Foundations of Machine Learning For Ecology

Page under construction. Check back after Sept 1. 

Modern ecology increasingly joins traditional fieldwork with large datasets, computer models, and artificial intelligence. Ecologists now draw on information from environmental sensors, camera traps, acoustic monitors, animal-tracking systems, remote sensing, and global biodiversity databases. Undergraduate students therefore need more than familiarity with ecological theory: they need a practical understanding of how machine-learning models find patterns, make predictions, and sometimes fail. This Foundations Course provides an introductory, hands-on guide to machine learning and AI for the next generation of ecologists, embedding computational methods within authentic questions about organisms, populations, communities, and changing environments.

Through custom-built interactive applications, ecological case studies, and progressively more independent investigations, students explore the logic behind methods ranging from regression, decision trees, clustering, and similarity analysis to neural networks, computer vision, recurrent models, and reinforcement learning. They move beyond simply running algorithms to preparing ecological data, building and evaluating models, interpreting results, and asking whether the conclusions make biological sense. Along the way, students develop portfolios of Python code and ethical reflections that demonstrate not only technical competence, but also the scientific judgment needed to use AI responsibly. The goal is not to replace the field notebook or the ecologist, but to add powerful new tools to the ecological toolkit and prepare students to investigate living systems in an increasingly data-rich world.