Thanks

landscapes (e.g. [96, 97]). Regarding wetland classification, Amani et al. [38] proposed a novel MCS to increase wetland classification accuracy using only SAR data in NL, Canada, in terms of both individual class and overall accuracies. The system initially removes poor classifiers and selects the best classification algorithm to identify each wetland class. Then, the final label is selected for each random pixel/object using the class label decision criteria introduced by the authors. The flowchart of the proposed MCS along with the corresponding criteria is illustrated in Figure 3. The proposed MCS outperformed the single classifiers and produced the highest producer and user accuracies for almost all wetland and non-wetland classes. It also increased the overall classification accuracy and kappa coefficient by 5–8 and 9–16%,

Wetlands are productive and diverse ecosystems providing numerous ecological services that are biologically important as well as playing a key role in surface water hydrology and flood risk. Wetlands are and have been threatened by land-use conversion, increased urbanization, industrial development, and climate change, resulting in more than half of the world's wetlands threatened, damaged, or destroyed. Earth observation provides a new cost-effective approach to mapping wetlands to aid in their management especially in remote and difficult to access regions. A combination of optical and SAR data provides adequate input data to use an object-based classification with machine learning algorithms such as Random Forest resulting in classification accuracies exceeding 90% for study sites in Newfoundland/Labrador. For more details on some of the information discussed in this chapter, please refer to our published papers [3, 26, 38, 40–42, 45–48, 50, 51, 61, 64, 68, 69, 98–100]. While [42] is a literature review paper on the use of interferometric synthetic aperture radar (InSAR) data for water level monitoring of wetlands, the rest mainly introduces new machine learning methods for wetland classification

This project was undertaken with the financial support of the Government of Canada, Federal Department of Environment and Climate Change, the Research and Development Corporation (RDC) of Government of Newfoundland and Labrador (now InnovateNL), and Natural Sciences and Engineering Research Council of Canada (NSERC) under Grant to B. Salehi (NSERC RGPIN-2015-05027). The SAR imagery was provided by the Canada Center for Mapping and Earth Observation and Environment and Climate Change Canada. Field data were collected by various organizations, including Ducks Unlimited Canada, Government of Newfoundland and Labrador Department of Environment and Conservation, and Nature Conservancy Canada. The authors thank these organizations for the generous financial supports and providing such

respectively.

5. Conclusion

using optical, SAR data, or the combination of both.

122 Wetlands Management - Assessing Risk and Sustainable Solutions

Acknowledgements

valuable datasets.

Thanks to Brian Huberty, U.S. Fish & Wildlife Service, National Wetland Inventory program for reviewing this chapter.
