This talk presents a practical approach to analyzing urban sprawl using open-source geospatial tools in a reproducible workflow. The focus is not on introducing new algorithms, but on demonstrating how existing tools can be effectively combined to address real-world challenges.

The session will walk through a simplified workflow built on Open Data Cube and Python in a Jupyter Notebook environment. It will cover key steps including satellite data preparation, classification using Random Forest, and the use of spatial metrics such as Shannon Entropy and Urban Expansion Intensity Index (UEII) to interpret urban growth patterns.

Using a case study from Indonesia, the talk highlights how this workflow can be applied in regions where technical and computational resources are limited. Special attention is given to reproducibility, showing how the process can be adapted and reused in different contexts.

In addition, the talk will briefly discuss practical challenges encountered during implementation, including data handling, model limitations, and workflow simplification, along with strategies used to address them. This makes the session relevant not only for researchers, but also for practitioners and students interested in applied geospatial analysis using open-source tools.