Published By: UC San Diego News Center, 9/14/2016
An interdisciplinary research team developed a large dataset of 21,030 high-resolution satellite images of India labeled for whether they show built-up areas. The dataset can be used as input to algorithms for detecting urban areas; for example, the team used it to map urbanization in India. This allows scientists and governments to study changes in urbanization and industrialization over time.
Extended Discussion Questions
- As potential users of maps based on this data, the article mentions scientists, government policymakers, businesses, and humanitarian or environmental organizations . Can you think of some examples of how the maps could help each of those users meet their goals?
- Are there any potential uses of this data that could be problematic for someone?
- The original research article explains that the images were labeled by graduate students working on the project.
- Why do you think they didn’t just pay people to do it online, via crowdsourcing?
- What are some advantages and disadvantages of crowdsourcing for a big labeling project like this?
“Detecting the Boundaries of Urban Areas in India: A Dataset for Pixel-Based Image Classification in Google Earth Engine”, by Ran Goldblatt, Wei You, Gordon Hanson, and Amit K. Khandelwal
Published By: Remote Sensing, 8/2016 || View the Article
The original research article provides additional details about data collection and processing, and about the detection algorithm.
Relating This Story to the CSP Curriculum Framework
Global Impact Learning Objectives:
- LO 7.2.1 Explain how computing has impacted innovations in other fields.
Global Impact Essential Knowledge:
- EK 7.2.1A Machine learning and data mining have enabled innovation in medicine, business, and science.
- EK 7.2.1E Open and curated scientific databases have benefited scientific researchers.
- EK 7.2.1G Advances in computing as an enabling technology have generated and increased the creativity in other fields.
Other CSP Big Ideas:
- Idea 3 Data and Information
Banner Image: “Network Visualization – Violet – Crop 14”, derivative work by ICSI. New license: CC BY-SA 4.0. Based on “Social Network Analysis Visualization” by Martin Grandjean. Original license: CC BY-SA 3.0