An Advanced Data Fusion Method to Improve Wetland Classification Using Multi-Source Remotely Sensed Data

Abstract

The goal of this research was to improve wetland classification by fully exploiting multi-source remotely sensed data. Three distinct classifiers were designed to distinguish individual or compound wetland categories using random forest (RF) classification. They were determined, in part, to best use the available remotely sensed features in order to maximize that information and to maximize classification accuracy. The results from these classifiers were integrated according to Dempster–Shafer theory (D–S theory). The developed method was tested on data collected from a study area in Northern Alberta, Canada. The data utilized were Landsat-8 and Sentinel-2 (multi-spectral), Sentinel-1 (synthetic aperture radar—SAR), and digital elevation model (DEM). Classification of fen, bog, marsh, swamps, and upland resulted in an overall accuracy of 0.93 using the proposed methodology, an improvement of 5% when compared to a traditional classification method based on the aggregated features from these data sources. It was noted that, with the traditional method, some pixels were misclassified with a high level of confidence (>85%). Such misclassification was significantly reduced (by ~10%) by the proposed method. Results also showed that some features important in separating compound wetland classes were not considered important using the traditional method based on the RF feature selection mechanism. When used in the proposed method, these features increased the classification accuracy, which demonstrated that the proposed method provided an effective means to fully employ available data to improve wetland classification.