Ecology, Climate Change and Related News

Conservation Science for a Healthy Planet

Advancing climate science with knowledge-discovery through data mining

Leave a Comment
January 18, 2018 Georgia Institute of Technology read full ScienceDaily article here

Big data and data mining have provided several breakthroughs in fields such as health informatics, smart cities and marketing. The same techniques, however, have not delivered consistent key findings for climate change….the analysis of climate teleconnections, has relied on methods that offer rather simplistic “yes or no” answers.

“It’s not that simple in climate….Imposing thresholds and throwing out weak connections would halt everything…”

And with millions of data points spread out around the globe, Bracco said current models rely too much on human expertise to make sense of the output. She and her colleagues wanted to develop a methodology that depends more on actual data rather than a researcher’s interpretation.

….The [new] methodology brings out commonalities of data sets without as much expertise from the user, allowing scientists to trust the data and get more robust — and transparent — results.

The methodology is open source and currently available to scientists around the world. The Georgia Tech researchers are already using it to explore sea surface temperature and cloud field data, two aspects that profoundly affect the planet’s climate….

Annalisa Bracco, Fabrizio Falasca, Athanasios Nenes, Ilias Fountalis, Constantine Dovrolis. Advancing climate science with knowledge-discovery through data mining. npj Climate and Atmospheric Science, 2018; 1 (1) DOI: 10.1038/s41612-017-0006-4

View all articles

Comments are closed