CIEN E4256: Applied Machine Learning in Civil Engineering

Course Overview

This course provides a gateway to advanced concepts in robot perception and machine learning, with a strong emphasis on multimodal sensing and machine learning algorithms for real-time processing. 

Vast amounts of data exist for everyday civil infrastructure, including buildings, roads, bridges, and water bodies. Making use of this data for design, engineering, and analysis gives opportunities to infrastructure owners, users, and policy makers to make informed decisions on design choices, investment decisions, retrofitting time, and proactive maintenance measures. This course will equip you with fundamental tools to analyze large-scale datasets and solve a range of civil engineering challenges, from traffic volume forecasting and indoor environmental quality assessment to building energy consumption prediction.

The course consists of two modules: a theoretical background of machine learning and the applications of machine learning used in the Architecture,  Engineering and Construction (AEC) industry. The first module covers essential theoretical topics such as classification and regression, probability theory, regularization, bias-variance trade-off, and performance metrics. The second module centers on practical applications in construction and facilities management, including construction worker safety, project take-off automation, traffic prediction, indoor environmental quality, and building energy forecasting. To gain valuable industry insight, you will engage with real-life, relevant problems experienced by civil engineers, project and facility managers.

By combining theory with hands-on problem-solving, this course trains you to apply modern machine learning methods to shape smarter, safer, and more efficient infrastructure systems. You must have basic understanding of linear algebra, probability and statistics to take this course.

Course Instructor

Zhengbo Zou

Assistant Professor

Zhengbo Zou is an Assistant Professor in the Department of Civil Engineering and Engineering Mechanics at Columbia University. He is also an affiliated member of the Columbia University Data Science Institute and the Zuckerman Mind Brain Behavior Institute.

Zou leads the Intelligent Construction Lab at Columbia ( ICON@Columbia ), which seeks to better understand how intelligent robots interact with human operators, co-workers, and the built environment. Leveraging machine learning and control theory, Zou’s lab designs, builds, and controls robots and conducts human participant experiments to study their impacts on the end users.