**7. Conclusions**

Wetland habitat characteristics, including wetland surface water area and vegetation presence, are essential for estimating waterfowl populations. The PPR contains millions of small wetlands providing abundant and critical habitats for waterfowl in North America. Mapping wetlands is needed to set conservation targets and develop management plans for waterfowl in the PPR. However, remote-sensing-based mapping of wetlands has previously been challenging. Many small wetlands in the region were missed by existing remote-sensing-derived surface water inventories due to limitations in the spatial resolution of remote sensing products. The trade-off between spectral and spatial resolution of remote sensing products necessitates the use of complementary data for wetland detection methods. Limiting the input parameters to the high-resolution bands of S2 helps detect smaller wetlands; however, it will ignore the spectral information of the other bands. Given its high resolution and ability to detect surface water, SAR can provide additional spectral information when combined with S2. The pre-processing of the original S1 and S2 images, and performing classification methods need massive computation. The GEE Cloud-based platform hosts many open access remote sensing images that provide remote analysis to apply machine learning algorithms for environmental monitoring. This study will share the resulting algorithm, which is tailored towards the needs of waterfowl conservation managers, with the management community, allowing its use for setting future conservation targets. These efforts will help conservation managers improve local estimates of pair abundance and waterfowl populations' distribution patterns in the study area, and similar settings elsewhere.

**Author Contributions:** Conceptualization, H.S. and J.O.; Data curation, H.S. and K.M.K.; Formal analysis, H.S. and J.O.; Funding acquisition, J.O. and K.M.K.; Methodology, H.S. and J.O.; Software, H.S. and J.O.; Supervision, J.O.; Writing—original draft, H.S., J.O. and K.M.K.; Writing—review & editing, H.S., J.O. and K.M.K. All authors have read and agreed to the published version of the manuscript.

**Funding:** Ducks Unlimited, Inc and the United States Fish and Wildlife Service funded this project through the Prairie Pothole Joint Venture. The United States Fish and Wildlife Service Habitat and Population Evaluation Team provided ground truth data for surface water models.

**Conflicts of Interest:** The authors declare no conflict of interest.
