New Class Leads Students through Data to Solutions
A new class, CEGE 4160/5180 Special Topic: Applied Machine Learning for CEGE, will enhance students' preparation to work with big data and sophisticated models. The course was developed by three CEGE faculty, Randal Barnes, Seongjin Choi, and Ardeshir Ebtehaj. It will be offered for the first time in spring 2025.
The offering of this class is timely as engineers are more and more expected to be able to collect, analyze, interpret, and apply large amounts of data to solve big problems and build and operate complex systems. The problems and solutions that civil, environmental, and geo- engineers work on require the assessment of multiple options and risks. Luckily, the expansiveness of available data—fueled by massive simulation based models and real-time data generated from sensors on everything from structures to roadways to wastewater systems—supports this large-scale problem solving.
This course will prepare graduate students and upper-level undergraduates to manage data and leverage machine learning techniques for applications in civil engineering, environmental engineering, and geoengineering. It will span classical methods to state-of-the-art deep learning approaches, tailored specifically for the problems that CEGE students might encounter. The course will emphasize hands-on learning, with one or two practical applications for each topic. By the end of the course, students will have gained the skills to apply machine learning techniques to solve real-world problems.
The Faculty
Seongjin Choi (transportation). Choi's research interests include urban mobility data analytics, spatiotemporal data modeling, deep learning & artificial intelligence, and connected automated vehicles (CAV) & cooperative-ITS.
Randal Barnes (geotechnical). In addition to his research, Barnes is recognized for his outstanding contributions to undergraduate teaching.
Ardeshir Ebtehaj (water resources). Ebtehaj is currently working on a NASA-supported project to provide the longest and most accurate record of global snowfall data.