Florida Gulf Coast University
U.A. Whitaker College of Engineering
Fall 2026/2027
Last updated: Oct 14, 2025
Recorded Lessons: Link
EGN 6455 AI in Engineering
CRN: 1XXXX
Credit hours: 3
Class: Online - Asynchronous
Exam: Wednesday Dec 8 from 6:00 pm to 8:00 pm - In-Person at TBD.
Instructor
Ahmed S. Elshall, PhD
Assistant Professor, Department of Bioengineering, Civil Engineering, and Environmental Engineering
U.A. Whitaker College of Engineering
Joint Faculty, The Water School
Affiliate Member, Dendritic: A Human-Centered AI and Data Science Institute
Research Website: https://aelshall.weebly.com
Office: Holmes Hall 423 (inside 416)
Office Hours: Tuesday 8:00 AM – 12:00 PM and by appointment using this link
Teaching Assistant
TBA
Office Hours: By appointment
Catalog Description
Foundations, applications, and responsible use of artificial intelligence (AI) in engineering practice and research.
Prerequisites: Introductory programming, statstics and calculus, or consent of the instructor.
Introduction
This course introduces engineering students to the foundations, applications, and responsible use of artificial intelligence (AI) in engineering practice and research, emphasizing ethical awareness, reproducible workflows, and problem solving. Through hands-on exercises and real-world case studies, students develop practical skills in coding, machine learning, and generative AI tools. Emphasis is placed on how AI can support data-driven analysis, modeling, and innovation across engineering domains.
This course is designed for students in civil and envionmental engineering and construction management with consideration that some students may not have a strong programming background. We will begin by building programming literacy through AI coding assistants. For demonstrations we will be use Python, which is a versatile and widely used programming language. We will then explore core machine learning paradigms including supervised and unsupervised learning, before advancing to deep learning and generative AI applications. The course concludes with an independent study module, where students explore AI tools or applications relevant to their engineering domain and present their findings to the class. Ethical and professional considerations of AI use are integrated throughout the course.
Human-AI Collaborative Learning
The course implements several pedagogical innovations through the FACT-3A framework (Elshall and Badir, 2025 and Elshall et al., In-Review), which integrates Fundamental skills, Applied projects, Conceptual understanding, and critical Thinking (FACT) assesssment with AI Affordance Alignment (A3). Through deliberately aligning learning objectives with AI capabilities, this framework balances traditional assessment of foundational knowledge with the open use of AI for real-world project learning. The framework includes the following pedagogical innovations:
- Collaborative human-AI learning environment with redefined roles such that the instructor acts as a mentor for higher-order reasoning, AI serves as a tutor for routine tasks, and the student becomes a lifelong learner.
- Dynamic syllabus where the course incorporates elective modules, independent study, and self-directed learning assignments to cultivate the adaptive skills required for lifelong learning.
- Instructor–learner co-design where students collaborate with the instructor to co-create course policies, AI-use guidelines, and evaluation rubrics, ensuring transparency and shared ownership of learning.
- Scaffolded AI use with a mix of no-AI use, AI-resistant assignments, structured-AI use, and open-AI use on complex projects, to build foundational knolwedge that is required to effectively and efficiently leverage AI assistance.
- Hybrid assessment design (FACT Framework) that balances no-AI exam that measures foundational knowledge with AI-assisted projects that assess applied skills, providing a comprehensive view of student learning.
This learner-centered framework is designed to equip you not only with technical skills but also with the mindset required in a future defined by human-AI collaboration.
Learning Outcomes
Upon successful completion, students will be able to:
- Explain key AI concepts and their applications in engineering
- Use a programming language and AI tools to analyze big data
- Apply supervised and unsupervised learning techniques for predictive modeling
- Employ generative AI to build upon specialized knowledge with critical oversight
- Identify and evaluate ethical and professional considerations of AI
- Continously develop a mindset required for a future defined by human-AI collaboration
- Share data and findings using notebooks and Git for reproducible workflow
Course Modules
The course has seven mandatory modules and one elective module as follows.
