Piece of Eden GIS Blog

 This week we learned how to perform supervised and unsupervised classification on ERDAS Imagine. On the figure 1 map below, you can see my attempt at classifying land use/cover of Germantown, Maryland. This week my map falls short of the assignment goals, as I was not able to get ArcGIS pro to replicate the recoded feature classification outputs I performed in ERDAS. I am not sure what I did wrong, but in the future, I will make sure to analyze signature points more carefully via their histograms and mean plots to identify potential errors.  Figure 1: Supervised classification of Germantown, Maryland with a smaller distance map of the main feature map. 

 This week we learned how to utilize histograms and different bands to highlight different features in a map. On the following map that we worked on, dark bodies of water caused high peaks on the left of histograms while snow-peaked mountains were small blips on the far right. These simple distinctions help to quickly identify map features on a graph, that you can then utilize as a stepping stone to finding them on the image. I found it incredibly interesting how the different band layers highlighted different features on the map. Figure 1 below depicts three different features we found on the image.  Figure 1: Distinct features found on an image using ERDAS Imagine. Feature 1: Large body of water. Feature 2: Snow-capped mountains transitioning to thick vegetation. Feature 3: Shallow turbulent body of water near urbanized land, transitioning to deep calm body of water. 

 This week, we were introduced to the software ERDAS Imagine. We utilized this software to look at the limited information raster data can provide in an attribute table. Additionally, we cut out a section of the image and calculated the subset images' distinct areas in acres. The subsequent map can seen below in Figure 1. Lastly, we explored other features of ERDAS Imagine: learning where to find the metadata, spatial and radiometric resolution Figure 1: Distinct acreage of classified areas of forested area in Washington State.   

 This week in Aeriel Photography and Remote Sensing we gave land use and land cover distinctions for Pascagoula, Missouri. We also used 30 random points to determine the map accuracy via ground-truthing. Figure 1 below shows the land use and land cover categories, as well as truthing points. In the end, accuracy was only at 70%. This was highly due to the fact that I only used the snapping function in ArcGIS Pro for the last 1/3 of the map. Using this function for the entire digitizing process in the future will help reduce the small spaces between polygons that can be seen in the bay and residential areas. A majority of the error points were located in these undefined spaces.  Figure 1: Land Use, Land Cover, and Ground Truthing of Pascagoula, Missouri.