Communications of the ACM
Machine Learning Method Lowers Computational Cost of Satellite Imagery Analysis
A single set of general purpose features can encode rich information in satellite images, researchers say.
Credit: NASA
A research team based at UC Berkeley has devised a machine learning system to tap the problem-solving potential of satellite imaging, using low-cost, easy-to-use technology that could bring access and analytical power to researchers and governments worldwide.
They describe their work in "A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery," published in the journal Nature Communications.
"Satellite images contain an incredible amount of data about the world, but the trick is how to translate the data into usable insights," says Esther Rolf, a Ph.D. student in computer science. "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 researchers were guided by a common interest in creating an open access tool that is usable even by communities and countries that lack resources and advanced technical skill. "It's like Ford's Model T, but with machine learning and satellites," says Solomon Hsiang, director of the Global Policy Lab.
From University of California, Berkeley
View Full Article
No entries found