Machine learning technology helps scientists recognize severe weather patterns.
Training an algorithm with satellite images of ocean color reveals the blooms and busts of phytoplankton communities.
Recent advances in machine learning hold great potential for converting a deluge of data into weather forecasts that are fast, accurate, and detailed.
Tens of thousands of ship tracks—cloud structures created when ships’ exhaust plumes interact with the atmosphere—are pinpointed automatically, furthering study of these climate-altering features.
2nd Annual Machine Learning in Solid Earth Geoscience Conference; Santa Fe, New Mexico, 18–22 March 2019
Onboard machine learning and compact thermal imaging could turn satellites into real-time fire management tools to help officials on the ground.
A new 34-year global time series of observed sea surface partial pressure of CO2 links regional variation to major climate modes.
Players dive off a research boat, identify and classify coral reefs using satellite and drone images, and bring marine life back to reefs. In doing so, they help scientists teach a machine to learn.
New methods of machine learning are bringing the phase arrival time and polarity picking used for automatic determination of earthquake fault planes to accuracies better than human analysists.
Space Weather: A Multi-disciplinary Approach; Leiden, Netherlands, 25–29 September 2017