Environmental Data Science

Course Description

This course covers the use of tools from data science (statistics, machine learning, and programming) to model climate hazards such as floods and droughts. Through hands-on programming assignments based on state-of-the-art published research, students will learn to apply methods to real-world problems with a strong emphasis on probabilistic methods and uncertainty quantification.

At the end of this class, students will:

  1. Write down generative or statistical models for climate hazards;
  2. Use Bayesian and maximum likelihood methods to estimate the parameters of simple statistical models (“inverse modeling”);
  3. Use simulation models (“forward modeling”) to assess the logical implications of statistical models;
  4. Understand and apply extreme value theory to estimate the probability of rare climate hazards;
  5. Critically interpret statistical analyses of environmental data applied in academic journals, government, and industry; and
  6. Understand and communicate subjective modeling choices to technical (e.g., scientist) and non-technical (e.g., policy-maker) audiences.

More information

For details, see the course website.