Teaching

Advanced Deep Learning Architectures for environmental sceinces

Semester: Spring

Offered: 2027

The course provides a hands-on introduction to advanced deep learning methods for Earth and environmental sciences, with an emphasis on modern architectures for complex spatial and spatiotemporal data. Topics include convolutional and recurrent networks, Transformers, generative models, foundation models, and physics-informed learning.

Through practical exercises and projects, students will learn to implement and adapt these architectures to real environmental data, addressing problems such as weather forecasting, remote sensing, extreme-event prediction, and geospatial modeling.

Introduction to Deep Learning

Semester: Spring

Offered: 2027

A hands-on introduction to deep learning, covering the fundamental concepts and architectures behind modern AI. The course progresses from fully connected neural networks to CNNs, LSTMs, Transformers, and Vision Transformers (ViTs), combining core theory with practical implementation and real-world examples.

Introduction to Data Science

Semester: Spring

Offered: 2027

A hands-on introduction to data science, designed to build the skills needed for a complete data science workflow. The course covers data processing, exploratory analysis, visualization, statistical modeling, and machine learning, progressing from code fundamentals to supervised and unsupervised learning and reproducible reporting. 

Introduction to Data Science for Economists

Semester: Spring & Autumn 

Offered: 2020-2023

A hands-on introduction to data science for economics students, taught in R and designed for students with little or no programming experience. The course covers the complete data science workflow from data processing and visualization to statistical modeling and machine learning with an emphasis on developing practical tools for working with economic and real-world data. 

Lecture Notes can be found here