Remote Sensing - Module 5 - Unsupervised & Supervised Classification

This week's lab module for GIS 5027L Remote Sensing and Photo Interpretation focused on supervised vs unsupervised classification of images in ERDAS Imagine. The module introduced us to several tools such as swipe, flicker, and blend and concepts such as Spectral Euclidean Distance, Neighborhood, and Spectral Confusion. Some of the outcomes from completing this module included manually reclassifying and recoding images to simplify data, creating spectral signatures and AOI features, and recognizing and eliminating spectral confusion between spectral signatures.

The module began with a unsupervised classification exercise of an aerial photograph of the UWF campus. We learned various tools that help complete the process and learned about reclassification and how to merge classes by recoding. This part of the exercise ended with calculating the difference in surface types that occur in the image.

The second part of the module was an exercise in supervised classification which was much more in depth than the unsupervised classification exercise. Supervised classification involves Signature Collection where the user creates class type inputs, which are used to "train" the classifier to recognize features with different spectral characteristics. The user then evaluates the signatures to ensure that they accurately represent unique land covers leading to the most accurate classification. This is done by examining things such as histogram plots and mean plots looking for evidence of spectral confusion and spectral separation. After creating the supervised and distance images it is necessary to compare them to see if you notice any errors. To finish we merged all like classes and added an area column to calculate the area of the final classes.

In the final exercise in the module, we were tasked with creating a supervised classification of Germantown, Maryland.  In this exercise we employed all of the concepts that we learned throughout the lab module to create the final deliverable. According to the governor's office, over the past 30 years, Maryland's population has increased by 30 percent while land consumption has increased by 100 percent. The map below is a current land use map for the area in response to the Maryland governor's desire to work toward Maryland's "Smart, Green, and growing Initiative".

Remote Sensing - Module 4 - Spatial Enhancement & Multispectral Data Analysis

This week's lab module for Remote Sensing and Photo Interpretation introduced us to a wealth of information related to image enhancements and multispectral data analysis. This involved topics ranging from image enhancements in ERDAS and ArcGIS Pro to interpreting histograms and additional forms of digital data used to identify features. In the final exercise, we were provided criteria that were used to identify three different features. We employed the four main methods we had learned to identify these three features. The four main methods were as follows: 

1. Examine the histogram data for shapes and patterns in the data. 

2. Visually examine the image in grayscale for light and dark shapes and patterns. 

3. Visually examine the image with multispectral band combinations to isolate features of interest.

4. Use the Inquire Cursor to validate the exact brightness value of a feature.

Once we had identified our features according to the specified criteria we used the Create Subset Tool in ERDAS to extract an area around the feature allowing us to then export this subset into ArcGIS Pro to create a map layout. 

The first map below displays water features that were identified by a spike in band/layer 4 pixel values of 12-18. I decided to use the False Color IR as my band combination as it creates a sharp contrast between the water and vegetation.

The criteria for the second feature included a small spike in layers 1-4 around pixel value 200 and a large spike between pixel values 9 and 11 in layers 5 and 6. I looked at layers 1-4 using the panchromatic image to see the brightest areas. I proceeded to do the same for layers 5 and 6 to see what areas appeared darkest since pixel values between 9 and 11 would be very dark. After consulting the histograms and using the Inquire Cursor, I confirmed that the snow and ice features fit the criteria. I chose the False Natural Color as my band combination which displays the snow and ice in a light blue teal color.

The third and final criterion was to locate an example area that shows variations in water using a band combination that makes them stand out. Evidenced by layers 1-3 becoming much brighter than normal, layer 4 becoming somewhat brighter, and layers 5 and 6 remaining the same I identified the areas in the map below using a custom band combination displaying shallow and deep water.

Remote Sensing - Module 3 - Intro to ERDAS Imagine and Digital Data

The third lab for Remote Sensing and Photo Interpretation introduced us to ERDAS Imagine. This included familiarization with the layout of the workspace and the use of some of its basic tools and functions.  We began by learning how to properly add raster layers to the Viewer. We continued with an exercise adding both AVHRR (Advanced Very High Resolution Radiometer) imagery as well as Landsat Thematic Mapper (TM) imagery. This involved comparing the difference in spatial resolution between the two types. Using the Landsat image we changed the band combinations observing the differences between the different combinations such as False Natural Color vs False Color IR. It was very interesting to observe the visibility differences between the two. We concluded part A of the lab by creating a subset image of our original and added an area column in order to calculate the area of thematic classifications represented in our new subset image. We then opened our new subset image in ArcGIS Pro and created a map as seen below.

