Object-based random forest wetland mapping in Conne River, Newfoundland, Canada

• Published in: Journal of Applied Remote Sensing
• Main Authors: Granger, Jean Elizabeth, Mahdianpari, Masoud, Puestow, Thomas, Warren, Sherry, Mohammadimanesh, Fariba, Salehi, Bahram, Brisco, Brian
• Format: Article in Journal/Newspaper
• Language: English
• Published: SPIE 2021
• Subjects: wetlands; classification; watershed; multispectral classification; image classification; data modeling; remote sensing; vegetation; image segmentation; visualization; accuracy assessment; feature extraction; roads; synthetic aperture radar; Canada; Atlantic salmon; Newfoundland
• Online Access: https://doi.org/10.1117/1.JRS.15.038506; https://nrc-publications.canada.ca/eng/view/object/?id=4b9500c9-8943-4b53-bb55-f16bf01905fc; https://nrc-publications.canada.ca/fra/voir/objet/?id=4b9500c9-8943-4b53-bb55-f16bf01905fc

The Conne River watershed is dominated by wetlands that provide valuable ecosystem services, including contributing to the survivability and propagation of Atlantic salmon, an important subsistence species that has shown a dramatic decline over the past 30 years. To better understand and improve the management of the watershed, and in turn, the Atlantic salmon, a wetland inventory of the area is developed using advanced remote sensing methods including field-collected data, object-based image analysis of Sentinel-1, Sentinel-2, and digital elevation model Earth observation data. The resulting classification maps consisted of bog, fen, swamp, marsh, and open water wetlands with an overall accuracy of 92% and a kappa coefficient of 0.916. Among wetland classes, user and producer accuracies range between 84% and 100%. Results show the dominance of peatland wetlands such as bog and fen, and the relative rareness of marsh wetlands. Peer reviewed: Yes NRC publication: Yes