GEOG 582 - AI in Spatial Data Science
This is a sample syllabus.
This sample syllabus is a representative example of the information and materials included in this course. Information about course assignments, materials, and dates listed here is subject to change at any time. Definitive course details and materials will be available in the official course syllabus, in Canvas, when the course begins.
Overview
In today's data-driven world, the power of artificial intelligence (AI) and GeoAI is transforming how we understand and interact with the spatial aspects of our environment. This course comprehensively introduces the cutting-edge methods and technologies that combine AI with geospatial data science. Starting with the fundamentals of AI, machine learning, and deep learning, you'll understand the theory of AI, gain practical skills in Python programming, and use the latest methods and tools to resolve real-world geospatial challenges.
This course is designed to equip you with theoretical and practical knowledge that's indispensable in today's world. As GeoAI continues to reshape the industries that rely on geospatial insights, you'll gain knowledge in this course that will provide endless opportunities for you to innovate, solve global challenges, and work toward thriving in your future careers.
Objectives
Students who excel in this course are able to:
- Evaluate and justify the selection of the appropriate artificial intelligence methods to complete spatial data science analysis tasks.
- Create workflows that integrate artificial intelligence approaches with spatial analysis methods to address key problems in spatial data science.
- Develop scientific programming skills that integrate state-of-the-art coding practices in support of advancing the AI-supported spatial data science.
- Synthesize, analyze, and visualize multiple types of spatial data using artificial intelligence methods in support of complex problem-solving.
Required Materials
The materials listed here represent those that may be included in this course. Students will find a definitive list in the course syllabus, in Canvas, when the course begins.
Recommended Textbooks
- Michael Schmandt (2009): GIS Commons: An Introductory Textbook on Geographic Information Systems (free textbook at https://giscommons.org/)
- Aurlien Gon (2019): Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems.
Prerequisites
No prerequisite requirements. However, knowledge and experience in Python and R programming is highly recommended.
Software Environments:
- Anaconda
- Jupyter Notebook
- Google Colab
- ChatGPT
Expectations
We have worked hard to make this the most effective and convenient educational experience possible. How much and how well you learn is dependent on your attitude, diligence, and willingness to ask for clarifications or help when you need them. We are here to help you succeed. Please keep up with the class schedule and take advantage of opportunities to communicate with us and with your fellow students. You can expect to spend an average of 12 – 15 hours per week on class work.
In this course, students are expected to actively engage with both the theoretical and practical components of AI and GeoAI. As part of the learning experience, you will:
- Develop a solid understanding of AI, machine learning, deep learning, and their applications within geospatial data science. This includes both learning the theory and gaining hands-on experience with Python programming.
- You will work on real-world case studies and projects where AI models are used to analyze and interpret spatial data.
- Gain experience in integrating LLMs into geospatial workflows, exploring how these powerful tools can enhance decision-making processes in geospatial tasks.
- Collaboration will be key as you explore AI solutions to current geospatial challenges. You are encouraged to work with peers, share insights, and think creatively about how AI can address real-world issues.
- Through project-based learning, you will develop a course lab project based on your domain of expertise and apply the knowledge you learn in this course to solve problems.
To succeed, students should be ready to engage with coding assignments, work through complex datasets, and actively participate in discussions. By the end of the course, you will be equipped with in-demand skills and a strong foundation in the rapidly evolving fields of AI in geospatial data science.
Major Assignments
Students earn grades that reflect the extent to which they achieve the learning objectives listed above. Opportunities to demonstrate learning include the following, and grades will be based on points assigned to each of several components of the course as follows:
- Laboratory Assignments (40%)
- Discussions (25%)
- Trainings (25%)
- Quizzes (10%)
Course Schedule
| Week | Topic | Assignment |
|---|---|---|
| 0 | Orientation |
|
| 1 | Lesson 1: Introduction to AI and GeoAI |
|
| 2 | Lesson 2: Fundamentals in Python Programming |
|
| 3 | Week 3 Lesson 3: Machine Learning Basics |
|
| 4 | Lesson 4: Deep Learning Basics |
|
| 5 | Lesson 5: Deep Learning Advanced |
|
| 6 | Lesson 6: Generative Models |
|
| 7 | Lesson 7: Geoparsing |
|
| 8 | Lesson 8: Location Encoding |
|
| 9 | Lesson 9: LLM Applications |
|
| 10 | Lesson 10: LLM Applications (continued) |
|