ai4aec.html

<!doctype html>
<html lang="en">
  <head>
    <meta charset="utf-8">
    <meta name="viewport" content="width=device-width, initial-scale=1">
    <meta
      name="description"
      content="AI Applications for the AEC Industry — course information, learning objectives, and grading from the Gradient Spaces Lab at Stanford."
    >
    <title>AI Applications for the AEC Industry | Gradient Spaces Lab</title>
    <meta property="og:title" content="AI Applications for the AEC Industry | Gradient Spaces Lab">
    <meta property="og:description" content="Course information, learning objectives, and grading for CEE 329, AI Applications for the AEC Industry, taught by Iro Armeni and Pooja Jain.">
    <meta property="og:type" content="website">
    <meta property="og:url" content="https://gradientspaces.github.io/ai4aec.html">
    <link rel="canonical" href="https://gradientspaces.github.io/ai4aec.html">
    <link rel="icon" type="image/png" href="assets/images/GradientSpacesLogo.png">
    <link rel="apple-touch-icon" href="assets/images/GradientSpacesLogo.png">
    <link rel="stylesheet" href="styles.css?v=20260925">
  </head>
  <body>
    <header class="site-header">
      <a class="brand" href="index.html">Gradient Spaces</a>
      <button class="nav-toggle" type="button" aria-expanded="false" aria-controls="site-nav" title="Open navigation">
        <span class="sr-only">Menu</span>
        <span aria-hidden="true"></span>
        <span aria-hidden="true"></span>
        <span aria-hidden="true"></span>
      </button>
      <nav class="site-nav" id="site-nav" aria-label="Main navigation">
        <a href="index.html">Home</a>
        <a href="people.html">People</a>
        <a href="research.html">Research</a>
        <a class="active" href="teaching.html">Teaching</a>
        <a href="events.html">Events</a>
        <a href="gradient-space.html">Gradient Space</a>
        <a href="index.html#news">News</a>
        <a href="index.html#connect">Connect</a>
      </nav>
    </header>

    <main>
      <section class="page-hero teaching-hero">
        <div>
          <a class="text-link back-link" href="teaching.html">Back to Teaching</a>
          <p class="eyebrow">Teaching</p>
          <h1>AI Applications for the AEC Industry</h1>
          <p class="lead">
            Equipping future professionals in architecture, engineering, and construction with the knowledge
            and tools to harness AI — aligning what technology can deliver with the value the industry needs.
          </p>
        </div>
      </section>

      <section class="section" aria-labelledby="info-title">
        <div class="section-heading">
          <p class="section-kicker">Overview</p>
          <h2 id="info-title">Course information</h2>
        </div>
        <dl class="info-grid">
          <div class="info-row">
            <dt>Course ID</dt>
            <dd>CEE 329 (Spring 2026)</dd>
          </div>
          <div class="info-row">
            <dt>Instructors</dt>
            <dd>Iro Armeni, Pooja Jain (Adjunct Lecturer)</dd>
            <dd>Prof. Martin Fischer is on sabbatical this year.</dd>
          </div>
          <div class="info-row">
            <dt>Teaching Assistant</dt>
            <dd>Jinpu Cao</dd>
          </div>
          <div class="info-row">
            <dt>Lectures</dt>
            <dd>Mondays and Wednesdays 9:30–10:50 AM, Y2E2 292A</dd>
          </div>
          <div class="info-row">
            <dt>Credits</dt>
            <dd>3</dd>
          </div>
          <div class="info-row">
            <dt>Office Hours</dt>
            <dd>Iro Armeni — by appointment, Y2E2 233</dd>
            <dd>Pooja Jain — by appointment, location TBD</dd>
            <dd>Jinpu Cao — TBD</dd>
          </div>
          <div class="info-row">
            <dt>Online Material</dt>
            <dd>Canvas</dd>
          </div>
          <div class="info-row">
            <dt>Notes</dt>
            <dd>For CEE MS SDC students: included in the Requirements.</dd>
          </div>
        </dl>
      </section>

      <section class="section" aria-labelledby="description-title">
        <div class="section-heading">
          <p class="section-kicker">Description</p>
          <h2 id="description-title">Course description</h2>
        </div>
        <div class="body-copy">
          <h3 class="course-detail-subhead">Motivation</h3>
          <p>
            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.
          </p>
          <p>
            The 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. It also 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.
          </p>

          <h3 class="course-detail-subhead">Vision</h3>
          <p>
            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 of all the main building stakeholders, because
            they:
          </p>
          <ul>
            <li>understand the range of performance of previous building projects and the drivers of performance,</li>
            <li>gain insights into the full design space thanks to rapid simulations of building performance for all important performance aspects, and</li>
            <li>continue to learn how to further improve the performance of buildings.</li>
          </ul>
          <p>
            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.
          </p>

