CEVE 543 - DATA-DRIVEN CLIMATE HAZARD
Long Title: DATA-DRIVEN MODELS FOR CLIMATE HAZARD
Department: Civil & Environmental Engr
Grade Mode: Standard Letter
Language of Instruction: Taught in English
Course Type: Lecture
Credit Hours: 3
Restrictions: Must be enrolled in one of the following Level(s):
Graduate
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. Examples of potential topics covered include nonparametric statistics, convolutional neural networks, Gaussian processes, wavelets and spectral analysis, extreme value distributions, hierarchical models, and graph neural networks. Recommended Prerequisite(s): Prior coursework in Bayesian statistics (e.g., STAT 425/525) and/or machine learning (e.g., ELEC 478/578) and some comfort writing code.