Machine Learning methods applied to the atmosphere, land and ocean
Office: EOS-South 162 Phone: 604-822-2821 Phone2: Fax:822-6088
Personal Website: http://www.ocgy.ubc.ca/projects/clim.pred/index.html
B.Sc. U.B.C. (1976) (combined honours in Mathematics & Physics);
M.Sc. U.B.C. (1978) (Physics);
Ph.D. U.B.C. (1981) (Physics and Oceanography).
Post-doctoral: Cambridge University (Dept. of Applied Maths. & Theoretical Physics) 1981-82;
University of New South Wales (School of Mathematics) 1983-85.
Visiting Fellow: Princeton University (Geophysical Fluid Dynamics Laboratory) 1992.
President's Prize (1999), Canadian Meteorological and Oceanographic Society.
Distinguished Scholar in Residence, Peter Wall Institute for Advanced Studies, U.B.C., 2000.
Fellow of the Canadian Meteorological and Oceanographic Society (2010).
Machine learning (ML), a major branch of computational intelligence (i.e. artificial intelligence), has a huge impact on our everyday lives through its ability to recognize complicated, nonlinear signals in large datasets. When we post a letter, the post office uses ML technology to understand our handwriting. Online vendors such as Amazon and Netflix suggest books and movies of interest using ML. Internet providers detect spam and credit card companies detect fraudulent transactions via ML.
The question that has intrigued us for the last two decades has been: How would machine learning impact the environmental sciences?
A prominent example of climate variability is the famous El Niño-La Niña phenomenon, an irregular fluctuation of the climate system which produces anomalous warming in the equatorial Pacific during El Niño and cooling during La Niña, with notable influence on the Canada winter climate. El Niño/La Niña episodes can be forecasted with reasonable accuracy 3-12 months in advance. Our group has built models for El Niño/La Niña prediction using artificial neural networks and other ML methods. We have developed neural network models for nonlinear principal component analysis, nonlinear canonical correlation analysis, and nonlinear singular spectrum analysis (our codes are freely downloadable and have users from over 60 countries). We have identified nonlinear atmospheric teleconnection patterns associated with the El Niño/La Niña, the Arctic Oscillation, the quasi-biennial oscillation and the Madden-Julian oscillation.
Our most recent research efforts have been directed to the following three areas:
My graduate-level book "Machine Learning Methods in the Environmental Sciences: Neural Networks and Kernels" was published by Cambridge Univ. Press in 2009.
Our climate forecasts are updated monthly on our web site: http://www.ocgy.ubc.ca/projects/clim.pred/.