Stanford Engineering
Gradient Spaces Lab

AI Applications for the AEC Industry

Course Information

  • Course ID: CEE 342 (Spring 2026)
  • Instructors: Prof. Iro Armeni, Adjunct Lecturer Pooja Jain      (Prof. Martin Fischer is on sabbatical this year)
  • Teaching Assistants: Jinpu Cao
  • Lectures: Mondays and Wednesdays, 9:30 - 10:50 AM in Y2E2 292A
  • Credits: 3
  • Online Material: Canvas
  • Office Hours:
    • Iro Armeni: OH by appointment, Y2E2 233
    • Pooja Jain: OH by appointment, TBD
    • Jinpu Cao: TBD, TBD
  • For CEE MS SDC Students: It is included in the Requirements.

Course Motivation

This course on AI Applications in architecture, engineering, and construction (AEC)  equips future professionals with vital knowledge and tools to harness artificial intelligence (AI) solutions, addressing the AEC industry's challenges. The curriculum underscores AI's transformative potential in design, construction, and management, advocating for its integration into project delivery and operational workflows. This course aims to educate the next generation of engineers, architects, entrepreneurs and builders in applying advanced technologies for smarter project execution, strategic planning, and predictive analysis, leading to practices that significantly elevate sustainability and efficiency. Furthermore, the course emphasizes the importance of considering sociopolitical dynamics and ethical dimensions, recognizing that AI's impact extends beyond individual projects to national, regional, and industry-wide scales. This broader perspective ensures that AI applications are developed and deployed responsibly, fostering positive societal outcomes and upholding ethical standards within the evolving AEC landscape.

Vision

We envision that professionals in all disciplines involved in shaping the design, construction, and operation of the built environment will leverage data-driven, AI-based methods to create design solutions that balance the aspirations and concerns for all the main building stakeholders because they:

  • understand the range of performance of previous building projects and the drivers of performance,
  • gain insights into the full design space thanks to rapid simulations of building performance for all important performance aspects, and
  • continue to learn about how to further improve the performance of buildings.

Note that “design” is understood holistically here. It includes the design of the building itself (“product design”), but also the design of the construction process, operational procedures, etc. (“process and organization design”), since a product design enables or hinders certain processes and vice versa.

Learning Objectives

This vision is a few years away. Today and for the foreseeable future, the best performance for a building project team will be achieved through a purposeful combination of AI-based, data-driven methods, and multi-disciplinary teams. In other words, we need to learn to combine human and artificial intelligence and we need to understand what AI systems can and cannot do vs. what humans are good at. Therefore, this course will introduce you to the most applicable AI and data-driven methods (Machine Learning, Computer Vision and Pattern Recognition, and Natural Language Processing). You will understand the types of problems addressed by these methods and will also understand the limitations of these methods so that you can connect the AI methods with the work of AEC industry professionals as envisioned above. At the end of the course, you should be able to:

  • present a business plan and POC for a specific AI solution within a company,
  • understand the GenAI ecosystem, including its various aspects such as infrastructure, legal, ethical, and human-centric perspectives,
  • articulate an industry problem clearly (the “value” perspective, right side in Figure 1) to set up the expected insights (center part of Figure 1) from the application of AI and establish the data necessary to generate the insights,
  • understand the insights that can be generated by a particular AI method when combined with the relevant data (the “data” perspective, left side in Figure 1), and
  • connect the data and value perspectives.

Figure 1: Diagram illustrating the main learning objective of the class.

Fig. 1 will guide this course. It will be complemented by other frameworks. To illustrate the application of the framework, consider the real-world example of a mid-sized general contractor in Norway. The contractor’s innovation team developed a weekly / daily construction site management software combining BIM and the Last Planner System. The system worked very well on a few demonstration projects allowing foremen and the superintendent to understand the work accomplished and the work ahead better in detail and holistically. Gunnar and his team expected, therefore, rapid deployment across many projects. This did not happen. Fig. 1 explains, at least in part, why. Working through the diagram from the technology perspective, you see that the technology improved the description of what is happening on site. Some site staff found this improvement helpful. Working through the diagram from the value side, we realized that most site staff really wanted a prescription, i.e., they wanted to know what should be done tomorrow and beyond. Hence, the insights expected by the business, i.e., the value perspective, didn’t align with the insights the technology could provide. We have seen such misalignments in most attempts to leverage technology for better decision making. These frequent misalignments motivate us to teach this course so that you can align the value and technology perspectives.

 

Course Content and Grading Basis

You will learn about AI Applications in AEC through these five course components:

  1. Class lectures
  2. Class readings and short videos
  3. Assignments
  4. Guest lectures
  5. Course project

The grading will be as follows:

  • Class attendance, participation, and engagement with guest speakers (25%)
  • Assignments (25% in total, 10% each)
  • Course project with industry partners (50% in total)

Course Project

In the course project, you will work with an industry practitioner who will offer a strong data or value perspective. In the project, you will complement the data or value perspective with the other perspective to establish an AI-based, data-driven method for generating insights that support decisions.