Lauren Chaphe's Geographic Information Science (GIS) Portfolio

  Supervised classification involves manually choosing representative areas ("signatures") in order to tell the program to classify all areas with similar pixel values to the same class. Unsupervised classification is the opposite, in that the program sorts through and assigns a set number of categories based on pixel values. After this, the categories are grouped manually. For this map of Germantown, Maryland, the categories were determined via supervised classification methods from a image with a band combo of 5, 4, 3 (Red, Green, Blue). This band combo was chosen because it differentiated the vegetation from the urban or fallow areas by including the Near Infrared band (Band 5), which is reflected by healthy vegetation and shows as red areas in the image. Using this image, signature areas were chosen for each of the 8 categories of land use, such as the lake, urban areas, and deciduous forested areas. The image was then classified based on these chosen signatures and the n...

 This week's lab continued with ERDAS Imagine to add various filters to raster imagery data, as well as editing the band color combinations. Available filters that can be applied include high pass, low pass, mean, range, etc. Each filter produces different variation to the photo and can be useful to highlight certain features in an image. For example, the high pass filter created a photo with more detail and more defined edges, while the low pass filter created an image with softer, smoother edges. Band combinations can also be changed. For the images above, we were given clues on what pixel values to look for when identifying an unknown feature. The first feature was a river with had pixel values between 12 and 18 on layer 4 and I chose to use a band combo of 4, 2, 1 which made the forested areas appear red and the water appear black. The second feature was the snow capped mountains. A band combo of 5, 4, 3 showed the snow as bright blue and the forested areas as a bright green. T...

  This week focused on the the introduction of a new digital image processing software, ERDAS Imagine. The goal was to take a raster dataset and process the data so that it could be uploaded to ArcGIS Pro and to learn the basic tools for ERDAS Imagine.  An Advanced Very High Resolution Radiometer (AVHRR) image was used to create a multispectral land cover image of a mountain range within Washington State. Using the newly introduced tools and menus within ERDAS Imagine, this image was processed to show pseudo color thematic symbology, or when each land cover class is assigned a different color. The attribute table was also modified to calculate the area of each land cover class. Then, a subset image was chosen from the original image. I chose this particular area of the image because of its visible mountain ridges and valleys, seen as the different colored NW vegetation and the SE vegetation layers. In addition, water or riparian areas are also clearly visible running in the va...