Michell's GIS Journey

  In this lab, I created a supervised land-use classification of Germantown, Maryland, to visualize current land-cover patterns and support sustainable planning. Maryland’s population has grown 30% over the last 30 years, while land consumption has doubled, making it critical to understand how urban and green spaces have changed. I used the dataset and selected a band combination that minimized spectral confusion between classes. Using histograms and mean plots, I created and refined spectral signatures for urban areas, roads, water, grass, deciduous and mixed forests, fallow fields, and agriculture. Adjusting parameters like Spectral Euclidean Distance and Neighborhood helped ensure each signature accurately represented its feature. The final map, recoded into eight classes, includes the classified image, a distance file inset, a legend with colors, class names, and areas, plus essential map elements. This project provided hands-on experience in creating accurate, meaningful land-...

  This map highlights a mountain peak located in the northwest section of the study area. The feature was identified by a small spike in layers 1–4 around pixel value 200 and a large spike in layers 5–6 between pixel values 9–11. To make the summit visually distinct, a false-color band combination emphasizing  Layers 5 and 6 was applied, which clearly contrasts the rocky peak from surrounding vegetated slopes and shadowed areas. Using the histogram and the inquire tool helped confirm the spectral characteristics and locate the feature accurately. This visualization provides a clear representation of terrain variability and the spectral differences between rocky and vegetated areas in the study site.

This week, I worked with a classified land cover image in ERDAS IMAGINE to explore how land cover types can be analyzed and mapped. I began by opening the file and examining its attribute table. To better understand the extent of each land cover type, I added a new Area field to the table, which allowed me to calculate the area each classification occupies in the image. After saving the updated layer, I used the Inquire Box tool to select a smaller region of interest within the image. I then exported this selected area as a new image. Once the new image was created, I added a new Area field again to ensure the area values reflected only the smaller region. I then moved to ArcGIS Pro to begin the map-making process. I added tm_subset.img to a new map, adjusted the symbology, and edited the class labels so that each land cover class displayed both its name and the amount of area it occupies. After setting up a layout with a title, legend, north arrow, scale bar, and my name, I exported t...

  This week’s assignment focused on learning how to classify land use and land cover (LULC) from high-resolution satellite imagery and then evaluate how accurate those classifications were. We worked with an aerial image of Pascagoula, Mississippi, and created our own data by digitizing different land use types. First, I created a new polygon feature class and digitized different land cover areas by identifying patterns of tone, texture, shape, and association. I assigned each polygon a Level II LULC code and a short description. My final categories included residential (11) , commercial and services (12) , deciduous forest (41) , forested wetlands (61) , non-forested wetlands (62) , lakes (52) , streams and canals (51) , and bays and estuaries (54) . Learning to recognize these features based on visual cues made me more aware of how land use reflects both natural environments and human activity. Next, I conducted a ground truth accuracy assessment . I created 30 sample points arou...