2026 ASEE Annual Conference & Exposition

This manuscript presents an in-person, active learning activity for civil engineering students that demonstrates how to construct and analyze complex network models. A secondary objective of the activity is to encourage students to leverage the power, popularity, and availability of artificial intelligence (AI) to efficiently and effectively support their learning process. By increasing the students’ AI literacy, it may encourage the students to more critically assess the problem and propose more creative solutions. The exercise investigated air travel in the Indo-Pacific region using open-source data for local airports, air travel statistics, and relevant constraints. The primary objective for the students was identification of the limits of an acceptable air transportation network. Students used open-source large language model (LLM) generative AI to both write python code and execute that code “under the hood” to complete hundreds of mathematical operations with only natural text prompting. This computation would otherwise have to be coded in Python, completed by hand, or iteratively solved via Microsoft Excel or another computational tool. Instructors prompted the students to verify their answers from AI to ensure accuracy. Once the students compiled the raw data, they created a full network visualization in Google Earth using AI instead of manually drawing the network. This exercise provided students with confidence that they could construct a real-world network map using a variety of data sources and software to produce a high-quality solution. The use of AI in this in-class exercise automates the repetitive mathematical operations and the Keyhole Markup Language (KML) code writing required to map and visualize the network, providing students with more time to engineer solutions. This paper provides a unique case study for civil engineering faculty to incorporate AI into their teaching and learning. The authors would like to present the results of this study in the “Hands-on AI” CE Division Session to demonstrate the activity and inspire other educators. This manuscript documents the design, implementation, and assessment of the network analysis activity using AI. The activity assessed both students’ learning based on their performance on a midterm exam and their perspective on the integration of AI through an anonymous survey. The students successfully achieved the learning objectives as automation of the redundant processes and visualization assistance provided them with additional time to critically evaluate the network and make recommendations to improve its performance.