How a Student Used Machine Learning to Shed Light on North Country Wildlife
Leveraging her passion for the environment and curiosity for computer science, Laura Bolduc ’24 dug into a research project that helped her capture a new perspective on wildlife in the North Country.
Thanks to funding from the Clare Booth Luce Undergraduate Research Scholar Program, Laura spent eight weeks using computer programming to efficiently comb through thousands of images of North Country wildlife to accurately identify a variety of species.
A part of the program, which provides female students majoring in the physical sciences with on-campus housing and a stipend to travel with their faculty mentor to professional conferences to present their findings, Laura collaborated with Associate Professor of Math, Computer Science, and Statistics Lisa Torrey.
Laura’s work was made possible by a dataset that resulted from hundreds of hours of field and computer work conducted by Professor of Biology Erika Barthelmess and several of her students, including Donovan Spaulding ’19, Kate Andy ’20, Cole Weigartz ’21, Maggie Munschauer ’22, and Oliva Bernier ’24.
Laura shared what it was like to dig into machine learning for the first time.
Note: Responses have been edited for length.
Laura Bolduc ’24
Hometown: Gorham, Maine
Project Title: “Using Machine Learning to Identify Animal Presence and Species in Game Camera Images”
How would you describe your research to someone who doesn’t know anything about the topic?
Game cameras take thousands of images and are currently identified by volunteers in the community. This, as one can imagine, takes a lot of time. My research helps quickly sort through thousands of game camera images and identify if there's an animal present in the image and what species of animal it is. I am able to do this using machine learning, which looks for patterns in the images that help it to differentiate between species.
What about this topic sparked your curiosity?
As an environmental studies and computer science major, this project combined both of my interests and also allowed me to gain a lot of experience with machine learning.
Was there a moment when you felt particularly challenged during your research process? How did you overcome it?
There were a couple of times when I felt like I wouldn't be able to finish my project. I have yet to take a machine learning course and because of this, I had almost no knowledge of how machine learning worked or how to apply it to my project. This was very discouraging at first, but I was able to overcome it by working closely with my advisor, Lisa Torrey, and researching a lot.
What about your research are you the most proud?
Everything I've learned. At the beginning of the summer, I knew nothing about machine learning, how I was going to use it, or how to attempt this project. At first, I thought I was just going to be adding to past research done by a SLU graduate, Corinna Pilcher ’21, but I was able to come up with new ways to make her work more advanced and add some ideas of my own.
What's the most rewarding aspect of working closely with a faculty member?
Gaining some of Lisa’s knowledge of machine learning one-on-one. She teaches the machine learning class that I hope to take in the future but this summer I've been lucky enough to learn some of it one-on-one with her, which has been extremely fun and rewarding.
Finish this sentence: “Through my research, I hope to show others that…
You can do research on anything you can dream of, even if you don't know much about it when you're beginning. This project was a learning experience and having different setbacks have led my research in different directions, but I've also learned more than I ever imagined.