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, environmental sustainability, environmental justice, and natural hazards. The course will start with introducing domain science theories and basics, and then move forward to discussing how modern data-driven and hybrid AI/ML approaches can be used to improve environmental prediction, understanding, and decision support in systems characterized by strong nonlinearity, uncertainty, complex or limited observation data. Students will learn the foundations of machine learning models alongside their application to simple environmental datasets, with emphasis on time series analysis, spatial data analysis, and spatiotemporal problems common in climate, water resources, and environmental sciences. Basic Python programming will be taught for students without any prior coding experience, particularly suitable for students from Sustainable Systems, Geospatial Data Science, Ecosystem Science and Management, and other specializations. This course is also designed to support research-oriented training for MS theses, capstone projects, and PhD research by guiding students through problem formulation, literature review, experimental design, and technical communication and presentation.