Module 2- Photo Interpretation and Remote Sensing- LULC Classification and Ground Truthing

    This weeks lecture/lab focused on the USGS Land Use Land Cover Classification System and ground truthing. It was a very interesting, but time consuming project. I could have easily spent 3x as long on this lab as I did, maybe more, but the lab said to spend close to 4 hours which I had already gone over. Every time I looked at the picture more features stood out and I would use different context clues, parking lot size, surrounding buildings, etc. to try to figure out what I was looking at. I would have loved to have gone more into level 3 classification as there were some specific features I was able to pick out but that would have been beyond the scope of the project. Going into this program I had absolutely 0 exposure to GIS and it's been stunning to me how quickly the time goes and how much work goes into each project/map. It's made me stop and think when I'm just perusing the internet and stumble upon a map clearly made with GIS.

    After we created our classification data on an image of Pascagoula, MS, we created random sample points and use ground truthing via Google Maps to determine the accuracy of our maps. I wasn't surprised that out of 30 random points, my 2 errors were in the residential and commercial fields. These were the hardest to distinguish for me. There are obvious features that would be classified as commercial- business with large parking lots, and even schools and churches, but then there are those buildings that are smaller or used to be homes that were rezoned, or buildings surrounded by homes on all sides although they themselves are commercial that are confusing. Water, trees, and even industrial areas are a lot easier to identify. I feel like I got a good grasp on this classification system with this hands-on experience.

Map depicting LULC in Pascagoula, MS, and random sample areas used for ground truthing with accuracy.

Module 1- Photo Interpretation and Remote Sensing- Visual Interpretation

 This week was my first introduction to remote sensing and visual image interpretation. We got hands-on experience interpreting image elements from an aerial photograph. For the first map created, we were working with a black and white image to identify tone (on a scale ranging from very light to very dark) and texture (on a scale ranging from very fine to very coarse). I found myself second guessing my choices a lot trying to get it “perfect”. I definitely see how this part of remote sensing is more of an “art” than a "science".

                  Map deliverable 1 depicts a range of tone and textures visible on an aerial photograph

The second map was focused on using Shape/Size, Pattern, Shadow, and Association image elements to identify features in a photo. For some of the features I feel like I used multiple elements to come to my conclusions about the nature of the object I was viewing but I chose the element I felt best reflected my process.

Map 2 deliverable depicts several identified features categorized by which image element was used to identify them

Introduction to GIS- Final Project

If someone told me I spent 30 hours on this project I would not be surprised. I made a lot of mistakes but learned a lot. I really wanted to get it finish before my kids went on fall break so I spent up to 6 hours a day working on it to try to get it done in one week. It really was a little of everything that we learned throughout the semester. I think my biggest takeaways were:

    1. How to use StoryMaps. I wasn't sure if I'd use this method versus a PowerPoint. I really wanted to since I hadn't done it before and I'm all about learning new programs when I can. I found it very intuitive and easy to use.

2. Make ONE layer and use the field mode to differentiate. I knew how to do this. I don't know why but when I dove into the project I was a little overwhelmed and not quite sure what I was doing. I told myself "just take a tiny step forward, what is the first step you need to take" and that led to me trying to build a map of the conservation lands and wetlands within the corridor. I knew to use select by attributes and I just got a little click-happy with the "export features to new layer" button. I should have used the "set field to..." option under the field calculator more often to keep my layers together. I was drowning in map layers!

3. You can't perform a union on point data. There may be a workaround. But when I went to perform a union on a layer I made the above mistake with I got the notification that my features had to be polygons to run that tool.

4. The amount of things I can do with python are seemingly infinite. While trying to correct mistake #2, I discovered a youtube video that helped me reclass one of my layers using python after a union. There are so many options! Definitely looking forward to learning what other tools I have at my disposal with coding.

The link to my StoryMap is: StoryMap

I also created a transcript to go along with my StoryMap with significantly more detail: Transcript