          <h3 class="course-detail-subhead">Learning objectives</h3>
          <p>
            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 to understand what AI systems can and cannot do versus what humans are
            good at.
          </p>
          <p>
            The course therefore introduces the most applicable AI and data-driven methods (Machine Learning,
            Computer Vision and Pattern Recognition, and Natural Language Processing). Students will understand
            the types of problems these methods address, as well as their limitations, so that they can connect
            AI methods with the work of AEC industry professionals as envisioned above. By the end of the
            course, students should be able to:
          </p>
          <ul>
            <li>present a business plan and proof of concept (POC) for a specific AI solution within a company,</li>
            <li>understand the GenAI ecosystem, including its infrastructure, legal, ethical, and human-centric aspects,</li>
            <li>articulate an industry problem clearly (the “value” perspective, right side of Figure 1) to set up the expected insights (center of Figure 1) from the application of AI, and establish the data necessary to generate those insights,</li>
            <li>understand the insights that a particular AI method can generate when combined with the relevant data (the “data” perspective, left side of Figure 1), and</li>
            <li>connect the data and value perspectives.</li>
          </ul>

          <figure class="course-figure">
            <img
              src="assets/images/ai4aec-figure1.jpg"
              alt="Diagram connecting the technology driver (data, models, and performance) through four levels of digital twin — description, diagnostic, prediction, and prescription — to the business driver (value and transformation)."
              width="1242"
              height="755"
              loading="lazy"
            >
            <figcaption>Figure 1: Diagram illustrating the main learning objective of the class.</figcaption>
          </figure>

          <p>
            Figure 1 guides the course and is complemented by other frameworks. To illustrate the framework,
            consider a real-world example of a mid-sized general contractor in Norway. The contractor's
            innovation team developed weekly and daily construction site management software combining BIM and
            the Last Planner System. The system worked very well on a few demonstration projects, helping
            foremen and the superintendent understand the work accomplished and the work ahead, both in detail
            and holistically. Gunnar and his team therefore expected rapid deployment across many projects.
            This did not happen.
          </p>
          <p>
            Figure 1 explains, at least in part, why. Working through the diagram from the technology
            perspective, the technology improved the <em>description</em> of what was happening on site, and
            some site staff found this helpful. Working through it from the value side, most site staff really
            wanted a <em>prescription</em> — they wanted to know what should be done tomorrow and beyond. The
            insights expected by the business did not align with the insights the technology could provide.
            Such misalignments appear in most attempts to leverage technology for better decision making, and
            they motivate this course: to learn to align the value and technology perspectives.
          </p>
        </div>
      </section>

      <section class="section" aria-labelledby="grading-title">
        <div class="section-heading">
          <p class="section-kicker">Structure</p>
          <h2 id="grading-title">Course content &amp; grading</h2>
        </div>

        <h3 class="course-detail-subhead">Course components</h3>
        <div class="body-copy">
          <p>Students learn about AI applications in AEC through five course components:</p>
          <ul>
            <li>Class lectures</li>
            <li>Class readings and short videos</li>
            <li>Assignments</li>
            <li>Guest lectures</li>
            <li>Course project</li>
          </ul>
        </div>

        <h3 class="course-detail-subhead">Grading</h3>
        <div class="table-wrap">
          <table class="data-table">
            <thead>
              <tr><th>Weight</th><th>Component</th></tr>
            </thead>
            <tbody>
              <tr><td>25%</td><td>Class attendance, participation, and engagement with guest speakers</td></tr>
              <tr><td>25%</td><td>Assignments (10% each)</td></tr>
              <tr><td>50%</td><td>Course project with industry partners</td></tr>
            </tbody>
          </table>
        </div>
      </section>

      <section class="section" aria-labelledby="projects-title">
        <div class="section-heading">
          <p class="section-kicker">Projects</p>
          <h2 id="projects-title">Course project</h2>
        </div>
        <div class="body-copy">
          <p>
            In the course project, students work with an industry practitioner who offers a strong data or
            value perspective. Students complement that perspective with the other one to establish an
            AI-based, data-driven method for generating insights that support decisions.
          </p>
        </div>
      </section>
    </main>

    <footer class="site-footer">
      <div class="footer-identity">
        <a href="https://cee.stanford.edu/" aria-label="Stanford Civil and Environmental Engineering">
          <img src="assets/images/stanford-cee-lockup.png" alt="Stanford University — Civil &amp; Environmental Engineering">
        </a>
        <a class="footer-soe-logo" href="https://engineering.stanford.edu/">
          <img src="assets/images/stanford-engineering-logo.png" alt="Stanford Engineering" width="1080" height="101">
        </a>
        <p>Gradient Spaces Research Group</p>
      </div>
      <div class="footer-meta">
        <p>Y2E2, 473 Via Ortega, Stanford, CA 94305</p>
        <p>Site owner: Iro Armeni · iarmeni@stanford.edu</p>
        <p class="footer-accessibility"><a href="https://www.stanford.edu/site/accessibility">Accessibility</a></p>
      </div>
    </footer>

    <script src="script.js?v=20260925"></script>
  </body>
</html>