GIS 4930 - Mountain Top Removal - Analyze Week - Unsupervised Classification

This week an analysis of LandSat imagery from 2010 within the study area was performed. After inspecting a raster from 2005 and a shapefile associated with it that showed mountain top removal from that time period, an unsupervised classification was performed on the 2010 imagery. With the previous data as a guide, classes were then designated as either MTR (areas where mountain top removal occurred) or non MTR. A new raster was then generated from this that only showed the MTR areas. The screen shot below shows the result, which will be integrated with reclassifications from classmates on my team as this project continues.

Screenshot showing reclassified raster image

GIS 4930 - Project 02: Addressing Mountain Top Removal (Hydrology & Remote Sensing)

Preparation

This week sees the beginning of a new project, the creation of a story map that shares information on the landscape footprint of an extreme coal mining practice - Mountain Top Removal.

In addition to the description of the practice shared above, we will be performing analyses of the how a regions hydrology and topography is impacted by this kind of mining. Preparations for this week included generation of hydrological rasters and shapefiles from an assigned study area (see below) and setting up a placeholder site for a story map that will be used to share the analysis once it is complete.

Preparatory Base Map for MTR Analysis in the Appalachians

GIS 4930 - Creation of Route Maps

This week saw the creation of a lot of maps, each with a specific audience in mind and intended to describe routes for those audiences.

One of the maps below is an inset map from a larger document showing a basic route from a hospital expected to be inundated by an oncoming storm to one on higher ground. The second map shows a driving route for emergency services personnel delivering supplies from the National Guard armory to one of the emergency shelters set up throughout the city of Tampa.

Route to St. Joeseph's Hospital

Route from National Guard Armory to Tampa Bay Blvd Elementary School (temporary emergency shelter)

GIS 4930 - GIS Network Analyst Route Generation

This week I took the road network I generated last week and created routes for the ostensible emergency hurricane situation in Tampa that's the conceit of this current mapping project. Routes were generated to evacuate a hospital, to direct national guard troops from the local armory to evacuation shelters to deliver emergency supplies, to show routes out of downtown to an evacuation center and a set of polygons was generated that shows residents which evacuation center is closest from their location.

All of these routes are shown on the map below, which makes things quite busy. Next week routes will each be featured individually on maps generated with a specific target audience in mind.

Tampa Metro Area Basic Evacuation & Emergency Services Routes

GIS 4930 - Network Analyst Data Preparation

This is the first installment of a multi-week project. The conceit of the project is that optimal evacuation routes need to be generated for the Tampa, Florida metro area just days ahead of an expected hurricane. These routes will then be produced in maps for use by both the general public and by emergency personnel. This week's was creating the base map from which a network dataset will be generated that will be used to generate routes in upcoming weeks. This involved prepping feature datasets for that upcoming work and also generating a basic map that shows the location of emergency services and also the expected flood zone of the area. This prep also included creating attributes in feature datasets that will be used for generating a network dataset.

Basic Map of 5 foot flood zone for Tampa, Florida metro area

GIS 4035 - Module 10: Supervised Classification for Thematic Mapping

This week focused on creating thematic maps via supervised classification. This involves indicating portions of a raster as training areas to feed to an algorithm. The training areas may be based on previously conducted ground survey, on interpretation of the rasters to be classified or by signature files created by experts and/or expert systems. In any case, the spectral information of the training areas is then used as a guide to classifying the rest of a raster image set, relying primarily on a comparison of multiple spectral bands to interpret their euclidean spectral distance. This later phrase refers to plotting out values of a raster pixel location on two or more bands and assessing how various pixels are grouped.

The map below was created by creating polygons based on spectral 'seeds' grown from a single pixel chosen from various locations on a raster set representing Germantown, MD. The seeds were expanded to polygons with a limited spectral variation from the initial pixel. Multiple locations were chosen for most of the classifications shown on the map, which were then merged after the classification was created using a Maximum Likelihood algorithm (using Bayesian methods to assess each pixels most likely classification). The spectral distance inset map shows the locations that were furthest, spectrally, from one of the classification classes, represented by the bright areas. The brightest areas tended to be fallow fields, which were deemed to have been correctly classified despite the indication of the distance map.

Thematic Map of Germantown, MD

GIS 4035 - Module 09: Unsupervised Image Classification

This week we dealt with unsupervised image classification. This is the process of using an algorithm to differentiate raster image pixels (often across and comparing multiple bands of an image set) in order to create classifications that produce (It is hoped) classifications of pixels that reflect actual ground features. The identification of groupings (and adjustment of classifications) are done after the classification is processed. This stands in contrast with supervised classification where an algorithmically based system is trained before classification by receiving input on areas across the image space that are grouped together into classifications.

The map below was produced by running an unsupervised classification on an orthophotograph of UWF's main campus. The initial classification was set to produce 50 classes. Once those were created, they were each identified as belonging to one of five very simple classes: Trees, grass, building/road, shadow or mixed. The mixed class was reserved for classes that were ambiguous as to their proper identification - encompassing a mix of grass and road. Once all the classes were identified, the classes were collapsed to encompass just those five and the map was created.

UWF Campus Thematic Raster Map