Communications of the ACM
Using Satellite Images to Improve Human Lives
A team based at the University of California, Berkeley, has devised a machine learning system to tap the problem-solving potential of satellite imaging using low-cost technology that could bring access and analytical power to researchers and governments w
Credit: Pxfuel/NASA
Researchers at the University of California, Berkeley (UC Berkeley) have developed a machine learning system that aims to make geospatial data more accessible to researchers and governments around the world.
UC Berkeley's Esther Rolf said, "We designed our system for accessibility, so that one person should be able to run it on a laptop, without specialized training, to address their local problems."
The system, MOSAIKS (Multi-Task Observation using Satellite Imagery & Kitchen Sinks), recognizes minuscule patterns in satellite images and groups them together, and it can identify similar patterns in different geographic areas.
It could be used to address development and environmental challenges, such as assessing the condition of existing infrastructure in a community or tracking the speed at which glaciers are disintegrating.
UC Berkeley's Solomon Hsiang calls the system "a Swiss Army Knife — a practical tool that everyone can access."
From UC Berkeley News
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found