CISL Seminar Series: A Novel Recurrent Convolutional Neural Network for Ocean and Weather Forecasting

08/25/2017 - 10:00am to 11:00am
ML - MSR

A Novel Recurrent Convolutional Neural Network for Ocean and Weather Forecasting

Robert Firth

Numerical weather prediction is a computationally expensive task that requires not only the numerical solution to a complex set of non-linear partial differential equations, but also the creation of a parameterization scheme to estimate sub-grid scale phenomenon.

The proposed method is an alternative approach to developing a mesoscale meteorological model – a modified recurrent convolutional neural network that learns to simulate the solution to these equations. Along with an appropriate time integration scheme and learning algorithm, this method can be used to create multi-day forecasts for a large region. The learning method presented is an extended form of Backpropagation Through Time for a recurrent network with outputs that feed back through as inputs only after undergoing a fixed transformation.

An initial implementation of this approach has been created that forecasts for 2,744 locations across the southeastern United States at 36 vertical levels of the atmosphere, and 119,000 locations across the Atlantic Ocean at 39 vertical levels. These models, called LM3 and LOM, forecast wind speed, temperature, geopotential height, and rainfall for weather forecasting and water current speed, temperature, and salinity for ocean forecasting.

A method for implementing this approach using TensorFlow will also be discussed.

 

Biography

Dr. Firth received his B.S. (2010) and Ph.D. (2016) in computer science from Louisiana State University, where he researched the use of recurrent convolutional neural networks to forecast the ocean and atmosphere. His research interests include meteorology, machine learning, and quantum computing. He is currently a software engineer in the private sector.

 

Friday, August 25th, 2017

10:00 a.m.-11:00 a.m.

Mesa Lab, Main Seminar Room