About the Project
This transfer project addressed a need identified by the St. Louis River Habitat Workgroup to support the identification and prioritization of areas for future restoration and conservation. The multi-phase project approach included the transfer of a repeatable habitat mapping process developed by the Lake Superior Reserve to a larger area encompassing 57,000 acres of wetlands and adjacent uplands spanning the lower twenty-one miles of the St. Louis River below the Fond du Lac dam. The team applied accessible image classification methods–including use of common machine learning classifiers and freely available, non-proprietary data–to create a reproducible approach that can easily be adopted in other locations and redeployed at regular intervals to illuminate change over time.
About this Resource
This project generated three datasets, including NAIP imagery mosaic of the study area, ground-truthed field data, and drone imagery in addition to the final habitat map. The dataset description provides more information about each dataset.
NAIP imagery, training polygons and classified land cover map
The imagery source for the habitat map is the National Agriculture Imagery Program (NAIP). A summer mosaic of NAIP images was created for the study area. Training polygons were produced by visual interpretation of the NAIP imagery. The final land cover map was produced with a machine learning algorithm called UNET. Data have been archived in a public AWS S3 bucket, managed by the University of Minnesota and can be downloaded directly from the links provided in the dataset description document.
Post-processing GIS layers, field data, final habitat map, and change map
This dataset is an Esri geodatabase containing feature classes used in the post-processing of the UNET land cover map to produce the final habitat map and change map. Available on GeoData@Wisconsin.
Drone Imagery
Hi-resolution multi-spectral imagery of selected areas within the St Louis River Estuary. Available on GeoData@Wisconsin.
Questions about these datasets can be directed to:
Howard Veregin, Wisconsin State Cartographer's Office, University of Wisconsin, [email protected]