Mapping coastal Great Lakes wetlands and adjacent land use through hybrid optical-infrared and radar image classification techniques
In the U.S., the National Wetland Inventory (NWI) is the most contiguous and current wetland map available, yet it lacks information on lands adjacent to wetlands and the distribution of invasive plants. Existing Canadian maps are comprised of a mosaic of mapping techniques, sources, and resolutions. A consistent baseline map is needed to monitor change in coastal ecosystems. Short falls in long-term monitoring is in part caused by reliance on dated, static, and inconsistent maps. Use of SOLEC or GLEI indicators is impeded by limitations of current maps, impacting the ability to monitor and detect effects from significant wetlands stressors; urban development and invasive plant species. Current work is underway to produce an international and contemporary baseline map for the Great Lakes Basin. Due to the complexity of wetland ecosystems, detection of species and extent as well as adjacent land use can be accomplished using sensor fusion approach. Synthetic Aperture Radar (SAR) is sensitive to flood condition as well as structure and biomass. Optical sensors, such as Landsat TM, are complementary in the classification and monitoring of wetland ecosystems. Previous research demonstrated the capability of ALOS PALSAR L-band data for detecting and mapping invasive Phragmites australis. The international wetlands map is being produced from a fusion of PALSAR and Landsat data and aims at detection of large stands of problematic plant species such Phragmites australis and Typha spp. A Random Forests classifier is used to create a land cover map through the integration of field and air photo interpreted data with underling sensor fusion data. The Lake Michigan map is complete and is being evaluated for accuracy through randomly selected field and air photo interpreted validation data. The basin wide maps will provide the first ever international Great Lakes coastal land cover map suitable for coastal wetland assessment and management.
Lake Michigan: State of the Lake, Great Lakes Beach Association Conference 2013
Endres, S. L.,
Bourgeau-Chavez, L. L.,
Laubach, Z. M.,
Miller, M. E.,
Mapping coastal Great Lakes wetlands and adjacent land use through hybrid optical-infrared and radar image classification techniques.
Lake Michigan: State of the Lake, Great Lakes Beach Association Conference 2013,
Retrieved from: http://digitalcommons.mtu.edu/mtri_p/123