区的决策树分类randomForest的湿地类型之间的区别。该分类器能够区分湿地高地和水与75%的准确性，使用光学，地形和SAR数据相结合，与72%单独使用光学和地形数据相比。分类湿地类型被证明是更具挑战性的，然而，结果显着改善了原来的国家湿地清单分类只有49%相比，63%，使用光学，地形和SAR数据相结合。本文举例说明，集成多个传感器平台和多个时期的遥感数据，在生长季节改善湿地制图和湿地类型分类在北方明尼苏达州。
Accurate and current wetland maps are critical tools for water resources management, however, many existing wetland maps were created by manual interpretation of one aerial image for each area of interest. As such, these maps do not inherently contain information about the intra- and interannual hydrologic cycles of wetlands, which is important for effective wetland mapping. In this paper, several sources of remotely sensed data will be integrated and evaluated for their suitability to map wetlands in a forested region of northern Minnesota. These data include: aerial photographs from two different times of a growing season, National Elevation Dataset and topographical derivatives such as slope and curvature, and multitemporal satellite-based synthetic aperture radar (SAR) imagery and polarimetric decompositions. We identified the variables that are most important to accurately classify wetland from upland areas and discriminate between wetland types for a forested region of northern Minnesota using the decision-tree classifier randomForest. The classifier was able to differentiate wetland from upland and water with 75% accuracy using optical, topographic, and SAR data combined, compared with 72% using optical and topographical data alone. Classifying wetland type proved to be more challenging; however, the results were significantly improved over the original National Wetland Inventory classification of only 49% compared with 63% using optical, topographic, and SAR data combined. This paper illustrates that integration of remotely sensed data from multiple sensor platforms and over multiple periods during a growing season improved wetland mapping and wetland type classification in northern Minnesota.