Lesson plan

AI-2: Mapping Terrain

Students collect aerial forest photos to build a dataset, exploring how unsupervised AI spots anomalies like illegal logging and tree disease.

AI-2: Mapping Terrain
Ages
Ages 8-10
Duration
45 min
Essential question

How can unsupervised machine learning use visual datasets to detect environmental damage in remote forests?

Overview

In this lesson, learners join a scientific aerial expedition to photograph remote forest landscapes. By gathering photographic records, students explore how large collections of visual data can train artificial intelligence to recognize the typical appearance of healthy woodlands.

Using Minecraft, students fly over terrain to compile image data and observe how unsupervised machine learning detects unusual changes. The AI scans datasets for environmental anomalies, such as shifting color patterns or expanding clearings, helping conservationists address threats like tree disease, wildfire risks, and illegal timber harvesting.

Learning objectives

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

  • Collect and organize photographic images to assemble an environmental dataset
  • Explain how unsupervised machine learning determines what a healthy forest looks like
  • Identify how machine learning models detect anomalies such as tree disease and illegal logging
  • Describe how AI-assisted conservation helps protect delicate ecosystems

Blocks and items used in this lesson

Key vocabulary

Dataset
A structured collection of data or photographs gathered for analysis by a computer.
Unsupervised Machine Learning
A type of AI learning where the computer finds patterns in data without pre-labeled answers.
Anomaly
Something that deviates from what is standard, normal, or expected in a dataset.

Before class

Lesson sequence

Suggested timing: about 45 minutes in total.

  1. Introduction: The Aerial Mission10 min

    Introduce the expedition scenario where students act as researchers, engineers, and scientists. Present the lesson slides to explain how visual datasets allow unsupervised machine learning to understand typical forest patterns.

  2. Activity 1: Flying High10 min

    Students launch into the Minecraft world, taking flight over remote wilderness areas to capture aerial imagery of the terrain below.

  3. Activity 2: Mapping Everything Out10 min

    Learners organize their collected photos into a working dataset, observing how large volumes of visual records establish a baseline of normal forest conditions.

  4. Activity 3: Detecting Anomalies8 min

    Students examine how the AI analyzes the dataset to spot unexpected discrepancies, such as discolored vegetation, spreading desolate ground, or displaced wildlife.

  5. Activity 4: Problem Solving & Reflection7 min

    Teams discuss how detecting illegal logging or forest disease early allows conservation teams to intervene, reviewing the Terrafuse case study on wildfire prevention.

Assessment: success criteria

  • Student accurately explains that the AI detects problems by comparing normal forest baselines to unexpected visual discrepancies.
  • Student articulates why early identification of illegal logging is critical for preventing severe ecosystem disruption.
  • Student successfully completes the in-world aerial photography and data mapping tasks.

Differentiation

Support

Walk through the flight controls and photo collection steps together using the classroom presentation slides.

Stretch

Ask learners to consider other real-world environmental threats, like expanding fire hazard zones, that aerial AI scanning could track.

Knowledge check

5 questions to check understanding after the lesson. Tap an answer to see if it is right; the score appears at the end.

  1. 1What kind of machine learning does the terrain monitoring AI use in this lesson?

  2. 2What primary type of data do students collect during their aerial expedition?

  3. 3How does the AI determine that illegal logging or tree disease is present?

  4. 4Why is early detection of illegal logging vital for environmentalists?

  5. 5How does partner organization Terrafuse apply AI to forestry management?

Resources

Part of the AI Foundations curriculum

This is lesson 2 of 18 in AI Foundations.

  1. AI-1: Who Is That Ocelot?
  2. AI-2: Mapping Terrain
  3. AI-3: Sustainable Farming
  4. AI-4: Ocean Observations
  5. AI-5: Water Quality
  6. Unit 9: AI
  7. AI Adventurers
  8. AI Wildlife Park
  9. CyberSafe AI: Dig Deeper
  10. Fantastic Fairgrounds
  11. Hour of AI: Field Agent
  12. Hour of AI: Generation AI
  13. Hour of AI: The First Night
  14. Hour of Code: AI for Good
  15. Hour of Code: Generation AI
  16. Mini Agent Mission
  17. Peter Is Here: AI for Cultural Heritage
  18. Reed Smart: AI Detective

Frequently Asked Questions

Does this lesson represent exact real-world AI programming workflows?

No. The concepts are simplified to explain the conceptual workflow of collecting data and detecting anomalies within Minecraft rather than replicating professional software development.

What materials are provided to guide classroom instruction?

The lesson package includes a step-by-step classroom presentation following the gradual release model, a downloadable Minecraft world, and a Curriculum Overview document.

Adapted from AI-2: Mapping Terrain by Minecraft Education on Minecraft Education, last updated Oct 4, 2024. This classroom version, the timings and the quiz were written by 9Minecraft Education.

You May Also Like

9Minecraft Education is an independent teaching resource and is not affiliated with Mojang or Microsoft. Lesson plans here are our own classroom-ready adaptations; each one links to the original resource and credits its author. © 2026 9minecraft.net