Resources

1. Course platforms¶

SDS320 uses a small number of course platforms. Each has a specific role.

Jupyter Book¶

The course website is the central reference for SDS320:

https://hendrikwulf.github.io/sds320-jb/

It contains the course information, setup instructions, weekly lessons, project handbook, project gallery and reference pages.

You should consult the Jupyter Book regularly, as the material may be updated during the semester.

MS Teams¶

MS Teams is the central communication platform for SDS320.

It is used to:

• share course materials and information,

• ask and answer questions,

• discuss projects and technical issues,

• submit presentations and the final project report.

The MS Teams class is called 26HS SDS320 - Spatial Data Analytics.

For questions related to lessons, projects and presentations, use the appropriate Teams channel. This helps everyone benefit from the discussion and reduces duplicate questions.

OLAT¶

OLAT is used only to provide the course syllabus. All other course-related communication takes place on MS Teams.

2. Technical resources¶

The following types of resources may be useful while working on SDS320 projects.

Start with the course material and then use external documentation when you need more detail.

Python and Jupyter¶

Use these resources when you need to reactivate basic Python concepts, notebooks or package usage.

• official Python documentation

• Jupyter documentation

• SDS210 GeoPython

Git and repositories¶

Use these resources when you need help with Git, GitHub or GitLab workflows.

• Git documentation

• GitHub and GitLab documentation

• See also: Git basics

• See also: Repository

Geospatial Python¶

Use these resources when working with vector data, raster data, maps or spatial workflows.

• GeoPandas documentation

• Rasterio documentation

• Xarray / Rioxarray documentation

• Leafmap / Folium documentation

Machine learning and GeoAI¶

Use these resources when working with classification, object detection, segmentation, regression, foundation models or satellite embeddings.

• scikit-learn documentation

• PyTorch documentation

• TorchGeo documentation

Related courses, materials and platforms¶

• GeoAI by Qiusheng Wu

• GeoAI Tutorial Videos

• Geospatial Python Tutorials by Spatial Thoughts

• Hugging Face

• kaggle

3. Project resources¶

For project work, the most important internal resources are:

• Project handbook — guidance from project idea to final report and presentation.

• Assessment — official overview of assessment components and expectations.

• Reference — glossary, cheatsheets, common errors, datasets and further reading.

4. Asking meaningful questions¶

Good questions are easier to answer and more useful for others.

When asking for help, include:

• the page, task or project step you are working on,

• what you tried,

• what you expected,

• what happened instead,

• the full error message if there is one,

• a short code snippet or screenshot if useful,

• what you already checked.

A good technical question provides enough detail to enable the issue to be reconstructed. Here is an example:

I am working on the data preprocessing page (include link) and trying to reproject my GeoDataFrame.
I expected the output CRS to be EPSG:2056, but it remains EPSG:4326.
Here is the code I ran, the output I got, and the error/warning message.

5. Keeping resources manageable¶

It is easy to open too many resources at once. Start with the course material and official documentation. Use videos, blogs, forums and AI tools selectively when they help you solve a specific problem.

The goal is not to collect links. The goal is to make progress on your project and understand the decisions you make.