Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Finding, checking, documenting and acquiring spatial data for your SDS320 project

1. Context

In the first project weeks, you move from a broad topic toward a feasible spatial question. This lesson focuses on the next critical step: finding data that can actually answer that question.

In SDS, data acquisition is not only downloading files. It includes searching for suitable datasets, checking whether they match your area and time period, understanding formats and licences, inspecting quality, and documenting what you selected.

This lesson sits between project planning and preprocessing. After this lesson, you should be able to create a first data inventory and decide whether your project idea is realistic with the data you can access.


2. Motivation

Many spatial data science projects fail because the data decision is made too late. A method may sound promising, but it only works if the required data exist, are accessible, have suitable resolution and can be processed in time.

For GeoAI projects, this matters even more. Remote Sensing data differ in spatial resolution, spectral bands, temporal coverage, cloud cover, licensing and file size. Vector Data can provide context, training labels, validation data or features for interpretation, but it also needs careful checking.

So, the big project question is:

Which data are suitable enough for my question, method, output and time budget?

3. Learning objectives

By the end of this lesson, you should be able to:


4. Lesson roadmap

Work through the pages in this order:

  1. Finding suitable spatial data — define what “suitable data” means for your project and create a first data inventory.

  2. Working with remote sensing data — use STAC-based search logic to find imagery such as Sentinel-2, Landsat, NAIP or SWISSIMAGE.

  3. Adding vector and contextual data — explore vector sources such as Overture Maps and other context data that can support your analysis.

  4. Citing and documenting data — record data provenance, licences, limitations and reuse conditions.

  5. Project transfer — turn the lesson into a concrete data acquisition plan for your own project.


5. Project framing

As you read, keep your own project in mind.

Use these guiding questions:


6. Before class

Before class, prepare the following:


7. After this lesson

After completing this lesson, you should have:

This does not need to be final. The goal is to move from “I might use this data” to “I know what I need to check next.”