☆ 4.7 Review

Machine learning for observational cosmology

REPORTS ON PROGRESS IN PHYSICS (2023)

Related references

Note: Only part of the references are listed.
Article Astronomy & Astrophysics

Bayesian field-level inference of primordial non-Gaussianity using next-generation galaxy surveys

Adam Andrews et al.

Summary: Detecting and measuring a non-Gaussian signature of primordial origin in the density field is a major science goal of next generation galaxy surveys. A field-level approach by Bayesian forward modelling the entire three-dimensional galaxy survey is presented to extract information on primordial non-Gaussianity. The method demonstrates potential improvements of a factor similar to 2.5 over current published constraints and provides a promising complementary path for analyzing next-generation surveys.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2023)

Add to Collection
Article Astronomy & Astrophysics

Photometric Classification of Early-time Supernova Light Curves with SCONE

Helen Qu et al.

Summary: In this work, a photometric classifier called SCONE is introduced, which uses convolutional neural networks to categorize supernovae based on their light curves. The study demonstrates that SCONE is capable of identifying supernova types at any stage and incorporating redshift information improves the classification performance.

ASTRONOMICAL JOURNAL (2022)

Add to Collection
Article Astronomy & Astrophysics

COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys

Alessio Spurio Mancini et al.

Summary: COSMOPOWER is a suite of neural cosmological power spectrum emulators that provide orders-of-magnitude acceleration for parameter estimation from two-point statistics analyses of Large-Scale Structure (LSS) and Cosmic Microwave Background (CMB) surveys. It replaces traditional computation methods and can quickly and accurately recover fiducial cosmological constraints, completing posterior distributions in just a few seconds.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Machine learning astrophysics from 21 cm lightcones: impact of network architectures and signal contamination

David Prelogovic et al.

Summary: This study uses neural networks to directly infer astrophysical parameters from 21 cm lightcone images, and introduces recurrent neural networks to characterize the evolution of the images. Comparing different network architectures, the simplest RNN performs the best in parameter estimation without instrumental effects. However, when the images are contaminated, parameter prediction errors increase and larger datasets and better data augmentation are needed to maximize the potential of neural networks in 21 cm parameter estimation.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Multifidelity emulation for the matter power spectrum using Gaussian processes

Ming-Feng Ho et al.

Summary: The study introduces a method for emulating the matter power spectrum by combining information from cosmological N-body simulations at different resolutions, achieving increased emulation accuracy through multifidelity emulation. The proposed multifidelity emulator predicts high-fidelity counterparts with percent-level relative accuracy and outperforms single-fidelity emulators, demonstrating a new way to predict nonlinear scales.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Simultaneously constraining cosmology and baryonic physics via deep learning from weak lensing

Tianhuan Lu et al.

Summary: In this study, the researchers incorporated a baryonic correction model to account for baryonic effects and developed a convolutional neural network (CNN) to simultaneously learn and constrain cosmological and baryonic parameters from weak lensing convergence maps. They found that the CNN achieved tighter constraints in omega(m)-sigma(8) space compared to traditional methods, even while marginalizing over baryonic effects.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Lifting weak lensing degeneracies with a field-based likelihood

Natalia Porqueres et al.

Summary: We present a field-based approach for analyzing cosmic shear data to infer cosmological parameters and dark matter distribution. This approach utilizes a physical gravity model to link the initial matter fluctuations to the non-linear matter distribution, allowing for consistent sampling and updating of cosmological parameters. The field-based approach is found to extract more information from the data compared to methods based on two-point statistics, and it provides tight constraints on parameters from weak lensing data alone.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

The combined and respective roles of imaging and stellar kinematics in identifying galaxy merger remnants

Connor Bottrell et al.

Summary: One of the challenges in studying the role of mergers in galaxy evolution is the selection of pure and complete merger samples. While spectroscopic criteria make it relatively easy to obtain large and pure samples of interacting galaxy pairs, automated selection of post-coalescence merger remnants is limited to the physical characteristics of the remnants alone. This study shows that even idealized stellar kinematic data has limited utility compared to imaging and does not significantly improve the identification of merger remnants when combined.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Inferring astrophysics and dark matter properties from 21 cm tomography using deep learning

Steffen Neutsch et al.

