Dimensionality-Reduction of Climate Data using Deep Autoencoders

TL;DR

This paper demonstrates that convolutional autoencoders can effectively reduce the dimensionality of climate temperature data, outperforming PCA, and potentially serve as a basis for surrogate climate models.

Contribution

The study introduces the use of deep convolutional autoencoders for nonlinear dimensionality reduction in climate data, showing improved reconstruction over PCA.

Findings

CAE outperforms PCA in reconstruction error

Autoencoders can be trained to improve results

Potential for surrogate climate model construction

Abstract

We explore the use of deep neural networks for nonlinear dimensionality reduction in climate applications. We train convolutional autoencoders (CAEs) to encode two temperature field datasets from pre-industrial control runs in the CMIP5 first ensemble, obtained with the CCSM4 model and the IPSL-CM5A-LR model, respectively. With the later dataset, consisting of 36500 96$\times$96 surface temperature fields, the CAE out-performs PCA in terms of mean squared error of the reconstruction from a 40 dimensional encoding. Moreover, the noise in the filters of the convolutional layers in the autoencoders suggests that the CAE can be trained to produce better results. Our results indicate that convolutional autoencoders may provide an effective platform for the construction of surrogate climate models.