In part B of the lab we began by learning how to examine layer metadata through the Layer Info feature which contains important information about the image, including number of layers, file, image and pixel size, projection information and statistical information. Next was an exercise focusing on spatial resolution where we compared some images that depicted the same area on the ground but their level of detail varied. Next was a similar exercise about Radiometric Resolution and then we finished with an exercise with Thematic Rasters and Attributes. This involved calculating area and generating a formula statement in order to meet certain criteria.

Remote Sensing - Module 2 - Land Use/Land Cover and Ground Cover

The focus of our second lab module for GIS5027L Photo Interpretation and Remote Sensing was the USGS Land Use/Land Cover Classification System. We learned in our textbook and lecture material that there are four levels in the classification hierarchy with each level increasing in detail leading to a need for increased spatial and spectral resolution. To be able to successfully assign classification codes to features on our photo we used the skills we learned in module 1 where we learned about visual interpretation of aerial imagery. In this exercise, we were only required to classify up to Level II Classification.

In the first exercise, we created a LULC feature class that consisted of the polygons that we created according to the features we identified in the photograph. The map needed to be 100% covered. I found that as I progressed in the exercise I began to see more and more features that I previously had overlooked especially many that would have been Level III classification. It became borderline frustrating but overall it was a great way to learn new techniques that I otherwise would be unaware of. I would have liked to classify to higher levels but time really began to fly as I believe I put in at least 7-8 by the end this exercise.

In the second portion of the lab we did a ground truthing exercise using Google Maps. I created a feature class that covered the mainland portion of the photograph and then used the create a random point tool to drop sample points on the map. We used Google Maps to determine the accuracy of our classifications by using the aerial imagery as well as the Google Maps Street View (GMSV). In most cases this allowed me to determine if my classification choices were true or false. Overall, this was a great hands on exercise for general land use and land cover that provided me with a solid understanding of the USGS Land Use/Land Cover Classification System.

LULC map of Pascagoula, MS with random ground truthing sample points.

Remote Sensing - Module 1 - Visual Interpretation

In our first lab assignment for GIS5027/L Photo Interpretation and Remote Sensing, we were introduced to interpreting the tone and texture of aerial photographs and identifying land features based on various visual attributes such as shape and size, shadows, pattern, associating, and color. 

The first exercise focused on tone and texture. This involved creating polygon feature classes focused on light vs dark areas and areas that exemplified ranges of texture. Being that I was a student of art in both high school and college as well as being an amateur photographer, much of the vocabulary as well as the overall concepts introduced were familiar to me. Even so, I never thought of these concepts as applied to aerial photography and even found myself second guessing my choices as I completed this exercise. Initially, I did not have the course textbook Remote Sensing of the Environment - An Earth Resource Perspective - An Earth Perspective, so after I read the corresponding chapter I made a few changes to my initial choices but overall I was on the right track.

The second exercise included creating point feature classes for identifying features based on shape and size, shadow, pattern, and association. I really found this exercise to be interesting because I've never really taken into consideration identifying features in aerial photography using these criteria. I especially found considering shadows to be of great benefit as some features were a mystery to me until I considered their shadows to analyze them. Since I initially did not have access to the text for this exercise also, I revisited it after reading the corresponding chapter. The text really provided some imperative information that was very helpful in completing the exercise. 

In the final portion of the lab, we did an exercise based on interpreting color. We chose five features from a true-color aerial photo and compared the features with how they appear in a false-color infrared version of the photo. Take a look at the aerial images below. Pick out some features and compare the differences between the two. 

True Color

False Color Infrared

Intro to GIS - Final Project - FPL Bobwhite-Manatee Transmission Line Project

Our final project task was the analysis of a transmission line corridor proposed by Florida Power and Light (FPL) in Manatee and Sarasota Counties. This project was called the Bobwhite-Manatee project.

After data analysis was conducted and public input considered, a proposed route corridor was identified for the project. What is never mentioned is the fact that GIS played an important role in making decisions concerning the the proposed line placement. The use of GIS enables projects like this to be executed confidently ensuring the required standards and objectives are considered.

Our project analysis consisted of four objectives that could be achieved using the GIS tools that we learned throughout the course. These four objectives were:

Objective #1: Define and quantify the environmentally sensitive lands imposed by the transmission line.

Objective #2: Quantify homes within proximity of the transmission line.

Objective #3: Define schools within proximity of the transmission line.

