Using AI to Analyze Stresses Beneath a Building Foundation

In this assignment, students analyzed vertical stress increases beneath a surface load using the Boussinesq method and compared it with alternative analytical approaches identified using a generative AI tool. Rather than using AI to solve the problem, students evaluated different methods and limitations to deepen their understanding and support engineering decision-making.

Authors: 

Civil and Environmental Engineering Department

  • Mohamad Mahdi Hallal, Assistant Professor
  • Adda Athanasopoulos-Zekkos, Associate Professor
  • Arwen Gosch, Graduate Student
  • James Nguyen, Project Engineer

Course Number & Title: CIVENG 175, Geotechnical and Geoenvironmental Engineering

This work is licensed under CC BY-NC-SA 4.0

Details
Assignment Title
 		Using AI to Analyze Stresses Beneath a Building Foundation
Delivery FormatIn-person
Learning Objectives
  • Apply the Boussinesq method to calculate vertical stress increases at depth due to uniform surface load.
  • Use AI tools to identify and implement alternative analytical methods for stress distribution.
  • Evaluate the assumptions, limitations, and applicability of different stress distribution methods to identify the most appropriate method.
  • Develop AI literacy skills, including method exploration, verification of AI-generated information, and engineering judgment in selecting appropriate analytical approaches.
Brief Summary of AssignmentStudents analyze vertical stress increases beneath a surface load using the Boussinesq method and compare it with alternative analytical approaches identified using a GenAI tool. The exercise introduces AI-assisted method exploration, where students evaluate different approaches, assumptions, and limitations rather than relying on AI for direct solutions. Rather than relying on AI for obtaining solutions, students use AI as a learning tool for expanding technical knowledge and supporting engineering decision-making. GenAI tools used: Any comparable large language model.
Guardrails Shared with StudentsThe assignment includes AI-use indicators that communicate expectations at the question level. These indicators can distinguish between questions where AI is not permitted (NAI), partially permitted (PAI), or fully permitted (FAI). In the NAI category, AI tools are not permitted at any stage of the task. In the PAI category, AI tools may be used for limited purposes, such as brainstorming, outlining, debugging, or providing feedback, but not for generating final solutions. In the FAI category, AI tools may be used throughout the task, including generating content or final solutions. These AI-use indicators would then be included next to each question to clearly and explicitly communicate AI use expectations.
Assignment Details
Content tags