This course introduces students to the theory and practice of artificial intelligence (AI) and machine learning (ML) as applied to environmental systems, including hydrology, water resources, weather and climate, ecosystems, and natural hazards. The course focuses on how modern data-driven and hybrid AI approaches can be used to improve environmental prediction, understanding, and decision support in systems characterized by strong nonlinearity, uncertainty, and limited observations. Students learn the foundations of machine learning alongside their application to real environmental datasets, with emphasis on time series, spatial, and spatiotemporal problems common in Earth and environmental sciences.

Specific topics include regression and classification, tree-based models, neural networks, recurrent and convolutional architectures, probabilistic prediction, and physics-informed and hybrid AI models. Throughout the course, AI methods are critically evaluated against physical models, statistical baselines, and climatology to emphasize scientific credibility, benchmarking, and interpretability. This course also combines conceptual lectures with hands-on data analysis and applied modeling exercises using Python-based tools commonly used in environmental data science. Student will not be required to have any prior Python programing experience and we will start with Python programming 101 for students. In addition to skill development, the course is intentionally designed to support research-oriented training for students pursuing MS theses, capstone projects, or PhD research. Students are guided through the process of identifying researchable environmental problems, conducting focused literature reviews, designing modeling experiments, evaluating model performance and uncertainty, and communicating results through written proposals and oral presentations.

This course fits naturally within the Environmental Systems, Water Systems, Geospatial Data Science, and Sustainability curricula and is particularly well suited for students interested in careers or advanced study in environmental modeling, forecasting, data science, and decision-support applications where AI is increasingly central.