Course Syllabus

Jump to Today

DCP4300: Artificial Intelligence in the Built Environment

Welcome!! Please carefully review the syllabus below. 

3 credits 

INSTRUCTOR

Dr. Vivian Wong, Assistant Professor, M.E. Rinker Sr. School of Construction, Department of Urban and Regional Planning (web profile)

COURSE MEETING TIMES: Tuesdays Period 7 - 9 (1:55 AM - 4:55 PM)

CLASSROOM: RNK 0106 (Rinker Hall, 573 NEWELL DR, GAINESVILLE, FL 32611)

OFFICE HOURS: 30 minutes following the in-class lectures in RNK 0106| (or) Tuesdays/Thursdays 12:30 PM - 1:30 PM by appointment. Book appointments 24 hours in advance through this link here. Additional open door OH Wednesdays 1-4 pm in ARCH 446. 

COURSE COMMUNICATION: All communication with course faculty will take place within Canvas, through the Inbox.  Please direct any questions to both instructors via the Inbox, and the instructor responsible for the relevant module will respond. All correspondence will be sent and received within Canvas.  You should NOT be emailing the course instructor outside of the system. The instructor is also available for a Zoom meeting by appointment. Please contact the instructor through the Inbox to arrange a meeting.

NO REQUIRED TEXTBOOK (Recommended readings listed below)

  1. VanderPlas, J. (2016). Python data science handbook: Essential tools for working with data. O'Reilly Media, Inc. GitHub link here. 
  2. Bishop, C. M. (2006). Pattern recognition and machine learning. GitHub link here. 
  3. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning: MIT press Cambridge.

CODING and Course Objectives

This course uses Python as the programing language. Students are expected to use Google Colab in the lab sessions. You don’t need to install Python and other libraries on your laptop because Colab provides a standardized coding platform. Upon successful completion of this course and its Python coding modules, students will be able to:

COURSE DESCRIPTION

This course introduces how to investigate the built environment with artificial intelligence (AI). The course consists of three modules with Module 1 focused on computational basics, Module 2 on diverse data in built environment, and Module 3 on AI techniques. Specifically, Module 1 introduces Python, GitHub, Google Colab, among other computational toolboxes. Module 2 presents diverse data sources, including the conventional data, such as census and travel survey, and the unconventional data, such as imagery, networks, and texts. Module 3 introduces four dominant AI models, including artificial neural networks (ANN) for numeric data, convolutional neural networks (CNN) for imagery, graph neural networks (GNN) for spatial networks, and LSTM and large language models (LLM) for texts. Students will learn the major Python packages, e.g., Pandas, GeoPandas, PyTorch, thus processing and analyzing the conventional and unconventional data structures. Through reading materials, students will also learn AI as a general analytical framework for economic development, urban mobility, sustainability, energy consumption, design, and community development. This course focuses on enhancing students’ hands-on experiences in AI for built environment, and empowering designers, planners, engineers, and data scientists to leverage AI to dissect cities and tackle enduring challenges in the built environment.

PREREQUISITE KNOWLEDGE OR SKILLS

No prerequisite course is needed. However, students need to take Practicum AI at UFL as a concurrent requirement. The prior Python coding skills are encouraged, and the prior knowledge in probability, statistics, and linear algebra can also facilitate your learning experiences. If you have questions, please contact the instructor to discuss your qualification. This course is the prerequisite for the Intermediate Urban Analytics in the Spring term.

COURSE POLICIES

ATTENDANCE POLICY

Students are responsible for satisfying all academic objectives as defined by the instructor. Absences count from the first class meeting. In general, acceptable reasons for absence from or failure to participate in class include illness, serious family emergencies, special curricular requirements (e.g., judging trips, field trips, and professional conferences), military obligation, severe weather conditions, religious holidays, and participation in official university activities such as music performances, athletic competition or debate. Absences from class for court-imposed legal obligations (e.g., jury duty or subpoena) must be excused. Other reasons also may be approved.

Students shall be permitted a reasonable amount of time to make up the material or activities covered in their absence.

Students cannot participate in classes unless they are registered officially or approved to audit with evidence of having paid audit fees. The Office of the University Registrar provides official class rolls to instructors.