Objective #4: Quantify length and cost of the transmission line.

 

To view my Power Point presentation click here.

To view a transcript of the presentation click here.

 

 

Intro to GIS - Module 6 - Georeferencing, Editing, & 3D

 

This week's lab module focused on georeferencing, editing, and 3D. In the initial portion, we were introduced to the georeferencing process which involved taking two aerial photos of the University of West Florida campus and georeferencing them to a raster base map within ArcGIS Pro. This involved identifying and creating "control points". Features such as street corners or building corners were then chosen identifying common points on the unknown/unreferenced layer with the known/referenced layer. The goal is to get as close as possible with your control points which then moves the unreferenced raster layer in line with the control points on the known/referenced raster layer. As we established our control points we were mindful to inspect the Control Point Table so that our RMS error was as low as possible (below 15). 

Second, we used the skills we learned by georeferencing the aerial photos to georeference a survey drawing document for the UWF Heritage Hall building. I found that getting the initial control points for the image was a little more challenging than the previous aerial photographs. However, after establishing a few points it went smoothly. The biggest difference that I would note is that due to the smaller size of the survey drawing there were fewer features to establish control points on.

After completing the georeferencing portion we created two new features. The first was a new polygon feature for the UWF Gymnasium and then a new line feature for Campus Lane. After creating the new features we used the Multiple Ring Buffer tool to create a conservation easement for an eagle's nest located on campus property so that expansion efforts would not disturb it. Using the Multiple Ring Buffer tool we created a 330 ft and 660 ft conservation buffer around the eagle's nest. The above map depicts the features described.

In the final portion of the lab module, we created a 3D scene which can be viewed in the above map. This process involved converting our UWF_Lidar.lasd to a DEM (digital elevation model) raster using the LAS dataset to raster tool. We then added some of our previous feature layers adjusting our Buildings layer to max height for a 3D effect. Although I was running short on time I believe I covered most if not all the requirements.

Intro to GIS - Module 5 - XY Point Data and Geocoding

 

The first portion of this week's lab module focused on converting lat/long Degrees, Minutes, Seconds coordinates to Decimal Degrees in order to be better compatible with ArcGIS Pro. This consisted of using an Excel spreadsheet to convert the data and add the data to ArcGIS Pro displaying three known eagle's nests in Santa Rosa County, Florida. Additionally, we projected the data to the Harn State Plane Florida West coordinate system.

The second portion of this lab consisted of obtaining school addresses in Manatee County and preparing them in an Excel spreadsheet for geocoding in ArcGIS Pro. This exercise involved copying data from the Florida Department of Education website and pasting it into an Excel spreadsheet. From here the data needed to be "cleaned up" or parsed into fields including school name, address, city, zip, phone, and the type of institution (high school, university, etc.) After our data was properly parsed in our Excel spreadsheet it was now ready to be geocoded in ArcGIS Pro. Prior to importing our Excel CSV file we downloaded and added some US County and Manatee County road shapefiles from the US Census Bureau website to ArcGIS Pro. The shapefiles were then projected to the Harn State Plane Florida West coordinate system. Using the Select By Attributes tool we created two new feature classes consisting of only Florida counties and Manatee County.

Finally, we added our school location data from our Excel spreadsheet, set up an address locator, and ran our geocoder to geocode all our addresses. I ended up with 5 unmatched addresses. I had to manually look these five locations up using Google/Google Maps and use the "Pick from the Map" tool to place new points. The above screenshot from my ArcGIS Online web map shows my final geocoded map. This map presents various types of schools that exist within Manatee County (with one exception). To view my web map in ArcGIS Online click here.

Intro to GIS - Module 4 - Vector Analysis

This map is the product of the fourth lab module for GIS5050. The main objective of this week's lab exercises was to stress the importance of GIS as an analytical tool and describe the process of how a successful GIS analysis is carried out. The exercises helped to solidify our understanding of numerous GIS analytical concepts and the vocabulary that accompanies them. We then put these concepts into practice through our two lab exercises.

In our initial exercise we learned what a geodatabase is, their attributes, and their purposes followed by looking at key differences between shapefiles and feature classes. The remainder of the first exercise focused on geodatabases and running various queries in order to select desired features. These concepts were carried over and built upon in exercise two.

In exercise two we used various GIS analysis tools to identify suitable camp sites in the De Soto National Forest near Hattiesburg, Mississippi. Our criteria consisted of a specific distance from roads, rivers, lakes, and areas that are not within conservation areas. In order to achieve our objective we used various buffer and overlay tools to get our desired result.

