Category: Retirement PhD Page 5 of 6

Long time since the last post. I am working madly on my PhD research. The above is the results of a machine learning predictor of stream flow calculated from images. I am amazed how much I enjoy this work. There is no money and not glory in it, but it is very interesting. The above is a machine learning prediction graph that will be part of our first journal article.

I have written quite a lot over the years and have even published a few journal articles. I am starting on what I believe is my first serious technical journal article. We have most of the research complete for the article and I have started putting things down on “paper.” One thing I can tell you about this is that it is not my favorite thing in the world to do. My plan is to do the minimal amount of writing necessary to finish the degree, then relegate myself to the fun stuff of writing machine vision and machine learning code. I hope to relegate my non-programming writing to emails, a letter or two and this blog. We will see how that works out.

Today, with the sun shining here in Washington state, it seems to be a good day to discuss my progress at University of Nebraska Lincoln on my retirement* PhD program in the School of Natural Resources. The short version of the story is that everything is going well. I work closely with my adviser, Dr. Troy Gilmore, on research for my dissertation–we talk almost every day. We have an academic poster in progress and have enough research results for at least one scholarly article. The more we talk about what we are doing, the more we believe we are onto something that will be of interest to a lot of people in the world of hydrology.

What we are doing is figuring out a way to measure the water level in images of streams and rivers when normally available data from the United States Geological Survey is available at the site where the images were captured. We have done a literature review and it appears no one has attempted what have already accomplished. That is a good thing. So, my non-retirement, retirement PhD proceeds ahead full bore. The plan is to finish our first pass at the research, publish a poster and a paper or two, then when I retire, take classes to catch me up on the highly technical aspects of Natural Resources Science and Hydrology about which I know absolutely nothing before finishing the writing of a thesis based on research we have pretty much completed (with a few small nooks and crannies we need to fill in).

*Scheduled to retire and go full time on the PhD within about two years if COVID-19 does not foul up our plans.

Next: #2 Extracting Metadata from Images

This is the second in a series of videos I am creating of the research I am performing under the direction of University of Nebraska Lincoln Professor Troy Gilmore to determine whether we can use images taken at the weir on North Platte River at the Nebraska-Wyoming State Line to replicate measurements of discharge and stage by extracting features from the images and using measurements from USGS sensors as ground truth.

My not yet official PhD adviser at University of Nebraska Lincoln is Troy Gilmore. We have been talking via video chat and trading lots of emails in anticipation of getting started after the first of the year. To get a jump on it before I start, Troy has provided me with images of a weir on North Platte River at the Nebraska-Wyoming State Line. He directed me to get started on the infrastructure needed to calculate features from the images that are well suited for use to build a classifier using a Machine Learning model. The first thing he believes we need is a tool to view the images, zoom in and out, load and save images and results, etc. This is the first pass at that. I am sure this application will evolve greatly by the time we are done, but this is our starting place.

We got up at 3:30 this morning and Lorena dropped me off at PDX to catch the 7 AM flight to Boston. Just another day in the commuter life. I found the JetBlue routes to Boston only run for five months per year so next month I will probably have to fly from Seattle which is generally way more hassle in terms of traffic. This trip, I am actually doing my first academic classwork for my PhD. Troy recommended I start with a book titled “Introduction to Open Channel Flow” by Glenn E. Moglen. I am just a few pages in, but it looks tractable but a little bit dry (no pun intended). I am going to see if I can work through the problems at the end of the chapter to keep a record of what I am doing.

I have not written for quite awhile, mostly because I did not have much that was interesting to say. Hopefully, that has changed although I think my topic is going to be only interesting to a small select group of people. That topic is the starting of a PhD that will almost certainly not be completed until after I retire in the next 4-5 years. I will list a few of the topics I hope to cover in this first post:

• My educational trajectory and how much or little of that applies to the PhD
• My career trajectory and how much or little that applies to the PhD
• How I got started on volunteer work that opened the PhD opportunity
• What I needed to do to get accepted into the PhD program
• My specific PhD program
• What I want to do with the PhD after I get it

I traded emails with my friend Troy today. We are making a plan to investigate a way to determine the toxicity of the water in agricultural settings by looking at satellite or drone images in a super secret way. It involves both imaging and knowledge of water chemistry. This is one idea we have for my doctoral research (if I actually to that). I am excited. Tomorrow I will write a couple of paragraphs for a proposal that explains my part of this work for a funding proposal that will allow us to gather data to do this. The whole retirement PhD thing continues to inch forward.