Deep Learning for Geo and Environmental Science#
This hands-on graduate-level course introduces students to the application of machine learning techniques in the field of environmental sciences. It covers the main classes of supervised and unsupervised machine learning algorithms and provides practical experience in training and validating real-world models. Students will gain the skills necessary to analyze environmental data, make predictions, and uncover hidden patterns.
Developed at the Climate Analytics Lab (CAL), it is currently taught at Scripps Institution of Oceanography as SIO(C) 209.
Prerequisites#
Prior knowledge of machine learning fundamentals, including linear algebra, gradient descent and backpropagation. Basic programming skills (e.g., Python) are required.
Course Objectives#
By the end of the course, students should be able to:
Understand the principles of machine learning and its applications in environmental sciences.
Apply supervised and unsupervised machine learning techniques to environmental data.
Evaluate and validate machine learning models using appropriate metrics.
Interpret and communicate results effectively.
Develop proficiency in using machine learning libraries and tools in Python.
Course Duration#
This is intended as a 10 week, 4-unit course (one quarter)