Deep spatial transformers for autoregressive data-driven forecasting of geophysical turbulence

This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint.

Add a Comment

You must log in to post a comment.


There are no comments or no comments have been made public for this article.


Download Preprint


Ashesh Chattopadhyay, Mustafa Mustafa, Pedram Hassanzadeh, Karthik Kashinath


A deep spatial transformer based encoder-decoder model has been developed to autoregressively predict the time evolution of the upper layers stream function of a two-layered quasi-geostrophic (QG) system without any information about the lower layers stream function. The spatio-temporal complexity of QG flow is comparable to the complexity of 500hPa Geopotential Height (Z500) of fully coupled climate models or even the Z500 which is observed in the atmosphere, based on the instantaneous attractor dimension metric. The ability to predict autoregressively, the turbulent dynamics of QG is the first step towards building data-driven surrogates for more complex climate models. We show that the equivariance preserving properties of modern spatial transformers incorporated within a convolutional encoder-decoder module can predict up to 9 days in a QG system (outperforming a baseline persistence model and a standard convolutional encoder decoder with a custom loss function). The proposed data-driven model remains stable for multiple years thus promising us of a stable and physical data-driven climate model.



Artificial Intelligence and Robotics, Atmospheric Sciences, Climate, Computer Sciences, Dynamical Systems, Earth Sciences, Environmental Sciences, Fluid Dynamics, Geophysics and Seismology, Mathematics, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Physics


Deep learning, Geophysics, atmosphere, Data-driven, Equivariance, Forecasting, Quasi-Geostrophic, Symmetry, Transformers, Turbulence, Weather


Published: 2020-07-05 14:54


GNU Lesser General Public License (LGPL) 2.1