Virgo: Scalable Unsupervised Classification of Cosmological Shock Waves. (arXiv:2208.06859v2 [astro-ph.IM] UPDATED)
<a href="http://arxiv.org/find/astro-ph/1/au:+Lamparth_M/0/1/0/all/0/1">Max Lamparth</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Boss_L/0/1/0/all/0/1">Ludwig Böss</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Steinwandel_U/0/1/0/all/0/1">Ulrich Steinwandel</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Dolag_K/0/1/0/all/0/1">Klaus Dolag</a>
Cosmological shock waves are essential to understanding the formation of
cosmological structures. To study them, scientists run computationally
expensive high-resolution 3D hydrodynamic simulations. Interpreting the
simulation results is challenging because the resulting data sets are enormous,
and the shock wave surfaces are hard to separate and classify due to their
complex morphologies and multiple shock fronts intersecting. We introduce a
novel pipeline, Virgo, combining physical motivation, scalability, and
probabilistic robustness to tackle this unsolved unsupervised classification
problem. To this end, we employ kernel principal component analysis with
low-rank matrix approximations to denoise data sets of shocked particles and
create labeled subsets. We perform supervised classification to recover full
data resolution with stochastic variational deep kernel learning. We evaluate
on three state-of-the-art data sets with varying complexity and achieve good
results. The proposed pipeline runs automatically, has only a few
hyperparameters, and performs well on all tested data sets. Our results are
promising for large-scale applications, and we highlight now enabled future
scientific work.
Cosmological shock waves are essential to understanding the formation of
cosmological structures. To study them, scientists run computationally
expensive high-resolution 3D hydrodynamic simulations. Interpreting the
simulation results is challenging because the resulting data sets are enormous,
and the shock wave surfaces are hard to separate and classify due to their
complex morphologies and multiple shock fronts intersecting. We introduce a
novel pipeline, Virgo, combining physical motivation, scalability, and
probabilistic robustness to tackle this unsolved unsupervised classification
problem. To this end, we employ kernel principal component analysis with
low-rank matrix approximations to denoise data sets of shocked particles and
create labeled subsets. We perform supervised classification to recover full
data resolution with stochastic variational deep kernel learning. We evaluate
on three state-of-the-art data sets with varying complexity and achieve good
results. The proposed pipeline runs automatically, has only a few
hyperparameters, and performs well on all tested data sets. Our results are
promising for large-scale applications, and we highlight now enabled future
scientific work.
http://arxiv.org/icons/sfx.gif
