Interested in watching this video? You have two options:
This video is part of the SER Conference Library. If you want to learn more about this resource please see this guide.
You can purchase a pass for this video on our website.
Already purchased access to this video, or want to redeem credit for a new order? Just enter your order number or email below:
Sign in below to get unrestricted access:
Will Bartsch , Lucinda Johnson , Katya Kovalenko , Kristi Nixon , Steve Kloiber
Minnesota has lost about half of its wetlands to agricultural, commercial, and industrial development. No-net-loss laws and a recognition of the tremendous ecological value of wetlands have driven recent restoration efforts across the state. These efforts benefit from accurate identification of areas that are suitable for restoration. Field surveys, remote sensing, historical record review, and the development of GIS-based indexes are among the most common approaches of identifying suitable areas. Increases in the quality of environmental spatial data and computer processing capabilities have made possible the development of statistically-based indexes at fine resolutions across large geographical areas. We used Random Forest modeling to predict the likelihood of an area being a wetland or a restorable wetland across the state of Minnesota at a resolution of 3 meters. Fifteen predictive variables representing landscape position, topography, hydrology, ecology, and soil were assembled along with information on the wetland status of nearly 8,000 field-verified and 300 remote-verified sites. Out-of-bag testing during model development indicated that uplands were classified with an error rate of 12% and wetlands and restorable wetlands were classified with an error rate of 15%. Areas identified as existing wetlands in the updated Minnesota National Wetland Inventory were removed during post-processing. The resulting Restorable Wetland Index is the most comprehensive effort to date to identify restorable wetlands in Minnesota.
Conference Presentation, SER2021
Pre-approved for CECs under SER's CERP program