TOWARD A MULTI-SOURCE REMOTE SENSING WETLAND INVENTORY OF THE USA: PRELIMINARY RESULTS ON WETLAND INVENTORY OF MINNESOTA
- 1Department of Environmental Resources Engineering, College of Environmental Science and Forestry, State University of New York, Syracuse, New York, USA
- 2C-CORE and Department of Electrical Engineering, Memorial University of Newfoundland, St. John’s, NL A1B 3X5, Canada
Keywords: Geo-Big data, Classification, Machine Learning, Random Forest, Minnesota, Google Earth Engine
Abstract. Wetlands are highly productive ecosystems that offer unique services on regional and global scales including nutrient assimilation, carbon reduction, geochemical cycling, and water storage. In recent years, however, they are being lost or exploited as croplands due to natural or man-made stressors (1.4 percent in 5 years within the USA). This decline in the extent of wetlands began legislative activity at a national scale that mandate the regulate use of wetlands. As such, the need for cost-effective, robust, and semi-automated techniques for wetland preservation is ever-increasing in the current era. In this study, we developed a workflow for wetland inventorying on a state-wide scale using optimal incorporation of dual-polarimetry Sentinel-1, multi-spectral Sentinel-2 and dual polarimetry ALOS-PALSAR with the Random Forest (RF) classifier in Google Earth Engine (GEE). A total of 45 features from a stack of multi-season/multi-year SAR and Optical imagery (included more than 5000 imagery) was extracted over Minnesota state, USA. We followed the Cowardin classification scheme for clustering the field data. The classification was performed in two levels in 5 different ecozones that cover the Minnesota state. Depending on the availability field data for each ecozone overall accuracies changed from 77% to 85%. The variable importance analysis suggests that Sentinel-2 spectral features are dominant in terms of their capability for wetland delineation. Sentinel-1 backscattering coefficient was also superior among other SAR features. Ultimately, the results of this study shall illustrate the applicability of free of charge earth observation data coupled with the advanced machine learning techniques that are available in GEE for better restoration and management of wetlands.