- Module 0: Introduction (1 week)
- Module 1: Start coding (2 weeks)
- Module 2: Coding with AI (2 weeks)
- Module 3: Supervised learning (3 weeks)
- Module 4: Unsupervised learning (1 weeks)
- Module 5: Neural networks (2 weeks)
- Module 6: Generative AI (2 weeks)
- Module 7: Responsible AI (1 week)
- Module 8: Elective - Domain-specific AI - Independent Study (2 weeks)
- Module 8: Elective - Domain-specific AI - Environmental Engineering (2 Weeks)
Course Schedule
These topics and number of assignments are tentative and subject to change based on class progress.
| Week |
Date (From - To) |
Topic |
Due Date |
| 1 |
18-Aug - 24-Aug |
0. Introduction: AI in Engineering |
HW1 |
| 2 |
25-Aug - 31-Aug |
1. Start coding: Installing and using Python and JupyterLab |
HW2 |
| 2 |
Monday 01-Sep |
Labor Day Observed (no classes) |
|
| 3 |
01-Sep - 07-Sep |
1. Start coding: Review of programming fundamentals |
HW3 |
| 4 |
08-Sep - 14-Sep |
2. Coding with AI: AI coding assistants |
HW4 |
| 5 |
15-Sep - 21-Sep |
2. Coding with AI: Prompt engineering |
HW5 |
| 6 |
22-Sep - 28-Sep |
3. Supervised learning: Regression |
HW6 |
| 7 |
29-Sep - 05-Oct |
3. Supervised learning: Modeling considerations |
HW7 |
| 8 |
06-Oct - 12-Oct |
3. Supervised learning: Claasification |
HW8 |
| 9 |
13-Oct - 19-Oct |
4. Unsupervised learning: Clustring |
HW9 |
| 10 |
20-Oct - 26-Oct |
5. Neural networks: Architectures of neural networks |
HW10 |
| 11 |
27-Oct - 02-Nov |
5. Neural networks: Deep learning |
HW11 |
| 12 |
03-Nov - 09-Nov |
6. Generative AI: Introduction and foundations |
HW12 |
| 13 |
10-Nov - 16-Nov |
6. Generative AI: Applications and evaluation |
HW13 |
| 13 |
Tuesday 11-Nov |
Veteran’s Day (no classes) |
|
| 14 |
17-Nov - 23-Nov |
7. Responsible AI: Ethical and critical collaboration with AI |
HW14 |
| 15 |
24-Nov - 25-Nov |
8. Domain-specific AI |
|
| 15 |
26-Nov - 30-Nov |
Thanksgiving Observed (no classes) |
|
| 16 |
01-Dec - 07-Dec |
8. Domain-specific AI |
HW15 |
| 17 |
08-Dec - 12-Ded |
Final Exam |
|
Topics
This course is designed for students in civil and environmental engineering and construction management, with consideration that some students may not have a strong programming background. The course builds foundational programming literacy, introduces AI-assisted coding, progresses through core machine learning, deep learning, and generative AI concepts and applications in engineering, and concludes with a domain-specific independent study.
Module 0: Introduction – 1 Week
Learning objectives: Describe the role and applications of AI in engineering practice and research.
- 0.1 Introduction to AI in Engineering
- Overview of course structure, expectations, and tools
- Introduction to artificial intelligence, machine learning, and generative AI in engineering
- Examples of AI applications in civil and environmental engineering, and construction management fields
- Homework 1 – Introduction to AI in Engineering
Module 1: Start Coding – 2 Weeks
Learning objectives: Install and use a dynamic programming language (Python), notebooks (JupyterLab), and version control (GitHub)
- 1.1 Installing and Using Python and JupyterLab
- Setting up Python and JupyterLab environments
- Navigating notebooks and running basic scripts
- Writing and documenting code using markdown and comments
- Sharing your data and notebook with version control using GitHub
- Homework 2 – Using Python, JupyterLab and GitHub
- 1.2 Review of Programming Fundamentals
- Variables, data types, operators, and control structures
- Lists, dictionaries, and loops in Python
- Functions, importing libraries, and working with data files
- Homework 3 – Fundamentals of Python Programming
Module 2: Coding with AI – 2 Weeks
Learning objectives: Use AI coding assistants and prompt engineering for effective and efficient coding
- 2.1 AI Coding Assistants
- Introduction to AI-assisted coding tools (e.g., ChatGPT, Gemini, Copilot)
- Writing, debugging, and explaining code with AI assistance
- Integrating AI assistants into Jupyter (or VS Code)
- Homework 4 – Using AI Coding Assistants for Programming Tasks
- 2.2 Prompt Engineering
- Fundamentals of effective prompting
- Crafting structured and context-aware prompts for coding tasks
- Iterative refinement and critical evaluation of AI-generated code
- Engineering applications: Exploratory data analysis of a survey results
- Homework 5 – Prompt Engineering for Exploratory Data Analysis
Module 3: Supervised Learning – 3 Weeks
Learning objectives: Apply supervised learning methods including regression and classification in engineering problems
- 3.1 Regression
