Education

The following courses have been offered regularly.

For all courses, please refer to the school website.

Scientific Machine Learning for Infrastructure Systems

Civil & Environmental Engineering (UG/PG), Spring Semesters

Scientific machine learning (ML) seeks to address domain-specific data challenges and extract insights from scientific data sets through innovative methodological solutions, and this course aims to introduce scientific ML to senior students with a special focus on civil engineering applications. The course starts with an extensive review of statistics, the difference between ML and descriptive statistics, discusses sampling approaches for uncertainty quantification, then covers the fundamental knowledge of supervised learning (Bayesian linear regression, Gaussian processes, deep neural networks), unsupervised learning (k-means clustering, principal component analysis, Gaussian mixtures), and state space models (Kalman, particle filters). The course will further emphasize on the proper use of ML for civil engineering applications, including incorporating physics-based knowledge (physics-informed ML), dealing with data acquisition challenges (design of experiment, global optimization), and so on. Students will learn to address some unique challenges of applying ML to real-world engineering applications, preparing themselves better in their future career.

Modeling Systems with Uncertainties

Civil & Environmental Engineering (UG), Fall Semesters

Identification and modeling of non-deterministic problems in civil engineering, and the treatment thereof relative to engineering design and decision making. Development of stochastic concepts and simulation models, and their relevance to real design and decision problems in various areas of civil engineering.