Summary: 21 cm tomography provides a new approach to study astrophysics and fundamental physics of early epochs in our Universe's history. By adopting a network-based approach, we can directly infer the parameters of Cosmic Dawn and Epoch of Reionization, as well as fundamental physics. The results show high-fidelity parameter recovery and robustness against foreground levels and modelling uncertainties.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Dark energy survey year 3 results: Cosmology with peaks using an emulator approach

D. Zuercher et al.

Summary: In this study, the matter density and the amplitude of density fluctuations within the ΛCDM cosmological model were constrained using shear peak statistics and angular convergence power spectra, leading to a tightening of constraints on the structure growth parameter with improved precision of 1.8%. The combination of angular power spectra and tomographic peak counts breaks the degeneracy between galaxy intrinsic alignment and S-8, improving cosmological constraints. Results are found to be consistent with previous studies using Dark Energy Survey (DES Y3) data.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Using artificial intelligence and real galaxy images to constrain parameters in galaxy formation simulations

Andrea Maccio et al.

Summary: This study demonstrates that machine learning techniques applied to galaxy images can differentiate between different parameter values in galaxy simulations, allowing for a comparison with observational results. This provides a viable method for understanding galaxy evolution.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

MATRYOSHKA: halo model emulator for the galaxy power spectrum

Jamie Donald-McCann et al.

Summary: MATRYOSHKA is a suite of neural-network-based emulators and accompanying python package that can provide fast and accurate predictions of the non-linear galaxy power spectrum. By combining linear component emulators with a non-linear boost component emulator, it is possible to predict the real space non-linear galaxy power spectrum with high accuracy.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Third data release of the Hyper Suprime-Cam Subaru Strategic Program

Hiroaki Aihara et al.

Summary: This paper presents the third data release of the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP), which includes data from three survey layers covering about 670 deg(2) in all five broad-band filters. The overall quality of the processed data has improved since the previous release, but there are still limitations in the data that users should be aware of before utilizing.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2022)

Add to Collection
Article Astronomy & Astrophysics

Kernel-based emulator for the 3D matter power spectrum from CLASS

A. Mootoovaloo et al.

Summary: This paper proposes a fast Bayesian method to generate the 3D matter power spectrum and provides the gradient of the spectrum with respect to the input cosmological parameters. The method is efficient and accurate, making it suitable for constraint derivation in cosmological data analysis.

ASTRONOMY AND COMPUTING (2022)

Add to Collection
Review Astronomy & Astrophysics

Photometric Redshifts for Next-Generation Surveys

Effrey A. Newman et al.

Summary: Photometric redshifts are crucial for studying galaxy evolution and cosmology, especially when spectroscopy is not feasible. Further improvements in photometric redshift methods are needed to enhance performance and accurately recover redshift distributions in upcoming large-scale imaging surveys.

ANNUAL REVIEW OF ASTRONOMY AND ASTROPHYSICS (2022)

Add to Collection
Article Astronomy & Astrophysics

NECOLA: Toward a Universal Field-level Cosmological Emulator

Neerav Kaushal et al.

Summary: In this study, we use convolutional neural networks (NECOLA) to correct the output of fast and approximate N-body simulations at the field level. Our model achieves high accuracy at the field level and can be trained on different values of cosmological parameters, as well as correct the output of fast/approximate simulations.

ASTROPHYSICAL JOURNAL (2022)

Add to Collection
Article Astronomy & Astrophysics

Finding Universal Relations in Subhalo Properties with Artificial Intelligence

Helen Shao et al.

Summary: The study utilizes neural networks to predict the total mass of a subhalo with high accuracy and extrapolation capabilities across different cosmologies and astrophysical models. The results suggest a universal relation and the derived analytic expressions are shown to be more accurate in some regimes compared to the neural networks.

ASTROPHYSICAL JOURNAL (2022)

Add to Collection
Article Astronomy & Astrophysics

The CAMELS Multifield Data Set: Learning the Universe's Fundamental Parameters with Artificial Intelligence

Francisco Villaescusa-Navarro et al.

Summary: This paper presents the Cosmology and Astrophysics with Machine Learning Simulations (CAMELS) Multifield Data set (CMD), which contains millions of 2D maps and 3D grids from more than 2000 simulated universes. CMD is designed for training machine-learning models and is the largest data set of its kind. The paper describes CMD in detail and focuses on parameter inference as one of its applications.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2022)

Add to Collection
Article Astronomy & Astrophysics

Recovering the CMB Signal with Machine Learning

Guo-Jian Wang et al.

