This dataset contains the materials necessary to reproduce the study submitted to Remote Sensing: "Tradeoffs Between UAS Spatial Resolution and Accuracy for Deep Learning Semantic Segmentation Applied to Wetland Vegetation Species Mapping". This includes the raw imagery output from the camera aboard the unoccupied aerial vehicle, the Red-Edge MX, captured over the Howard Slough Waterfowl Management Area, Utah, in August of 2020, resampled images, code to resample the images, a link to ground reference data, and the training and testing data used for the convolutional neural network in the study.

Last modified

• 12/05/2023

Creator

• Saltiel, Troy M.
• Campbell, Michael J.
• Thompson, Thomas R.
• Hambrecht, Keith R.
• Dennison, Philip E.

Contributors

• Christian Hardwick (Utah Geological Survey)

Subject

• geography

Language

• English

Identifier

• https://doi.org/10.7278/S50d-h9z0-5ft8

Keyword

• invasive species
• wetlands
• phragmites australis
• Howard Slough Waterfowl Management Area
• multispectral imagery
• remote sensing
• uncrewed aerial systems

Date created

• 2020-08-11

Location

• Howard Slough Waterfowl Management Area, Utah, United States

Resource type

• Dataset

Source

• Library of Congress Subject Headings (LCSH)

License

• CC BY NC - Allows others to use and share your data non-commercially and with attribution.