This course introduces advanced methods and technologies in urban analytics, such as urban simulation, and location intelligence in GeoAI (Geospatial Science + AI), to address challenges in sustainable urban development.

Students will gain hands-on experience with advanced analytical techniques using programming tools process, analyse, and visualize diverse datasets such as geospatial, textual, and image data. The course also covers the integration of advanced methods such as machine learning, deep learning and large-scale cloud-based data processing in urban analytics workflows.

By the end of the course, students will have practical expertise in state-of-the-art urban analytics tools. They will develop the technical expertise and critical thinking skills necessary for both academic research and industry applications, enabling them to contribute to evidence-based policymaking, smart city, and urban sustainability strategies.

Classes to run in Semester 2 and delivered in 3 hourly blocks, once per week, over 9 consecutive weeks. These would take place in the computer labs, and would combine lectures with supervised practical sessions.

Classes start from the fifth week of Semester 2.

None

None

Given the technically demanding nature of this course, it is essential to design assessments that distribute evaluation across multiple components, avoiding reliance on a single high-stakes assessment.

The summative assessment includes a project report including

■ Project output and Python scripts (35%, 2500 words), submitted after the teaching course, align with ILO (a,b,c,d)

■ Students will undertake an urban analysis project which requires them to demonstrate the skills which they have acquired during the course. This will be written up as a project markdown file with the scripts they have produced to do the analysis.

■ An oral presentation of the project (20%, 8min), submitted after the teaching course, align with ILO (a,b,c,d)

■ Students will record an oral presentation about the project justification and the project output.

■ Analytical practice exercise in the format of GitHub portfolio (15%*3=45%), submitted in the mid of the teaching course, align with ILO (a,b,c)

The summative assessment consists of three components, a project report, an oral presentation, and a GitHub-based analytical practice portfolio. These components are designed to test the Intended Learning Outcomes (ILOs) as outlined below.

1.Project Report (35%, 2,500 words)

Submission Time: After the teaching course
Format: A Markdown report including project output and Python scripts

Students will undertake an urban analysis project that requires them to apply the skills and knowledge acquired in the course. The project will be written up in a Markdown file, supported by the Python scripts used for the analysis.

This assessment tests each of the ILOs as follows

■ ILO (a): Demonstrated through a clear rationale also well-structured and justified design of the project.

■ ILO (b): Assessed by the effective application of data management techniques and the implementation of the designed analytical method.

■ ILO (c): Evaluated by the appropriate and effective use of data visualisations to communicate analytical results.

2. Oral Presentation (20%, 8 minutes)

Submission Time: After the teaching course
Format: A recorded presentation

Students will submit a recorded oral presentation summarising the project's justification, methodology, and key findings.

This assessment tests each of the ILOs as follows

■ ILO (d): Assessed by the ability to clearly summarise and present analytical results in an oral format.

3. Analytical Practice Exercises (GitHub Portfolio) (3 × 15% = 45%)

Submission Time: Midway through the teaching course
Format: GitHub repository with documented exercises

Students will deliver a series of analytical exercises based on course content. These exercises will be submitted via GitHub to demonstrate practical analytical techniques.

This assessment tests each of the ILOs as follows

■ ILO (b): Assessed by the accurate and effective implementation of the assigned exercises.

■ ILO (c): Evaluated through clear and effective visualisation and presentation of analytical results.

The course equips students with advanced knowledge and skills to tackle urban challenges using emerging data forms and machine learning (ML) and AI-enhanced analytical workflows. The aims of this course are:

a) Introduce advanced analytical tools for data wrangling, management, processing, and visualization, encompassing diverse data forms;

b) Develop analytics workflows by integrating ML and AI into urban data analysis;

c) Provide hands-on experience with tools to support advanced urban analytics applications and complex data-driven decision-making.

d) Enable students to apply analytical techniques to address policy and planning challenges, contributing to evidence-based, sustainable policymaking.

By the end of this course students will be able to:

a) Design and justify urban analytics workflows by integrating GeoAI, data management techniques, and advanced analytical methods.

b) Apply analytical skills to efficiently acquire, process, and manage large-scale datasets.

c) Utilize advanced analytical techniques to interpret large-scale of data and effectively visualize insights.

d) Develop and implement urban analytics workflows incorporating ML/AI methods to address urban, environmental, and location-based challenges, effectively communicating findings in both verbal and written formats.

Students must submit at least 75% by weight of the components (including examinations) of the course's summative assessment.