Type of Credit: Elective
Credit(s)
Number of Students
This course on Spatial Decision Making introduces students to the principles and tools of decision theory through a hands-on approach. The course begins with simple, non-spatial decision problems to build a foundation in structured decision-making, using techniques such as multi-criteria analysis, weighting methods, and regression models.
The second half of the course emphasizes applied problem-solving using Geographic Information System (GIS) software and its integrated modeling tools. Students will engage in practical labs focused on real-world spatial challenges—such as facility sites and infrastructure planning, identifying hazard zones, or evaluating land-use policy scenarios. Along the way, students explore how Spatial Decision Support Systems (SDSS) are built, adapted, and assessed to meet different decision-making needs.
Machine learning methods incorporating decision trees, logistic regressions and clustering are introduced in the context of detecting and analyzing patterns in decision behaviors. In addition, spatial machine learning models and feature ranking strategies offer a state-of-the-art complement to classical analytical approaches.
By the end of the course, students will not only know how to use GIS and its integrated tools, but also how to design and evaluate spatial decision workflows from the ground up and how to critically assess the decision process in terms of robustness.
能力項目說明
Students will learn about existing spatial decision-making projects from the literature, learn how to select useful projects, collect and model data, how to develop workflows and how to arrive at conclusions based on a set of variables and their critical assessment and judgment.
They will be able to create a targeted decision making system from scratch using Geographic Information System software and their own spatial data model.
Classes are 3 hours and take place in the GIS lab (270610).
Due to the practical nature of this course, we will follow a hybrid approach with mixed theory and practice.
This course and all handout/upload material are provided in English, therefore a basic command of the English language will be required.
Also, a basic understanding of spatial data and a feeling for spatial information and relationships are of advantage. Basic knowledge of, and experience with (a) GIS and (b) database management systems are welcome but not required.
| Week | Topic | Content and Reading Assignment | Teaching Activities and Homework |
|---|---|---|---|
| 1 | Course Introduction | Course organization and contents overview. Reading of handout material. | First simple multi-criteria decision making process with exercises. |
| 2 | Decision Making Processes | Definition and basics of decision making. Introductory reading of course script. | Examining various MCDM methods with comparative exercises. |
| 3 | Decision Making Processes | Definition and basics of decision making. Introductory reading of course script. | Introduction of Fuzziness in the Evaluation Process with exercises. |
| 4 | Decision Making Systems | Coverage of major decision-making platforms in the spatial domain. | Investigation of spatial decision making in the literature and available on web platforms. Homework focuses on the identification of various types. |
| 5 | Public Holiday | ||
| 6 | Public Holiday | ||
| 7 | Model Components | Conceptualizing a decision-making system with its subsystems. | Developing a strategy for and EIA and SDG spatial MCDM solution from scratch. Homework will focus on the extraction of relevant parameters. |
| 8 | Mid-Term Exam Week | ||
| 9 | System Requirements | Standard requirements and SRS documents. | Developing a strategy for and EIA and SDG spatial MCDM solution from scratch. |
| 10 | System Requirements | Definition of standard requirements and formulating SRS documents. Reading of SRS specification standards. | Developing a strategy for and EIA and SDG spatial MCDM solution from scratch. Homework will focus on the extraction of relevant parameters. |
| 11 | Data and Variables | Search, priming and integration of data from public sources. | Data search, assessment, priming and integration in class with finalization of process as homework. Application of pre-trained AI models to extract land-cover information. |
| 12 | Definition of Workflows | Development of workflows using spatial modeling software. | Coverage of spatial modeling tools and limitations, developing basic workflows with finalization as homework. |
| 13 | Definition of Workflows | Development of advanced workflows using spatial modeling software, use of iterators. | Coverage of spatial modeling tools and limitations, developing advanced workflows with finalization of model as homework. |
| 14 | Assessments and Optimization | Accuracy assessments and evaluation, methods and explanatory AI | Discussion of which assessment methods will be integrated. |
| 15 | Project Use Case | Performing in-depth analyzes using a use-case from and Environmental Impact Assessment (EIA) | Project introduction and lab exercise on the integration of a solution given pre-defined criteria and potential locations. |
| 16 | Final Exam Week | Development of Multicriteria Decision Making Project | Project introduction and lab exercise on the integration of a solution given pre-defined criteria and potential locations. |
This course has a midterm and final exam.
Homework assignments and bonus exercises will help to consolidate the obtained knowledge.
All relevant material will be distributed during class.
There is currently no suitable textbook on the market for spatial decision making (plenty for decision making in general), and those that provide some background detail on this dynamic topic are outdated. The following contribution comes closest to the course aims and if you find it online or as hardcopy in a library, it does not hurt to take a look. All other material will be provided in class.
Sugumaran R, Degroote, J (2010): Spatial Decision Support Systems: Principles and Practices. - 469 pp, CRC Press. ISBN: 9781420062120.