Summary: This study developed a deep convolutional neural network (CNN) to recover the weak cosmic microwave background (CMB) signals from foreground contaminations. The CNN model successfully recovered the CMB temperature maps with high accuracy and consistency with actual observations. Moreover, this method proved effective in recovering CMB polarization signals and could assist in detecting primordial gravitational waves in future CMB experiments.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2022)

Add to Collection
Article Astronomy & Astrophysics

Neural network acceleration of large-scale structure theory calculations

Joseph DeRose et al.

Summary: We use neural networks to accelerate the calculation of power spectra for galaxy clustering and weak gravitational lensing analysis. By constructing neural network-based surrogate models, we achieve high accuracy over a broad range of scales and a computation speed 1000 times faster than traditional methods. The release of these surrogate models will facilitate rapid iteration on analysis settings, which is essential for complex large-scale structure analyses.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2022)

Add to Collection
Article Astronomy & Astrophysics

Deep learning methods for obtaining photometric redshift estimations from images

Ben Henghes et al.

Summary: The researchers compared deep learning methods with traditional machine learning algorithms for photometric redshift estimation and introduced a mixed-input model to improve the accuracy of redshift estimation. In the tests, the mixed-input inception CNN outperformed the traditional random forest algorithm, especially at lower redshifts.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Cosmological forecasts with the clustering of weak lensing peaks

Christopher T. Davies et al.

Summary: In this study, we investigate the clustering of weak lensing (WL) peaks and present parameter constraint forecasts for a survey similar to LSST. We find that the clustering of low-amplitude peaks is complementary to that of high-amplitude peaks, and their combination gives significantly tighter constraints. The peak two-point correlation function is more sensitive to cosmological parameters than the peak abundance, and when combined with other probes, it improves constraints on omega(m), S-8, h, and w(0) by at least a factor of 2. We also compare the forecasts for WL peaks and voids, and show that both probes offer better constraints on S-8 and w(0) than the shear correlation function by roughly a factor of 2.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Mimicking the halo-galaxy connection using machine learning

Natali S. M. de Santi et al.

Summary: This study utilizes machine-learning techniques to analyze the connection between galaxy properties and their hosting haloes, predicting baryonic properties from halo properties. The results show consistent predictions among different algorithms and the ability to accurately reproduce the power spectra of various galaxy populations. The use of data augmentation methods also improves the accuracy of predictions.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

Extracting the 21-cm Power Spectrum and the reionization parameters from mock datasets using Artificial Neural Networks

Madhurima Choudhury et al.

Summary: In this work, artificial neural networks (ANNs) are used to extract the HI 21-cm power spectrum and reionization parameters from synthetic datasets. This novel approach demonstrates a potential solution to the challenge of bright foregrounds in low-frequency radio interferometers.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Article Astronomy & Astrophysics

All-purpose, all-sky photometric redshifts for the Legacy Imaging Surveys Data Release 8

Kenneth J. Duncan

Summary: This paper presents photometric redshift (photo-z) estimates for the Dark Energy Spectroscopic Instrument (DESI) Legacy Imaging Surveys. The photo-z methodology is based on a machine-learning approach using sparse Gaussian processes and Gaussian mixture models, which can predict reliable and unbiased redshifts for galaxies in wide area surveys. The estimates are significantly less biased and more accurate at z > 1 compared to previous literature estimates, and have negligible loss in precision or reliability for resolved galaxies at z < 1. This approach also offers accurate predictions for rare high-value populations, including optically selected quasars at high redshifts and X-ray or radio continuum selected populations across a broad range of flux and redshift.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2022)

Add to Collection
Review Astronomy & Astrophysics

Cosmology intertwined: A review of the particle physics, astrophysics, and cosmology associated with the cosmological tensions and anomalies

Elcio Abdalla et al.

Summary: The paper discusses the limitations of the standard Lambda Cold Dark Matter (Lambda CDM) cosmological model and proposes new physics models to alleviate the tensions in various cosmological measurements. The authors emphasize the importance of considering a wide range of data and discuss the significance of upcoming experiments and space missions in addressing open questions in cosmology.

JOURNAL OF HIGH ENERGY ASTROPHYSICS (2022)

Add to Collection
Article Physics, Multidisciplinary

Uncertainties associated with GAN-generated datasets in high energy physics

Konstantin T. Matchev et al.

