Lab Two, Pixel-based supervised classification

Background and Goal:

    The mail goal of this lab was to gain experience in extracting LC/LU (Land use/ Land Cover) information from remotely sensed images using pixel-based supervised classification. Another goal was to understand how to select and properly add training data to a supervised classification.

Methods:

    Simply put, the method used was to get straining samples, combine into their separate classifications, and then run the supervised classification. 

    As for a more detailed method, we collected 12 water training samples, 11 first, 10 agriculture, 5 for urban areas, and 12 for areas of bare soil. These samples were then viewed on the mean data plot windows, and outliers were removed and replaced. Below is the mean plot of all of the signatures used for this exercise.

Signature mean plot used for this exercise

    From there a separability report was ran, with the results below.

Separability report

     These signatures were then consolidated, and the classification was ran.

Results:

    The result of this lab is the below  LC/LU map of Eau Claire, WI. and the surrounding areas.  

LC/LU map of Eau Claire Area

Sources:

Earth Resources Observation and Science Center. (2014).[Landsat image of Eau Claire                                         and surrounding areas]. United States Geological Survey.  Provided by Cyril Wilson.