- Linear regression, multiple linear regression, ridge and lasso regression
- Model fitting, evaluation metrics, and visualization
- Engineering applications of regression (e.g., groundwater flux estimation or cost estimation)
- Homework 6 – Regression Modeling in Engineering Applications
- 3.2 Modeling Considerations
- Overfitting, underfitting, and model validation
- Feature scaling, selection, and cross-validation techniques
- Interpreting and communicating model results
- Homework 7 – Model Validation and Performance Evaluation
- 3.3 Classification
- Classification algorithms (k-NN, decision trees, random forest)
- Performance evaluation (confusion matrix, accuracy, precision, recall)
- Engineering applications of classification (e.g., red tide weekly forecast or quality control)
- Homework 8 – Classification Techniques for Engineering Problems
Module 4: Unsupervised Learning – 1 Week
Learning objectives: Apply clustering and pattern recognition methods to discover structure in data
- 4.1 Clustering
- Introduction to unsupervised learning
- k-means, hierarchical, and DBSCAN clustering methods
- Engineering applications of clustering (e.g., clustering of water quality data or anomaly detection)
- Homework 9 – Clustering and Pattern Discovery in Environmental Data
Module 5: Neural Networks – 2 Weeks
Learning objectives: Explain neural network architectures and apply deep learning techniques to engineering applications
- 5.1 Architectures of Neural Networks
- Structure and components of neural networks
- Activation functions, forward and backward propagation
- Building simple neural networks in Python
- Homework 10 – Building and Training Simple Neural Networks
- 5.2 Deep Learning
- Introduction to deep learning frameworks (TensorFlow, PyTorch)
- Training, testing, and optimizing deep models
- Engineering applications of deep learning (e.g., image-based inspection or sensor data analysis)
- Homework 11 – Deep Learning Applications in Engineering Analysis
Module 6: Generative AI – 2 Weeks
Learning objectives: Use generative AI to access and build upon specialized knowledge responsibly
- 6.1 Introduction and Foundations
- Overview of generative AI models (LLMs, GANs, VAEs)
- Text, image, and data generation techniques
- Using APIs and AI platforms for generative tasks
- Homework 12 – Exploring Generative AI Models and Tools
- 6.2 Applications and Evaluation
- Applying generative AI for engineering documentation, design, and analysis
- Evaluating generated content for accuracy and bias
- Maintaining oversight and ethical use of generative tools
- Homework 13 – Applying and Evaluating Generative AI in Engineering
Module 7: Responsible AI – 1 Week
Learning objectives: Evaluate ethical, professional, and societal considerations in AI use
- 7.1 Ethical and Critical Collaboration with AI (Homework 14)
- Principles of responsible AI
- Bias, transparency, and accountability in AI systems
- Ethical use of generative AI in engineering workflows
- Homework 14 – Responsible and Ethical Use of AI
Module 8: Domain-Specific AI – 2 Weeks
Learning objectives: Apply AI tools to a domain-specific engineering problem and communicate findings effectively
- 8.1 Independent Study (Project)
- Selecting an AI application relevant to civil, environmental, or construction engineering
- Conducting analysis or building a prototype using AI tools
- Preparing and delivering a short presentation including notebook demonstration
- Project – Domain-Specific AI Application
For more information, refer to course map
Course Materials
Required
In this course, you are required to have access to the following resources and tools:
- Foundational generative AI models such as GPT (OpenAI), Gemini (Google), or Claude (Anthropic)
- API key for at least one generative AI platform such as OpenAI API key for ChatGPT models for AI coding assistants
- Laptop with working installation of Python and Jupyter Notebook via miniconda or VS Code
- A Git account such as GitHub for managing and sharing code and notebooks
- Slides, supplementary materials, and videos are available on Canvas
Recommended textbooks
In addition to ChatGPT and Gemini, key references used in preparing course materials include:
- Module 1: Start Coding
- Module 2: Coding with AI
- Modules 3 to 5: Supervised Learning, Unsupervised Learning and Neural Networks:
- Module 6: Generative AI
- Module 7: Responsible AI
- Module 8: Domain-specific AI
- Lee T., V.P. Singh, and K.H. Cho (2021), Deep Learning for Hydrometerology and Environmental Science, 1st Ed, Springer: Open-access Link
Assessment and Grading
Grading scale
The instructor may elect to employ a curve that favors the students.
