AI+CEE MS Track

The AI courses in CEE balance data science methodology and disciplinary contents from different CEE areas of study. Students will choose 3 courses from AI courses in CEE list as part of the 9 total courses (36 credits) required to complete the non-thesis AI+CEE MS Track. 

AI Courses in CEE

CEE 492. Data Science for CEE 
Students will learn to leverage data to study CEE problems, identify patterns and make actionable insights. The course include training in digital and computer tools (such as data processing, exploratory data analysis, spatial data, data visualization, distributed computing, and statistical modeling) with their applications to CEE issues. Class offered every fall semester.

CEE 498MLC. Machine Learning for CEE
Students will learn the fundamentals behind advanced machine learning and learn how to use machine learning tools to solve CEE problems. Topics include regression, Bayesian inference, deep neural networks, scientific deep learning, and Gaussian Processes. Class offered every spring semester.

CEE 598DL. Deep Learning for CEE Sensing, Simulation, & Prediction
This course focuses on deep learning within all areas of civil and environmental engineering. In addition to examining the basics of deep learning, students will investigate practical applications in sensor data processing, information extraction, remote sensing, surrogate modeling, and predictive analytics. Topics of interest include deep convolutional networks, recurrent neural networks, and generative adversarial learning. Students will learn to identify, understand, and compare different deep learning techniques and formulate civil engineering problems using appropriate techniques. 

CEE 522. Visual Data Analytics
An introduction to 2D and 3D visual sensing for data acquisition and analysis of buildings and civil infrastructure systems. It is intended mainly for graduate students who want to acquire basic understanding of the theoretical concepts as well as application of computer vision and image processing for sensing buildings, civil infrastructure systems and sustainable construction operations.

CEE 598LM. Learning Methods in Civil Engineering
This course will focus on the fundamentals of learning methods and how they can be applied to civil engineering applications. This course will cover the following materials: Markov decision process, partially observable Markov decision process, reinforcement learning, temporal difference, game theory, genetic algorithm, simulated annealing, and multi-agent deep reinforcement learning. Note that these materials will be covered in accordance to civil engineering problems.

CEE 598PIM. Physics-Informed Machine Learning
Students will learn how to: (a) construct data-driven ML models; (b) constrain ML models with the laws of physics and engineering principles; (c) apply physics-informed ML models to engineering problems. The main topics will include physics-informed Deep Neural Network and Gaussian process regression models and theory-guided machine learning. We will focus on flow, transport, and other processes key to water resources and environmental engineering applications.  

View AI+CEE MS Track Course Requirements