GEOG 885 - Analytical Methods and GEOAI in Geospatial Intelligence
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
GEOG 885 explores the challenges and opportunities created by combining human expertise with computational analysis methods in the field of geospatial intelligence (GEOINT). The course focuses on the science and technology of human-machine collaboration using geospatial artificial intelligence (GeoAI) in GEOINT and the professional and ethical concerns that must be considered as we move forward in this rapidly evolving field. Students completing this course will be able to explain and apply Structured Analytic Techniques (SATs), automation methods, and GeoAI tools in combination to solve geospatial intelligence problems. Students will create analysis workflows that ensure the efficiency, credibility, and accuracy of analytical insights. SATs are evaluated by students to gauge their ability to improve the quality and rigor of analysis. Students will also learn how to apply emerging GeoAI tools to summarize data and perform analytical tasks that have typically required human intelligence. GEOINT plays an increasingly critical role in supporting decision-making across a broad range of industries, from defense and intelligence to environmental monitoring and urban planning. The amount of geospatial data available today is overwhelming, but by leveraging the strengths of both humans and machines, we can gain deeper insights into high-dimensional spatial data and more effectively solve geographic problems. The course does not require any technical background, and it is open to students from all disciplines.
Objectives
Students who excel in this course are able to:
- LO-1: Apply the geospatial intelligence process including problem spatialization, recording, discovering, tracking, comprehending, and communicating analytic results.
- LO-2: Contrast the strengths and limitations of the human and machine in geospatial analysis.
- LO-3: Explain the professional and ethical considerations surrounding machine-driven analysis, automation, and GeoAI in geospatial intelligence analysis.
- LO-4: Elaborate about the application of human cognitive techniques (Structured Analytic Techniques), computational thinking, GeoAI and automation in geospatial analysis.
- LO-5: Compare the potential impact of human-machine collaboration on decision-making across different applications.
- LO-6: Apply critical thinking and problem-solving skills to analyze complex geospatial intelligence problems using a human-machine collaborative approach.
- LO-7: Defend the results of a geospatial analysis to decision-makers while safeguarding trust, credibility, and accuracy of analytic insights.
- LO-8: Articulate an understanding of emerging trends and future directions in human-machine collaboration for geospatial intelligence analysis.
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.
Required Textbooks
There is no required textbook for this course.
Required Software
ArcGIS Online StoryMap will be used and is free for registered students.
Prerequisites
None.
Expectations
Like any upper-level course, you will be challenged to move beyond the knowledge and skills that you bring to the class. You can expect to be busy; as rough estimate, you should allow 12-15 hours per week for class assignments. You'll be glad to know that you don't need to show up for class at a certain time! All you need to do is complete assignments before the published deadlines each week.
Major Assignments
9 Case Study Discussions: (30%)
Each week, we will provide you with a real-life case study along with some resources to get you started thinking about it. You will read the documents, do your own research, and discuss your thoughts, and some specific prompts with your classmates.
2 Reflection Papers: (20%)
These are 500 word essays of your thoughts about an article, video, concept, etc. expressing your personal experiences and/or thoughts about the concepts put forth in lessons 2 and 8.Capstone: (Total of 50% divided among several types of assignments described below).
1 Capstone (50%)
The capstone challenges you to work collaboratively and apply the GEOINT process tasks and double-loop approach that is introduced in Lesson 1. You will explore the complexities of human-machine teaming using a real-world problem and investigate the case from two different methodological perspectives. It is split into four different types of assignments.
- 6 weekly individual written responses to a prompt related to the capstone project. (25%)
- 6 weekly team project note contributions in the form of an ArcGIS StoryMap. The goal here is to help you progressively work on, and receive feedback on, the final StoryMap and video presentation. (5%)
- 1 final team video presentation related to the problem using a revised StoryMap your team created throughout the semester. (20%)
Course Schedule
| Week | Topic | Assignment |
|---|---|---|
| 0 | Orientation |
|
| 1 | Course Introduction, Ethics and Standards in Intelligence Analysis |
|
| 2 | Humans and Machines |
|
| 3 | Problem Spatialization |
|
| 4 | Recording Spatial Data |
|
| 5 | Spatial Discovery |
|
| 6 | Tracking Phenomena in Space and Time |
|
| 7 | Comprehending Results |
|
| 8 | Competing Human & Machine Methodologies |
|
| 9 | Communicating Insights |
|
| 10 | Capstone Report and Presentation |
|