Funding agency: NSERC
Description:
We are developing methodologies to classify wetlands (Open Bog, Treed Bog, Open Fen, Treed Fen, and Swamps) and map surface water from multi-source remotely sensed data using advanced classification algorithms. The data are being investigated include multispectral optical and thermal data (Landsat-5), and SAR imagery from RADARSAT-2, and Sentinel-1. The goals are to determine the best way to combine the aforementioned imagery to classify wetlands, and determine the most significant image features and strategies in wetland classification. Classification algorithms investigated in this study are Naive Bayes, K-Nearest Neighbor (K-NN), Support Vector Machine (SVM), and Random Forest (RF). We will also exploit deep learning networks.
Publications:
Zhang, W., B. Hu, and G. Brown, “Automatic surface water mapping using Polarimetric SAR data for long-term change detection”, Water 2020, 12(3), 872; https://doi.org/10.3390/w12030872