| Grade |
Range |
Grade |
Range |
Grade |
Range |
| A |
94% or above |
B- |
80% to 82.99% |
D+ |
67% to 69.99% |
| A- |
90% to 93.99% |
C+ |
77% to 79.99% |
D |
60% to 66.99% |
| B+ |
87% to 89.99% |
C |
73% to 76.99% |
F |
Below 60% |
| B |
83% to 86.99% |
C- |
70% to 72.99% |
|
|
Assessment plan (100%)
- Participation 10%
- Homework 60%
- Final Exam 30%
General notes
- If you are falling behind, consult the academic calendar for the last day to drop.
- Incomplete grades are granted in exceptional circumstances (e.g., medical emergency)
Participation
For participation assessment, students are expected to:
- Watch recorded videos and fill-out exit tickets and participation activities
- Complete the survey at the end of each module meaningfully to provide instructor with constructive feedback and suggestions
These form the majority of your participation grade.
Homework
A weekly homework will be posted on Canvas. Each assignment is due by Sunday at 11:59 pm, unless otherwise posted on CANVAS. Few assignments are designed to include self-directed learning opportunities. This is to give you the opportunity to explore and experiment with engineering problems of your interest.
Late Homework Policy
- If you encounter challenges that may affect your ability to submit on time, please communicate with the instructor as early as possible to explore possible accommodations.
- Deadline maybe extended for execused absences
- Unexecused late submissions received after the deadline will incur a penalty of 20% per day of the total possible points
- Once the solutions and grades are posted, late unexecused submissions will not be accepted, and a score of zero will be assigned
Exam
- A final comprehensive exam will be in-person, conducted with pencil and paper in FE exam format.
- The exam will cover mandatory modules (Modules 1 to 7).
- The exam is one hour and consists of about 60 multiple-choice questions.
- The exam is open-book but no internet access is allowed.
- Only FE-approved calculators are permitted. That is a regular calculator and not a smart calculator or smart phone that is connected to the internet. Laptops are allowed as long as there is no internet access. Any form of internet access is prohibited.
- Study guide: If you can solve the exercises, practice problems, and homework, you will be prepared for the exam.
- Receiving or providing unauthorized assistance, including using the internet, will result in a grade of zero on this exam. The academic dishonesty policy will apply.
- A makeup exam may be provided for students with an execused absence
Execused Absence Policy
- Absence excuse requires written documentation from a certified medical professional, faculty member, administration, coach, or athletic director.
- Absence will be execused after the verification of the submitted document
- Any attempt to falsify documents will be taken very seriously in accordance with FGCU policies and procedures
Generative AI Use
Use of generative AI tools (e.g., ChatGPT, Gemini, Perplexity, Consensus) is prohibited on any assignment, quiz or exam marked “AI Not Permitted” and will result in a grade of zero. For all other work, AI use must be cited. Violations will be treated as academic dishonesty and will be subject to Policy for Academic Integrity Violations.
Policy for Academic Integrity Violations
- Academic dishonesty in assignments, projects, or exams will result in a grade of zero for that submission, and will be strictly addressed in line with FGCU policies and procedures.
- Familiarize yourself with the FGCU Student Guidebook that outlines the consequences for academic integrity violations.
Financial Aid Statement
As of fall 2015, all faculty members are required to use Canvas to confirm a student’s attendance for each course by the end of the first week of classes. Failure to do so will result in a delay in the disbursement of your financial aid. The confirmation of attendance is required for all students, not only those receiving financial aid.
Core Syllabus Policies
FGCU has a set of central policies related to student recording class sessions, academic integrity and grievances, student accessibility services, academic disruption, generative AI, and religious observances that apply to all courses at FGCU. Be sure to review these online
This link provide information on FGCU Writing lab, access to high performance computing (HPC) resources, program learning outcomes and other useful resources.
Syllabus Change Policy
Except for changes that substantially affect implementation of the evaluation (grading) statement, this syllabus is a guide for the course and is subject to change with advance notice.