Requirements for class attendance and make-up exams, assignments, and other work in this course are consistent with university policies that can be found at:  

https://catalog.ufl.edu/ugrad/current/regulations/info/attendance.aspx

 

HOMEWORK ASSIGNMENT POLICY

Please refer to the course schedule in Canvas for all due dates. There are 3 problem sets (psets) that are due throughout the semester.

MAKE-UP POLICY

Students shall be permitted a reasonable amount of time to make up the material or activities covered in their absence, if the absence is due to the one of accepted reasons listed in the Attendance Policy.

If you are unable to turn in an assignment on time, please contact me before the due date to discuss your options. A grade reduction of 5% per day (equivalent to 3pts for a 15pt pset) will occur unless there is an acceptable excuse for the late submittal.

Computer problems that arise during submission will not be accepted as an excuse for late work. In the event that you have technical difficulties with e-Learning, please contact the UF Help Desk. If technical difficulties cause you to miss a due date, you MUST report the problem to Help Desk. Include the ticket number and an explanation of the issue based on consult with Help Desk in an e-mail to the instructor to explain the late assignment/exam. The course faculty reserves the right to accept or decline tickets from the UF Help Desk based on individual circumstances.

COURSE TECHNOLOGY

This course uses Python as the programing language. Students are expected to use Google Colab in the lab sessions. You don’t need to install Python and other libraries on your laptop because Colab provides a standardized coding platform.

COMPUTER REQUIREMENTS

Students will need a computer that has access to internet and a browser. 

UF POLICIES

SPECIAL ACCOMMODATIONS

Students requesting disability-related academic accommodations must first register with the Disability Resource Center (Links to an external site.).

The Disability Resource Center will provide documentation to the student who must then provide this documentation to the instructor when requesting accommodation.

UNIVERSITY POLICIES

University policies on such matters as add/drop, incomplete, academic probation, termination of enrollment, reinstatement, and other expectations or procedures can be found in the graduate student handbook (Links to an external site.) and at the Dean of Students website (Links to an external site.).

UNIVERSITY POLICY ON ACADEMIC MISCONDUCT

Academic honesty and integrity are fundamental values of the University community. Students should be sure that they understand the UF Student Honor Code (Links to an external site.).

STUDENT HONOR CODE

In adopting this Honor Code, the students of the University of Florida recognize that academic honesty and integrity are fundamental values of the University community. Students who enroll at the University commit to holding themselves and their peers to the high standard of honor required by the Honor Code. Any individual who becomes aware of a violation of the Honor Code is bound by honor to take corrective action.

Student and faculty support are crucial to the success of the Honor Code. The quality of a University of Florida education is dependent upon the community acceptance and enforcement of the Honor Code (Links to an external site.).

The Honor Pledge: We, the members of the University of Florida community, pledge to hold ourselves and our peers to the highest standards of honesty and integrity by abiding by the Honor Code.

On all work submitted for credit by students at the University of Florida, the following pledge is either required or implied: "On my honor, I have neither given nor received unauthorized aid in doing this assignment."

CLASS DEMEANOR OR NETIQUETTE

Course communication should be civilized and respectful to everyone. All members of the class are expected to follow rules of common courtesy in all e-mail messages, threaded discussions and chats. The means of communication provided to you through e-Learning (e-mail, discussion posts, course questions, and chats) are at your full disposal to use in a respectful manner. Abuse of this system and its tools through disruptive conduct, harassment, or overall disruption of course activity will not be tolerated. Conduct that is deemed to be in violation with University rules and regulations or the Code of Student Conduct will result in a report to the Dean of Students.

Refer to the Netiquette Guide for Online Courses (Links to an external site.) for more information.

Accessing University Academic Policies and Campus Resources
To support consistent and accessible communication of university-wide student resources, please use this link to academic policies and campus resources: https://go.ufl.edu/syllabuspolicies.

STUDENT SUPPORT SERVICES

As a student in a distance learning course or program, you have access to the same student support services that on-campus students have. For course content questions contact your instructor.

For any technical issues you encounter with your course please contact the UF computing Help Desk at 342-392-HELP (4357). For Help Desk hours visit: http://helpdesk.ufl.edu (Links to an external site.).  For a list of additional student support services links and information please visit: http://www.distance.ufl.edu/student-services (Links to an external site.).

