Mentor & Lab: Anna Poulton, Munch & Palkovacs Labs
Positions: 1 intern
Tentative dates: Summer 2026 (exact dates flexible)
Project Location: Coastal Campus/hybrid
Project Background: Forecasting is an important component of ecological conservation and management. For example, forecasts of fish abundance are essential for setting harvest limits in fisheries. Many models used by ecological managers require strong assumptions about the system’s structure. As a result, their predictive performance is sometimes poor, even in data-rich ecological systems. Newly developed machine learning (ML) tools offer an important alternative to such models that allow us to make forecasts without strong assumptions about the system. Adapting these new ML approaches to solve practical problems in conservation and management is an exciting area of current research.
Intern duties:
The intern will learn about ecological forecasting with machine learning. Mentored by a postdoc, the intern will analyze ecological time series and evaluate the performance of ML forecasting methods. Depending on the intern’s skills and interests, this could involve gathering and analyzing historical data for key fisheries species, testing improvements to data-driven forecasting methods (e.g., comparing noise reduction algorithms on simulated and real data), or developing a web application that allows users to upload and forecast their own data.
Intern qualifications:
Some mathematical/statistical background (for example, Stat 7/7L for EEB students). Training on specific methods will be provided.
Some experience coding in R or another language (MATLAB, Python, C++, etc.). Additional training and programming support will be available during the project, but the intern should be comfortable with the basics (e.g., as introduced in Stat 7L).
Enthusiasm for learning about ecological modeling and forecasting!
Do you recommend the intern(s) volunteer in your lab during Spring quarter? Optional. Depending on the intern’s availability, spring quarter could be used to refresh on coding basics or get a head start on learning the project background, allowing for more research time in the summer.
