DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
Nathanaël Perraudin,
Michaël Defferrard,
Tomasz Kacprzak,
Raphael Sgier
Astronomy and Computing, 2019
Convolutional Neural Networks (CNNs) are a cornerstone of the Deep Learning toolbox and have led to many breakthroughs in Artificial Intelligence. These networks have mostly been developed for regular Euclidean domains such as those supporting images, audio, or video. Because of their success, CNN-based methods are becoming increasingly popular in Cosmology. Cosmological data often comes as spherical maps, which make the use of the traditional CNNs more complicated. The commonly used pixelization scheme for spherical maps is the Hierarchical Equal Area isoLatitude Pixelisation (HEALPix). We present a spherical CNN for analysis of full and partial HEALPix maps, which we call DeepSphere. The spherical CNN is constructed by representing the sphere as a graph. Graphs are versatile data structures that can act as a discrete representation of a continuous manifold. Using the graph-based representation, we define many of the standard CNN operations, such as convolution and pooling. With filters restricted to being radial, our convolutions are equivariant to rotation on the sphere, and DeepSphere can be made invariant or equivariant to rotation. This way, DeepSphere is a special case of a graph CNN, tailored to the HEALPix sampling of the sphere. This approach is computationally more efficient than using spherical harmonics to perform convolutions. We demonstrate the method on a classification problem of weak lensing mass maps from two cosmological models and compare the performance of the CNN with that of two baseline classifiers. The results show that the performance of DeepSphere is always superior or equal to both of these baselines. For high noise levels and for data covering only a smaller fraction of the sphere, DeepSphere achieves typically 10% better classification accuracy than those baselines. Finally, we show how learned filters can be visualized to introspect the neural network.
@article{deepsphere_cosmo,
title = {{DeepSphere}: Efficient spherical Convolutional Neural Network with {HEALPix} sampling for cosmological applications},
author = {Perraudin, Nathana\"el and Defferrard, Micha\"el and Kacprzak, Tomasz and Sgier, Raphael},
journal = {Astronomy and Computing},
volume = {27},
pages = {130-146},
year = {2019},
month = apr,
publisher = {Elsevier BV},
issn = {2213-1337},
doi = {10.1016/j.ascom.2019.03.004},
archiveprefix = {arXiv},
eprint = {1810.12186},
url = {https://arxiv.org/abs/1810.12186},
}
PDF available at arXiv and Astronomy and Computing.
Related: code, data, blog, slides.
Compile the latex source into a PDF with make.
Run make clean to remove temporary files and make arxiv.zip to prepare an archive to be uploaded on arxiv.
All the figures are in the figures folder.
The code and data to reproduce them is found in the code repository.
The journal reviews and rebuttal are in rebuttal.tex and will be compiled in a PDF by make.