GRADING POLICIES

COURSE GRADE

Summary:

Component

Percent of Grade

Problem Set (pset) Assignments

45%

Attendance (if a lecture contains a lab, must upload completed lab to Gradescope to qualify as full attendance)

10%

Final Project

  1. Idea (5%). Limit to 1 page.
  2. Proposal (10%). Limit to 3 pages.
  3. Final paper (20%). Limit to 8 pages.
  4. Poster presentation of the final paper (10%).

45%

 

GRADING SCHEME

Letter Grade

Percentage

Grade Points

A

93-100%

4.00

A-

90-92%

3.67

B+

88-89%

3.33

B

83-87%

3.00

B-

80-82%

2.67

C+

78-79%

2.33

C

73-77%

2.00

C-

70-72%

1.67

D+

68-69%

1.33

D

58-67%

1.00

D-

55-57%

0.67

E

Below 55%

0.00

For greater detail, see the Grades section of the Graduate Catalog for the University of Florida (Links to an external site.). It also contains the policies and procedures, course descriptions, colleges, departments, and program information for UF.

Expectations on COVID-19 Relevant Practices

In response to COVID-19, the following practices are in place to maintain your learning environment, to enhance the safety of our in-classroom interactions, and to further the health and safety of ourselves, our neighbors, and our loved ones.  

  • If you are not vaccinated, get vaccinated. Vaccines are readily available at no cost and have been demonstrated to be safe and effective against the COVID-19 virus. Visit this link for details on where to get your shot, including options that do not require an appointment: https://coronavirus.ufhealth.org/vaccinations/vaccine-availability/. Students who receive the first dose of the vaccine somewhere off-campus and/or outside of Gainesville can still receive their second dose on campus.  
  • You are expected to wear approved face coverings at all times during class and within buildings even if you are vaccinated. Please continue to follow healthy habits, including best practices like frequent hand washing.  Following these practices is our responsibility as Gators.  
    • Sanitizing supplies are available in the classroom if you wish to wipe down your desks prior to sitting down and at the end of the class. 
    • Hand sanitizing stations will be located in every classroom. 
  • If you are sick, stay home and self-quarantine. Please visit the UF Health Screen, Test & Protect website about next steps, retake the questionnaire and schedule your test for no sooner than 24 hours after your symptoms began. Please call your primary care provider if you are ill and need immediate care or the UF Student Health Care Center at 352-392-1161 (or email covid@shcc.ufl.edu) to be evaluated for testing and to receive further instructions about returning to campus. UF Health Screen, Test & Protect offers guidance when you are sick, have been exposed to someone who has tested positive or have tested positive yourself. Visit the UF Health Screen, Test & Protect website for more information. 
    • Course materials will be provided to you with an excused absence, and you will be given a reasonable amount of time to make up work. 
    • If you are withheld from campus by the Department of Health through Screen, Test & Protect you are not permitted to use any on campus facilities. Students attempting to attend campus activities when withheld from campus will be referred to the Dean of Students Office.
  • Continue to regularly visit coronavirus.UFHealth.org and coronavirus.ufl.edu for up-to-date information about COVID-19 and vaccination. 

COURSE SCHEDULE

CRITICAL DATES

This course includes 3 modules that are covered over a 15 week semester. Please be aware of the course schedule and critical dates below.

WEEKLY SCHEDULE OF TOPICS AND ASSIGNMENTS

Week 

Dates

Lectures

Lab sessions

Psets

Project

1

Aug 26

Class overview

Module 1. Computational Basics

2

Sep 02

Python, Colab, and data sources 

Lab 01. Getting started with Colab
Lab 02. Python Basic Computations in Colab 

3

Sep 9

Python, GitHub, and data processing

Lab 03. Data collection and processing 

Module 2. Diverse Data Sources

4

Sep 16

Data description and visualization

Lab 04. Matplotlib, Seaborn, and Pandas

5

Sep 23

Tabular data analysis and predictions

Lab 05. Pandas, Linear Regression and plotting scatterplots

pset 1 out

6

Sep 30

Images and videos

Lab 06. Viewing your own video

Idea guidance out;

7

Oct 07

Network and Text data

Lab 07. Tokenize

pset 1 due

8

Oct 14

Integrating your own data into an AI project with PyTorch Dataset/DataLoader

Lab 08. Complicating Lab 06-07 with Dataset/DataLoader 

 

Idea due;

Module 3. AI Methods and Applications to Built Environment

9

Oct 21

 Class cancelled - Canvas Outage

10

Oct 28

Modeling basics and artificial neural networks

Lab 09. Predicting property values

pset 2 out

Milestone guideline out

 

11

Nov 04

Convolutional neural networks for urban imagery

How do large language models (LLMs) work and how they can help or break me? A demo of "vibe coding".

