arXiv subjects

Shirley Ho

Publications and source records attributed to Shirley Ho.

At least 91 records · Page 5Linked to original sources

arXiv2021

The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations

We present the Cosmology and Astrophysics with MachinE Learning Simulations --CAMELS-- project. CAMELS is a suite of 4,233 cosmological simulations of $(25~h^{-1}{\rm Mpc})^3$ volume each: 2,184 state-of-the-art (magneto-)hydrodynamic simulations run with the AREPO and GIZMO codes, employing the same baryonic subgrid physics as the IllustrisTNG and SIMBA simulations, and 2,049 N-body simulations. The goal of the CAMELS project is to provide theory predictions for different observables as a function of cosmology and astrophysics, and it is the largest suite of cosmological (magneto-)hydrodynamic simulations designed to train machine learning algorithms. CAMELS contains thousands of different cosmological and astrophysical models by way of varying $Ω_m$, $σ_8$, and four parameters controlling stellar and AGN feedback, following the evolution of more than 100 billion particles and fluid elements over a combined volume of $(400~h^{-1}{\rm Mpc})^3$. We describe the simulations in detail and characterize the large range of conditions represented in terms of the matter power spectrum, cosmic star formation rate density, galaxy stellar mass function, halo baryon fractions, and several galaxy scaling relations. We show that the IllustrisTNG and SIMBA suites produce roughly similar distributions of galaxy properties over the full parameter space but significantly different halo baryon fractions and baryonic effects on the matter power spectrum. This emphasizes the need for marginalizing over baryonic effects to extract the maximum amount of information from cosmological surveys. We illustrate the unique potential of CAMELS using several machine learning applications, including non-linear interpolation, parameter estimation, symbolic regression, data generation with Generative Adversarial Networks (GANs), dimensionality reduction, and anomaly detection.

astro-ph.CO↗

arXiv2021

The Quijote simulations

The Quijote simulations are a set of 44,100 full N-body simulations spanning more than 7,000 cosmological models in the $\{Ω_{\rm m}, Ω_{\rm b}, h, n_s, σ_8, M_ν, w \}$ hyperplane. At a single redshift the simulations contain more than 8.5 trillions of particles over a combined volume of 44,100 $(h^{-1}{\rm Gpc})^3$; each simulation follow the evolution of $256^3$, $512^3$ or $1024^3$ particles in a box of $1~h^{-1}{\rm Gpc}$ length. Billions of dark matter halos and cosmic voids have been identified in the simulations, whose runs required more than 35 million core hours. The Quijote simulations have been designed for two main purposes: 1) to quantify the information content on cosmological observables, and 2) to provide enough data to train machine learning algorithms. In this paper we describe the simulations and show a few of their applications. We also release the Petabyte of data generated, comprising hundreds of thousands of simulation snapshots at multiple redshifts, halo and void catalogs, together with millions of summary statistics such as power spectra, bispectra, correlation functions, marked power spectra, and estimated probability density functions.

astro-ph.CO↗

arXiv2021

HInet: Generating neutral hydrogen from dark matter with neural networks

Upcoming 21cm surveys will map the spatial distribution of cosmic neutral hydrogen (HI) over very large cosmological volumes. In order to maximize the scientific return of these surveys, accurate theoretical predictions are needed. Hydrodynamic simulations currently are the most accurate tool to provide those predictions in the mildly to non-linear regime. Unfortunately, their computational cost is very high: tens of millions of CPU hours. We use convolutional neural networks to find the mapping between the spatial distribution of matter from N-body simulations and HI from the state-of-the-art hydrodynamic simulation IllustrisTNG. Our model performs better than the widely used theoretical model: Halo Occupation Distribution (HOD) for all statistical properties up to the non-linear scales $k\lesssim1$ h/Mpc. Our method allows the generation of 21cm mocks over very big cosmological volumes with similar properties as hydrodynamic simulations.

astro-ph.CO↗

arXiv2021

Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes

Among the most extreme objects in the Universe, active galactic nuclei (AGN) are luminous centers of galaxies where a black hole feeds on surrounding matter. The variability patterns of the light emitted by an AGN contain information about the physical properties of the underlying black hole. Upcoming telescopes will observe over 100 million AGN in multiple broadband wavelengths, yielding a large sample of multivariate time series with long gaps and irregular sampling. We present a method that reconstructs the AGN time series and simultaneously infers the posterior probability density distribution (PDF) over the physical quantities of the black hole, including its mass and luminosity. We apply this method to a simulated dataset of 11,000 AGN and report precision and accuracy of 0.4 dex and 0.3 dex in the inferred black hole mass. This work is the first to address probabilistic time series reconstruction and parameter inference for AGN in an end-to-end fashion.

astro-ph.IM↗

arXiv2021

deep21: a Deep Learning Method for 21cm Foreground Removal

We seek to remove foreground contaminants from 21cm intensity mapping observations. We demonstrate that a deep convolutional neural network (CNN) with a UNet architecture and three-dimensional convolutions, trained on simulated observations, can effectively separate frequency and spatial patterns of the cosmic neutral hydrogen (HI) signal from foregrounds in the presence of noise. Cleaned maps recover cosmological clustering statistics within 10% at all relevant angular scales and frequencies. This amounts to a reduction in prediction variance of over an order of magnitude on small angular scales ($\ell > 300$), and improved accuracy for small radial scales ($k_{\parallel} > 0.17\ \rm h\ Mpc^{-1})$ compared to standard Principal Component Analysis (PCA) methods. We estimate posterior confidence intervals for the network's prediction by training an ensemble of UNets. Our approach demonstrates the feasibility of analyzing 21cm intensity maps, as opposed to derived summary statistics, for upcoming radio experiments, as long as the simulated foreground model is sufficiently realistic. We provide the code used for this analysis on Github https://github.com/tlmakinen/deep21 as well as a browser-based tutorial for the experiment and UNet model via the accompanying http://bit.ly/deep21-colab Colab notebook.

astro-ph.CO↗

arXiv2021

Meta-Learning for One-Class Classification with Few Examples using Order-Equivariant Network

This paper presents a meta-learning framework for few-shots One-Class Classification (OCC) at test-time, a setting where labeled examples are only available for the positive class, and no supervision is given for the negative example. We consider that we have a set of `one-class classification' objective-tasks with only a small set of positive examples available for each task, and a set of training tasks with full supervision (i.e. highly imbalanced classification). We propose an approach using order-equivariant networks to learn a 'meta' binary-classifier. The model will take as input an example to classify from a given task, as well as the corresponding supervised set of positive examples for this OCC task. Thus, the output of the model will be 'conditioned' on the available positive example of a given task, allowing to predict on new tasks and new examples without labeled negative examples. In this paper, we are motivated by an astronomy application. Our goal is to identify if stars belong to a specific stellar group (the 'one-class' for a given task), called \textit{stellar streams}, where each stellar stream is a different OCC-task. We show that our method transfers well on unseen (test) synthetic streams, and outperforms the baselines even though it is not retrained and accesses a much smaller part of the data per task to predict (only positive supervision). We see however that it doesn't transfer as well on the real stream GD-1. This could come from intrinsic differences from the synthetic and real stream, highlighting the need for consistency in the 'nature' of the task for this method. However, light fine-tuning improve performances and outperform our baselines. Our experiments show encouraging results to further explore meta-learning methods for OCC tasks.

cs.LG↗

arXiv2021

A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients

There is a shortage of multi-wavelength and spectroscopic followup capabilities given the number of transient and variable astrophysical events discovered through wide-field, optical surveys such as the upcoming Vera C. Rubin Observatory. From the haystack of potential science targets, astronomers must allocate scarce resources to study a selection of needles in real time. Here we present a variational recurrent autoencoder neural network to encode simulated Rubin Observatory extragalactic transient events using 1% of the PLAsTiCC dataset to train the autoencoder. Our unsupervised method uniquely works with unlabeled, real time, multivariate and aperiodic data. We rank 1,129,184 events based on an anomaly score estimated using an isolation forest. We find that our pipeline successfully ranks rarer classes of transients as more anomalous. Using simple cuts in anomaly score and uncertainty, we identify a pure (~95% pure) sample of rare transients (i.e., transients other than Type Ia, Type II and Type Ibc supernovae) including superluminous and pair-instability supernovae. Finally, our algorithm is able to identify these transients as anomalous well before peak, enabling real-time follow up studies in the era of the Rubin Observatory.

astro-ph.HE↗

arXiv2021

The Role of Machine Learning in the Next Decade of Cosmology

In recent years, machine learning (ML) methods have remarkably improved how cosmologists can interpret data. The next decade will bring new opportunities for data-driven cosmological discovery, but will also present new challenges for adopting ML methodologies and understanding the results. ML could transform our field, but this transformation will require the astronomy community to both foster and promote interdisciplinary research endeavors.

astro-ph.IM↗

arXiv2021

A Bayesian neural network predicts the dissolution of compact planetary systems

Despite over three hundred years of effort, no solutions exist for predicting when a general planetary configuration will become unstable. We introduce a deep learning architecture to push forward this problem for compact systems. While current machine learning algorithms in this area rely on scientist-derived instability metrics, our new technique learns its own metrics from scratch, enabled by a novel internal structure inspired from dynamics theory. Our Bayesian neural network model can accurately predict not only if, but also when a compact planetary system with three or more planets will go unstable. Our model, trained directly from short N-body time series of raw orbital elements, is more than two orders of magnitude more accurate at predicting instability times than analytical estimators, while also reducing the bias of existing machine learning algorithms by nearly a factor of three. Despite being trained on compact resonant and near-resonant three-planet configurations, the model demonstrates robust generalization to both non-resonant and higher multiplicity configurations, in the latter case outperforming models fit to that specific set of integrations. The model computes instability estimates up to five orders of magnitude faster than a numerical integrator, and unlike previous efforts provides confidence intervals on its predictions. Our inference model is publicly available in the SPOCK package, with training code open-sourced.

astro-ph.EP↗

arXiv2020

Learning the Evolution of the Universe in N-body Simulations

Understanding the physics of large cosmological surveys down to small (nonlinear) scales will significantly improve our knowledge of the Universe. Large N-body simulations have been built to obtain predictions in the non-linear regime. However, N-body simulations are computationally expensive and generate large amount of data, putting burdens on storage. These data are snapshots of the simulated Universe at different times, and fine sampling is necessary to accurately save its whole history. We employ a deep neural network model to predict the nonlinear N-body simulation at an intermediate time step given two widely separated snapshots. Our results outperform the cubic Hermite interpolation benchmark method in interpolating N-body simulations. This work can greatly reduce the storage requirement and allow us to reconstruct the cosmic history from far fewer snapshots of the universe.

astro-ph.CO↗

arXiv2020

dm2gal: Mapping Dark Matter to Galaxies with Neural Networks

Maps of cosmic structure produced by galaxy surveys are one of the key tools for answering fundamental questions about the Universe. Accurate theoretical predictions for these quantities are needed to maximize the scientific return of these programs. Simulating the Universe by including gravity and hydrodynamics is one of the most powerful techniques to accomplish this; unfortunately, these simulations are very expensive computationally. Alternatively, gravity-only simulations are cheaper, but do not predict the locations and properties of galaxies in the cosmic web. In this work, we use convolutional neural networks to paint galaxy stellar masses on top of the dark matter field generated by gravity-only simulations. Stellar mass of galaxies are important for galaxy selection in surveys and thus an important quantity that needs to be predicted. Our model outperforms the state-of-the-art benchmark model and allows the generation of fast and accurate models of the observed galaxy distribution.

astro-ph.CO↗

arXiv2020

Fast and Accurate Non-Linear Predictions of Universes with Deep Learning

Cosmologists aim to model the evolution of initially low amplitude Gaussian density fluctuations into the highly non-linear "cosmic web" of galaxies and clusters. They aim to compare simulations of this structure formation process with observations of large-scale structure traced by galaxies and infer the properties of the dark energy and dark matter that make up 95% of the universe. These ensembles of simulations of billions of galaxies are computationally demanding, so that more efficient approaches to tracing the non-linear growth of structure are needed. We build a V-Net based model that transforms fast linear predictions into fully nonlinear predictions from numerical simulations. Our NN model learns to emulate the simulations down to small scales and is both faster and more accurate than the current state-of-the-art approximate methods. It also achieves comparable accuracy when tested on universes of significantly different cosmological parameters from the one used in training. This suggests that our model generalizes well beyond our training set.

astro-ph.CO↗

arXiv2020

Modeling assembly bias with machine learning and symbolic regression

Upcoming 21cm surveys will map the spatial distribution of cosmic neutral hydrogen (HI) over unprecedented volumes. Mock catalogues are needed to fully exploit the potential of these surveys. Standard techniques employed to create these mock catalogs, like Halo Occupation Distribution (HOD), rely on assumptions such as the baryonic properties of dark matter halos only depend on their masses. In this work, we use the state-of-the-art magneto-hydrodynamic simulation IllustrisTNG to show that the HI content of halos exhibits a strong dependence on their local environment. We then use machine learning techniques to show that this effect can be 1) modeled by these algorithms and 2) parametrized in the form of novel analytic equations. We provide physical explanations for this environmental effect and show that ignoring it leads to underprediction of the real-space 21-cm power spectrum at $k\gtrsim 0.05$ h/Mpc by $\gtrsim$10\%, which is larger than the expected precision from upcoming surveys on such large scales. Our methodology of combining numerical simulations with machine learning techniques is general, and opens a new direction at modeling and parametrizing the complex physics of assembly bias needed to generate accurate mocks for galaxy and line intensity mapping surveys.

astro-ph.CO↗

arXiv2020

Discovering Symbolic Models from Deep Learning with Inductive Biases

We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, then we apply symbolic regression to components of the learned model to extract explicit physical relations. We find the correct known equations, including force laws and Hamiltonians, can be extracted from the neural network. We then apply our method to a non-trivial cosmology example-a detailed dark matter simulation-and discover a new analytic formula which can predict the concentration of dark matter from the mass distribution of nearby cosmic structures. The symbolic expressions extracted from the GNN using our technique also generalized to out-of-distribution data better than the GNN itself. Our approach offers alternative directions for interpreting neural networks and discovering novel physical principles from the representations they learn.

cs.LG↗

arXiv2020

Neural networks as optimal estimators to marginalize over baryonic effects

Many different studies have shown that a wealth of cosmological information resides on small, non-linear scales. Unfortunately, there are two challenges to overcome to utilize that information. First, we do not know the optimal estimator that will allow us to retrieve the maximum information. Second, baryonic effects impact that regime significantly and in a poorly understood manner. Ideally, we would like to use an estimator that extracts the maximum cosmological information while marginalizing over baryonic effects. In this work we show that neural networks can achieve that. We made use of data where the maximum amount of cosmological information is known: power spectra and 2D Gaussian density fields. We also contaminate the data with simplified baryonic effects and train neural networks to predict the value of the cosmological parameters. For this data, we show that neural networks can 1) extract the maximum available cosmological information, 2) marginalize over baryonic effects, and 3) extract cosmological information that is buried in the regime dominated by baryonic physics. We also show that neural networks learn the priors of the data they are trained on. We conclude that a promising strategy to maximize the scientific return of cosmological experiments is to train neural networks on state-of-the-art numerical simulations with different strengths and implementations of baryonic effects.

astro-ph.CO↗

arXiv2020

Anomaly Detection for Multivariate Time Series of Exotic Supernovae

Supernovae mark the explosive deaths of stars and enrich the cosmos with heavy elements. Future telescopes will discover thousands of new supernovae nightly, creating a need to flag astrophysically interesting events rapidly for followup study. Ideally, such an anomaly detection pipeline would be independent of our current knowledge and be sensitive to unexpected phenomena. Here we present an unsupervised method to search for anomalous time series in real time for transient, multivariate, and aperiodic signals. We use a RNN-based variational autoencoder to encode supernova time series and an isolation forest to search for anomalous events in the learned encoded space. We apply this method to a simulated dataset of 12,159 supernovae, successfully discovering anomalous supernovae and objects with catastrophically incorrect redshift measurements. This work is the first anomaly detection pipeline for supernovae which works with online datastreams.

astro-ph.IM↗

arXiv2020

Line confusion in spectroscopic surveys and its possible effects: Shifts in Baryon Acoustic Oscillations position

Roman Space Telescope will survey about 17 million emission-line galaxies over a range of redshifts. Its main targets are H$α$ emission-line galaxies at low redshifts and [O III] emission-line galaxies at high redshifts. The Roman Space Telescope will estimate the redshift these galaxies with single line identification. This suggests that other emission-line galaxies may be misidentified as the main targets. In particular, it is hard to distinguish between the H$β$ and [O III] lines as the two lines are close in wavelength and hence the photometric information may not be sufficient to separate them reliably. Misidentifying H$β$ emitter as [O III] emitter will cause a shift in the inferred radial position of the galaxy by approximately 90 Mpc/h. This length scale is similar to the Baryon Acoustic Oscillation (BAO) scale and could shift and broaden the BAO peak, possibly introduce errors in determining the BAO peak position. We qualitatively describe the effect of this new systematic and further quantify it with a lightcone simulation with emission-line galaxies.

astro-ph.CO↗

arXiv2020

Lagrangian Neural Networks

Accurate models of the world are built upon notions of its underlying symmetries. In physics, these symmetries correspond to conservation laws, such as for energy and momentum. Yet even though neural network models see increasing use in the physical sciences, they struggle to learn these symmetries. In this paper, we propose Lagrangian Neural Networks (LNNs), which can parameterize arbitrary Lagrangians using neural networks. In contrast to models that learn Hamiltonians, LNNs do not require canonical coordinates, and thus perform well in situations where canonical momenta are unknown or difficult to compute. Unlike previous approaches, our method does not restrict the functional form of learned energies and will produce energy-conserving models for a variety of tasks. We test our approach on a double pendulum and a relativistic particle, demonstrating energy conservation where a baseline approach incurs dissipation and modeling relativity without canonical coordinates where a Hamiltonian approach fails. Finally, we show how this model can be applied to graphs and continuous systems using a Lagrangian Graph Network, and demonstrate it on the 1D wave equation.

cs.LG↗