Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1807.05657

Visualizing the Hidden Features of Galaxy Morphology with Machine Learning

Jia-Ming Dai·Jizhou Tong
View original source ↗Read source document ↗Export metadata ↓

Abstract

We train three convolutional neural networks (CNNs) to classify galaxies with Galaxy Zoo 2 dataset and extract the activations from the last fully connected layer or the last average pooling layer of CNNs to study the high-dimensional abstract feature representations of galaxy images. We apply t-Distributed Stochastic Neighbour Embedding (t-SNE), a popular dimensionality reduction technique, to visualize the high-dimensional galaxy feature representations in two-dimensional scatter plots. From the visualization, we try to understand the galaxy images data itself and obtain some highly valuable insights. For instance, the learned galaxy feature representations from networks indicate that the galaxies belonging to the same class tend to group together, i.e. same morphological galaxies are clustered; The cluster of completely round smooth galaxy and the cluster of in-between smooth galaxy (between completely round and cigar-shaped) are moved closer, compared to other clusters; The cluster of cigar-shaped smooth galaxy and the cluster of edge-on galaxy are intertwined surprisingly; A galaxy mislabelled as spiral galaxy in the original dataset falls in the cluster of completely round smooth galaxy, and manual inspection also identifies out the outlier as a completely round smooth galaxy. These findings will facilitate the study of galaxy morphology.

Explore related subjects

astro-ph.GAastro-ph.IM

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Jia-Ming Dai, Jizhou Tong. 2018-07-16. Visualizing the Hidden Features of Galaxy Morphology with Machine Learning. https://arxiv.org/abs/1807.05657

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Gravitational Waves from Cosmic Dawn: Tracing Cosmic Black Hole Binaries with ET, LGWA, and LISA

Next-generation detectors, such as LISA, LGWA, and ET, will for the first time probe the high redshift Universe, offering unique insight into the birth, growth, and dynamics of the first black holes (BHs) during their earliest stages of formation. We aim to predict merger rates and gravitational wave (GW) signatures of "cosmic" binary BHs forming as a result of galaxy mergers at $z\geq 4$. We investigate how BH seeding, accretion physics, and dynamical delays affect their properties and detectability across cosmic epochs. We used the semi-analytic model Cosmic Archaeology Tool (CAT) to trace the evolution and delayed mergers, driven by dynamical friction, of BH binaries formed from light, medium-weight, and heavy seeds under Eddington-limited (EL) and super-Eddington (SE) accretion prescriptions. We employed the GWFish package to evaluate their GW signals and detectability by LISA, LGWA, and ET. Our results show the impact of BH accretion and seeding prescriptions on the properties and distribution of detectable sources. In the EL model, the detected populations are dominated by nearly equal-mass binaries ($\tilde{q} = 0.7$). In contrast, SE growth leads to lower mass ratios for LISA detections ($\tilde{q} \sim 0.2$) and medium ratios for ET and LGWA ($\tilde{q} \sim 0.4$ and $0.3$, respectively). We present the total detection rates predicted under the two accretion scenarios. The SE model allows BHs to grow faster, transferring a significant fraction of detectable systems from the ET band to the LISA band, compared to the EL model. As a result, the predicted LISA detection rate increases from ~ 32 yr$^{-1}$ in the EL case to ~ 64 yr$^{-1}$ in the SE scenario, and the ET detection rate reduces from ~ 64 yr$^{-1}$ in the EL model to only ~ 4 yr$^{-1}$ in the SE scenario. In both scenarios, LGWA yields comparable detection rates (~ 21 yr$^{-1}$ in EL and ~ 12 yr$^{-1}$ in SE).

astro-ph.GA↗
arXiv2026

The Radio-FIR Correlation in the Context of Deep Radio Source Counts

Increasingly deep, confusion-limited radio surveys have pushed direct radio source-count measurements down to tens of $μ$Jy at 1.4 GHz. Confusion-noise P(D) analyses extend the statistical counts to below $1\,\mathrm{μJy}$. Radio source counts have allowed for constraints on the radio-derived star formation rate density (SFRD) history through models of the backwards evolution of the local radio luminosity function, using the radio-FIR correlation, $q \propto \log(L_{\mathrm{FIR}}/L_{1.4})$, to convert radio luminosities to FIR luminosities and hence star-formation rates. Recent deep radio source counts from MeerKAT suggest a potential tension in the SFRD history between radio and UV/IR measurements at $1\lesssim z\lesssim 2$. This corresponds to a $\gtrsim 3σ$ discrepancy between the predicted and measured source counts near the star forming galaxy source count $S^2n(S)$ peak of ${\sim}30\,\mathrm{μJy}$ under both a pure luminosity (PLE) and combined luminosity and density evolution (LADE). We consider what the requirement of agreement between radio source counts and the observed UV/IR SFRD indicates about the redshift evolution of the radio-FIR correlation and its intrinsic scatter out to $z=3$. We introduce a radio-luminosity based parameterization to $q_{\mathrm{FIR}}(z)$ based on changing thermal radio fractions alone that agrees with the observed stellar-mass dependent $q_{\mathrm{FIR}}(z)$ better than a non-evolving or decreasing $q_{\mathrm{FIR}}(z)$. Despite this, we find that a decreasing $q_{\mathrm{FIR}}(z)$ at fixed radio luminosity provides better agreement between source counts and the observed SFRD, while a $q_{\mathrm{FIR}}(z)$ that breaks down due to cosmic ray losses requires an intrinsic scatter up to $σ_q\approx 0.3\,\mathrm{dex}$.

astro-ph.GA↗
arXiv2026

An Ionized Superstructure at Cosmic Dawn Revealed by a Foundation Model for Astrophysical Research

The spatial structure of cosmic reionization remains poorly constrained. Using a foundation model trained for James Webb Space Telescope datasets, we identify a luminous galaxy at redshift $z=7.567$ showing strong Ly$α$ transmission at $z=6.80\pm0.07$. The transmission extends over $210.5^{+55.7}_{-53.5}$ comoving megaparsecs, indicating an ionized superstructure with hydrogen neutral fraction $x_{\rm HI}=(2.07^{+0.29}_{-0.30})\times10^{-6}$, in an epoch when the cosmic mean neutral fraction is $\sim0.4$. Cosmological simulations suggest a probability of $\approx10^{-5}$ for a random sightline to reproduce the signal. We find no significant galaxy overdensity associated with the transmission region, in tension with canonical inside-out reionization models. These observations severely challenge existing reionization models in the standard $Λ$CDM Universe, and provide the first example of deep learning discovering a previously unknown astrophysical phenomenon.

astro-ph.GA↗