Ant Wars: Ant Tracking with Machine Learning + Computer Vision

Ants are among the most abundant organisms on earth, with a recent estimate placing their number around 20 quadrillion individuals and their biomass around 20% of human biomass. They play key roles in ecosystems around the world, contributing to seed dispersal, soil aeration and nutrient cycling. However, invasive ants such as the Argentine Ant are giving a bad rap to ants in general by invading people's homes and also causing major crop damage. Worse, such invasive ants often create cooperative super-colonies that spread over hundreds of miles, driving out native ant species within their range. Despite well-established evidence that Argentine ants drive out native harvester ants across California, here at our Bernard Field Station Argentine ants and native harvester ants seem to be coexisting, even though frequent interactions have been observed. What allows this population of harvester ants to resist Argentine ant invasion? 

To explore this question, we have been documenting the daily rhythm of harvester ant activity around the nest using field cameras programmed to take short videos throughout the day. To gather useful data from these videos in an efficient way, we have been developing a custom-built ant tracking software pipeline which uses machine learning to detect harvester ants against a background of dirt and pebbles, then uses these detections to feed into an OpenCV-based tracking step, and finally counts the number of ants entering and leaving the nest in four different directions. The next steps will be to test, improve, and validate the software pipeline. This will allow us to process hundreds of videos and gather useful behavioral data, allowing us to assess whether one key to harvester ants' survival is their ability to adjust foraging behavior to flexibly avoid contact with the invasive Argentine ants.

Students working on this project will (1) use field cameras to observe and document native harvester ant colonies at the Bernard Field Station, (2) analyze data and videos from the field cameras using a combination of manual and automated methods, and (3) statistically analyze and present the results in visual and written form.

Name of research group, project, or lab
HMC Bee Lab
Why join this research group or lab?

You will be part of a team of students working on an interdisciplinary project, using mathematics, computation and engineering to solve problems of biological and applied conservation interest. You'll also have the opportunity to spend some time outdoors, observing nature. The variety of techniques and approaches will give you an opportunity to explore your interests and develop new skills. This is a new project, currently developing collaborations with researchers at nearby universities including UC San Diego and UC Riverside, which could expand your professional network. There may be opportunities to continue the work in a senior thesis, present at a regional or national conference, and/or co-author future publications stemming from ongoing work.

Representative publication
Logistics Information:
Project categories
Biology
Computer Science
Computer Vision
Data Science
Ecology
Student ranks applicable
Sophomore
Junior
Senior
Student qualifications

Strong programming experience in Python is required.

Here is a list of other skills/interests that could be useful, or which you might develop along the way. They're not requirements, but if you already have experience or interest in any of them, be sure to mention it in your application.

  • Linux/UNIX command line and shell scripting, high performance computing
  • Computer vision and image processing, e.g. using OpenCV
  • Machine learning and classification
  • Data science and visualization, particularly with R
  • Ecology and animal behavior
Time commitment
Spring - Part Time
Compensation
Academic Credit
Number of openings
1
Techniques learned

In this project, you will

  • contribute to a software pipeline written in Python
  • test and optimize common computer vision tasks such as object recognition and tracking
  • extract, analyze and visualize data resulting from the pipeline

You will also learn to read and discuss scientific literature, and to communicate across disciplinary boundaries and with the public about your work.

 

Project start
Spring 2026
Contact Information:
Mentor
mdonaldsonmatasci@hmc.edu
Associate Professor of Biology
Name of project director or principal investigator
Matina Donaldson-Matasci
Email address of project director or principal investigator
mdonaldsonmatasci@g.hmc.edu
1 sp. | 0 appl.
Hours per week
Spring - Part Time
Project categories
Ecology (+4)
BiologyComputer ScienceComputer VisionData ScienceEcology