A team of researchers at Pennsylvania State University (Penn State) and Syracuse University applied a novel machine learning algorithm to help scientists better understand stream chemistry and its environmental impact.
They said they used the algorithm to analyze how the chemical composition of streams changes over time, concentrating on carbon dioxide fluctuations.
The team based the algorithm on an unsupervised learning model called on-negative matrix factorization to detect patterns in data, like the chemicals in the stream, that have not been tagged.
Penn State's Andrew Shaughnessy said the study helped characterize "the interplay between stream chemistry matching rock chemistry."
The researchers suggested the algorithm could be used to analyze the role of streams in sequestering carbon dioxide and discharging it back into the atmosphere.
From Penn State News
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA