Current Courses

Machine Learning in Earth and Environmental Sciences

EAS 4803/8803 – Fall Semester (Graduate/Undergraduate Level)

This course offers a comprehensive introduction to machine learning with a focus on applications in Earth systems and environmental sciences. Students explore both foundational and advanced algorithms, applying them to real-world environmental datasets through hands-on coding in Python. Topics include feature engineering, supervised and unsupervised learning, ensemble methods, neural networks, deep learning architectures (CNNs, RNNs, GANs, transformers, diffusion models), and interpretable machine learning. Coursework combines lectures, practical coding sessions, and collaborative discussions, culminating in a group research project that addresses a real-world environmental or Earth system challenge. Designed for senior undergraduates and graduate students, the course equips participants with the skills to design, implement, and validate data-driven models for environmental science research and applications.

Introduction to Weather Risk and Catastrophe Modeling

EAS 4525/6525 – Spring Semester (Graduate/Undergraduate Level))

This course equips junior and senior undergraduates, as well as early-stage graduate students, with the knowledge and skills to understand, analyze, and manage weather-related risks in real-world contexts. Students explore the physical processes driving hazardous weather and climate events — from extreme rainfall, flooding, wildfires, and tropical cyclones to complex cascading and compound extremes — and examine their behavior across temporal and spatial scales in a warming climate. Building on this scientific foundation, the course introduces the philosophy, concepts, and methodologies of catastrophe modeling, with an emphasis on physics-based damage assessment to quantify potential losses and inform risk management strategies. Through hands-on labs, coding exercises in R, and applied projects, students gain practical experience in quantifying weather risk, analytically estimating damages from historical and synthetic events, processing and visualizing meteorological datasets, and applying catastrophe models to evaluate economic impacts and resilience strategies.