I began creating my map by defining my symbology. I decided that 5 classes seemed to work well and tried to create my intervals with somewhat of an even distribution. I then chose my color scheme which consisted of a set of earthy tones ranging from a light cream beige representing smaller areas to a dark orange/red representing the largest areas. After this, I began creating my layout. I started by establishing my main map frame with the possible campsites map then moved to the inset map. I was able to utilize some data that I found on the MARIS website to use for my inset.  I ran into a little bit of a problem trying to find some data to represent the De Soto National Forest but was able to add two tile packages from ArcGIS Online that worked well. Next, I labeled the roads because I thought it would be imperative for them to be on the map for somebody who was going to use it. I ended by creating my legend and arranging the remainder of the elements to make the map as visually pleasing as possible. Overall, I spent a great deal of time on this lab, but through spending the extra time I was able to better understand the key concepts presented.

Intro to GIS - Module 3 - Data Collections and Map Projections.

 

The third lab module for GIS5050L consisted of two separate exercises. The first portion of the lab consisted of using ArcGIS Field Maps to collect data for our feature class. This feature class was then shared as an editable layer to create a web map in ArcGIS Online. We also learned to share our data as a KML and an ESRI Map Package. The image above shows the data presented in Google Earth by importing the KML files I created through ArcGIS Online and ArcGIS Pro. I enjoyed this exercise because it introduced me to the various limitations and characteristics of the available map outputs that I have been curious about applying to some of my historic preservation/archeological projects.

The second portion of this week's lab consisted of creating a map comparing three different projections with the same data. This exercise introduced us to the Project Tool so that we are now familiar with changing a layer's projection or, rather, creating a new reprojected layer. We also learned how to assign or reproject a raster to ensure it is in the correct coordinate system. This then establishes the correct location for the raster.  Based on the results, it is very apparent that consistent map projections are imperative for accurate data/spatial analysis. I liked how this assignment built on last week's by giving us even more of a chance to make our map our own. I'm looking forward to the concepts introduced in this lab becoming more familiar and clear in the coming weeks.

Intro to GIS - Module 2 - Cartography: Layout and Essential Map Elements

 

This map is the product of the second lab module for GIS5050L. This week's lab was more challenging and time-consuming than our introductory module. This week's module focused on how to create a map layout and add the essential map elements in order to create a professionally looking map that presents accurate data and is aesthetically pleasing to the viewer.

Before we began creating our map, we had to fill out our metadata table to ensure we knew how to document and find our metadata, especially if it is not readily available in the catalog pane. After this, we began the process of creating our two maps from our six shapefiles consisting of an inset map showing Escambia County in an overview of Florida followed by our more detailed map of Escambia County showing the location of the UWF campus.

Once we created our map frames for our layout it was time to add our shapefiles to the UWF Campus Location Map View and clip our data to create new layers that feature only the data we wanted for Escambia County. Next, for the cities we wanted displayed we executed a definition query followed by creating an expression that resulted in a new feature layer containing only the cities of Pensacola and Ferry Pass. In the final sections, we learned about editing symbology, choosing colors, labeling, and adding essential map elements such as titles, a legend, a north arrow, scale bars, data sources, and the cartographer's name.

Overall, I enjoyed this module even though it took me a long time to complete. I am happy with my finished product, but I think I could benefit from revisiting some sections to solidify my understanding of the content.

 

Intro to GIS - Module 1 - Overview of ArcGIS Pro - World Map

 

This map is the product of the first lab module for GIS5050L. The first objective of this lab was to demonstrate one’s efficiency of accessing and moving data within ArgoApps. Next was an exercise introducing the basics of ArcGIS Pro resulting in a world country population map represented in a continuous color scale.  In addition to displaying population by country, 2,539 major cities are represented by black point symbols. I did run into an issue where my layout was slightly zoomed in therefore resulting in eastern Russia and western Alaska being cut off from view. I was able to correct this by clicking on the “full extent” button located in the Map group while under the Layout tab.

To conclude, we exported our final map as a JPEG and were asked to define some basic terminology pertaining to ArcGIS Pro. It has been nearly 15 years since I used ArcMap so luckily, I did not have to relearn anything.

Overall, since I have a had a little bit of experience with ArcGIS Pro over the past six months this lab was fairly easy for me to follow and complete. I did have a few confused moments while creating my folders in ArgoApps, but I believe at this point I have them correct. I am looking forward to the next module and building on what I have learned in this one.