Given the key role wetlands play in climate regulation and shoreline stabilization, identifying their spatial distribution is essential for the management, restoration, and protection of these invaluable ecosystems. The increasing availability of high spatial and temporal resolution optical and synthetic aperture radar (SAR) remote sensing data coupled with advanced machine learning techniques have provided an unprecedented opportunity for mapping complex wetlands’ ecosystems. A recent partnership between the National Aeronautics and Space Administration (NASA) and the Indian Space Research Organization (ISRO) resulted in the design of the NASA‐ISRO SAR (NISAR) mission. In this study, the capability of L‐band simulated NISAR data for wetland mapping in Yucatan Lake, Louisiana, is investigated using two object‐based machine learning approaches: Support vector machine (SVM) and random forest (RF). L‐band Unmanned Aerial Vehicle SAR (UAVSAR) data are exploited as a proxy for NISAR data. Specifically, we evaluated the synergistic use of different polarimetric features for efficient delineation of wetland types, extracting 84 polarimetric features from more than 10 polarimetric decompositions. High spatial resolution National Agriculture Imagery Program imagery is applied for image segmentation using the mean‐shift algorithm. Overall accuracies of 74.33% and 81.93% obtained by SVM and RF, respectively, demonstrate the great possibility of L‐band prototype NISAR data for wetland mapping and monitoring. In addition, variable importance analysis using the Gini index for RF classifier suggests that H/A/ALPHA, Freeman‐Durden, and Aghababaee features have the highest contribution to the overall accuracy.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.