“Applications of Deep Learning to ocean data inference and subgrid parameterization”

This is another nail in the coffin of the claim I heard at last year’s Lorenz-Charney Symposium at MIT that machine learning methods would not make a serious contribution to advancements in the geophysical sciences.

T. Bolton, L. Zanna, “Applications of Deep Learning to ocean data inference and subgrid parameterization“, Journal of Advances in Modeling Earth Systems, 2019, 11.

About ecoquant

See https://wordpress.com/view/667-per-cm.net/ Retired data scientist and statistician. Now working projects in quantitative ecology and, specifically, phenology of Bryophyta and technical methods for their study, notably Macrophotography. Some photos of mine: https://www.flickr.com/photos/198372469@N03/
This entry was posted in American Meteorological Association, American Statistical Association, artificial intelligence, Azimuth Project, deep learning, deep recurrent neural networks, dynamical systems, geophysics, machine learning, Mathematics and Climate Research Network, National Center for Atmospheric Research, oceanography, oceans, science, stochastic algorithms. Bookmark the permalink.

Leave a Reply