Activity 2: combating future forest fires using K-means clustering and Apache Zeppelin¶
Design · All designs
Evidence · no claims cited
Description¶
A problem-based learning activity adapted from a forest fire prevention case study, in which students derive a resource allocation solution for wildfire response in Oregon using a frame-model-program-decide mode. "The K-means clustering algorithm is selected to partition the locations of historical forest fires into clusters", and cluster centroids assist in allocating firefighting infrastructure to regions most prone to burning. Students work with US forest fire data from 2000 to 2016 in the Apache Zeppelin web-based data science notebook.
Design Implications¶
Context¶
Requirements¶
- Teacher and technical assistant support when students encounter difficulty in programming work
- Teacher explanation of the rules and steps of algorithmic design
Constraints¶
- Assumes driving factors of past wildfire trends are not changed or reduced when predicting the future
Target Learners¶
- high school geography students
Learning Goals¶
- predicting wildfire occurrence from historical data
- making data-informed fire management and infrastructure investment decisions
Claims¶
Related Designs¶
Examples¶
-
Key Sources¶
- Xi Xiang & Michael E. Meadows. (2025). Being proactive about anthropogenic environmental changes: augmenting students' decision making with artificial intelligence (AI) technology. Education Tech Research Dev. https://doi.org/10.1007/s11423-025-10523-9
Page metadata
| Field | Value |
|---|---|
type |
design |
id |
activity-combating-future-forest-fires-kmeans |
title |
Activity 2: combating future forest fires using K-means clustering and Apache Zeppelin |
description |
A problem-based learning activity adapted from a forest fire prevention case study, in which students derive a resource allocation solution for wildfire response in Oregon using a frame-model-program-decide mode. |
status |
review |
generated |
by process:settle-candidates on 2026-10-29 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — xi-xiang-michael-e-meadows-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.