Guest speaker: Dr. Zhaoxi Zhang on ChatBot applications to Urban Data

Lab 10. Dissecting satellite imagery & Semantic segmentation for street-view images

 

 

12

Nov 11

Veteran's Day (no class) 

 

pset 2 due

pset 3 out

Milestone due.

Final report guidance out. 

Module 4. Final Project

13

Nov 18

Reinforcement Learning + Everything everywhere all at once: a comprehensive review

Guest speaker: Austin Commercial on AI in Construction Tech.

NA

pset 3 due

14

Nov 25

15

Dec 02

Final Project Poster Presentation 

Final project poster and final report due

Disclaimer:

This syllabus represents my current plans and objectives.  As we go through the semester, those plans may need to change to enhance the class learning opportunity.  Such changes, communicated clearly, are not unusual and should be expected.

Four Required Reading Tasks

  1. Week 5 (Required). Newman, P. W., & Kenworthy, J. R. (1989). Gasoline consumption and cities: a comparison of US cities with a global survey. Journal of the American Planning Association, 55(1), 24-37.
  2. Week 9 (Required). Wang, S., Mo, B., Hess, S., & Zhao, J. (2021). Comparing hundreds of machine learning classifiers and discrete choice models in predicting travel behavior: an empirical benchmark. arXiv preprint arXiv:2102.01130.
  3. Week 10 (Required). Jean, N., Burke, M., Xie, M., Davis, W. M., Lobell, D. B., & Ermon, S. (2016). Combining satellite imagery and machine learning to predict poverty. science, 353(6301), 790-794.
  4. Week 11 (Required). Xue, J., Jiang, N., Liang, S., Pang, Q., Yabe, T., Ukkusuri, S. V., & Ma, J. (2022). Quantifying the spatial homogeneity of urban road networks via graph neural networks. Nature Machine Intelligence, 4(3), 246-257.

 

Details in Course Schedule

Practicum AI provides a wonderful overview for using Python, Colab, GitHub, and other tools in computation. It is highly recommended for the students to read the materials.

Module 1. Computational basics

Module 2: Diverse Data Sources

Module 3: AI Applications

  • Python Scikit-learn for machine learning.
  • Unsupervised learning tutorial in Scikit-learn: https://scikit-learn.org/stable/unsupervised_learning.html
  • GitHub tutorials for Chapters 4, 5, and 7 for Bishop, C. M. (2006): https://github.com/gerdm/prml
  • Python PyTorch for deep learning.
  • Readings
    • (Required) Wang, S., Mo, B., Hess, S., & Zhao, J. (2021). Comparing hundreds of machine learning classifiers and discrete choice models in predicting travel behavior: an empirical benchmark. ArXiv:2102.01130.
    • (Required). Xue, J., Jiang, N., Liang, S., Pang, Q., Yabe, T., Ukkusuri, S. V., & Ma, J. (2022). Quantifying the spatial homogeneity of urban road networks via graph neural networks. Nature Machine Intelligence, 4(3), 246-257.
    • (Required). Jean, N., Burke, M., Xie, M., Davis, W. M., Lobell, D. B., & Ermon, S. (2016). Combining satellite imagery and machine learning to predict poverty. science, 353(6301), 790-794.
    • (Optional). Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531. 
    • (Optional). Wang, Q., Wang, S., Zheng, Y., Lin, H., Zhang, X., Zhao, J., & Walker, J. (2024). Deep hybrid model with satellite imagery: How to combine demand modeling and computer vision for travel behavior analysis? Transportation Research Part B: Methodological, 179, 102869. 
    • (Optional). Gebru, T., Krause, J., Wang, Y., Chen, D., Deng, J., Aiden, E. L., & Fei-Fei, L. (2017). Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States. Proceedings of the national academy of sciences, 114(50), 13108-13113.
    • (Optional). Zheng, Y., Lin, Y., Zhao, L., Wu, T., Jin, D., & Li, Y. (2023). Spatial planning of urban communities via deep reinforcement learning. Nature Computational Science, 3(9), 748-762.

Upcoming Assignments and Due Dates are listed below: 

Course Summary:

Course Summary
Date Details Due