Summary: This paper points out that the data generated by Generative Adversarial Networks (GANs) cannot be statistically better than the data it was trained on, and critically examines the applicability of GANs in different situations. By using information theoretic demonstrations, a toy example, and a formal statement, the paper presents arguments and identifies potential valid uses of GANs in collider simulations.

SCIPOST PHYSICS (2022)

Add to Collection
Article Astronomy & Astrophysics

Finding strong gravitational lenses through self-attention Study based on the Bologna Lens Challenge

Hareesh Thuruthipilly et al.

Summary: The study investigates the performance of self-attention-based encoder models in the Bologna Lens Challenge, showing that these models outperformed CNNs in certain aspects, especially in terms of TPR0 and TPR10 scores. Additionally, they address the overfitting issue present in CNNs.

ASTRONOMY & ASTROPHYSICS (2022)

Add to Collection
Article Astronomy & Astrophysics

Searching for Anomalies in the ZTF Catalog of Periodic Variable Stars

Ho-Sang Chan et al.

Summary: Periodic variables are important for understanding the physical processes of stars. We propose a new unsupervised machine-learning approach for identifying anomalous periodic variables using phase-folded light curves. Our method utilizes a convolutional variational autoencoder to learn a low-dimensional latent representation and an isolation forest to find anomalies within this representation. We discover irregularly variable anomalies, which are likely highly variable red giants or young stellar objects concentrated in the Milky Way galactic disk.

ASTROPHYSICAL JOURNAL (2022)

Add to Collection
Article Astronomy & Astrophysics

Inferring Halo Masses with Graph Neural Networks

Pablo Villanueva-Domingo et al.

Summary: This study introduces a model that uses Graph Neural Networks (GNNs) to infer the mass of a halo based on various galaxy properties. By training the model on state-of-the-art simulations, the researchers were able to accurately constrain halo masses and demonstrate the robustness of their method. The implementation of the GNN is publicly available for further use.

ASTROPHYSICAL JOURNAL (2022)

Add to Collection
Article Astronomy & Astrophysics

Field-level inference of galaxy intrinsic alignment from the SDSS-III BOSS survey

Eleni Tsaprazi et al.

Summary: In this study, constraints on the linear alignment model were provided using a fully Bayesian field-level approach, and 4 sigma evidence of intrinsic alignment was found.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2022)

Add to Collection
Article Astronomy & Astrophysics

BAO scale inference from biased tracers using the EFT likelihood

Ivana Babic et al.

Summary: The physical scale corresponding to baryon acoustic oscillations (BAO) can be accurately determined by CMB experiments. However, the precision of inferring the BAO scale from galaxy clustering analysis is reduced by non-linear structure formation. In this paper, a forward modeling approach combined with the EFT likelihood is used to infer isotropic BAO from rest-frame halo catalogs, resulting in a small remaining systematic bias.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2022)

Add to Collection
Article Astronomy & Astrophysics

Deep-learning real/bogus classification for the Tomo-e Gozen transient survey

I. C. H. I. R. O. TAKAHASHI et al.

Summary: We present a deep neural network real/bogus classifier that improves the performance of the Tomo-e Gozen Transient survey by handling label errors in the training data. This classifier saves human effort in relabeling and works well with high label error data, achieving high accuracy in actual observations.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2022)

Add to Collection
Article Astronomy & Astrophysics

Mangrove: Learning Galaxy Properties from Merger Trees

Christian Kragh Jespersen et al.

Summary: Efficiently mapping baryonic properties onto dark matter is a major challenge in astrophysics. This paper introduces a graph-based emulator framework called Mangrove that can simulate various galactic properties with lower error and in a much shorter time compared to other methods. Mangrove also allows for quantification of the dependence of galaxy properties on merger history.

ASTROPHYSICAL JOURNAL (2022)

Add to Collection
Article Astronomy & Astrophysics

Full-shape cosmology analysis of the SDSS-III BOSS galaxy power spectrum using an emulator-based halo model: A 5% determination of σ8

Yosuke Kobayashi et al.

Summary: In this study, the authors present the results of their cosmology analysis based on the redshift-space power spectra of galaxy samples from the SDSS-III BOSS DR12 galaxy catalog. They use an emulator built from N-body simulations to compute the redshift-space power spectrum of halos, and model the galaxy-halo connection using the halo occupation distribution. The authors validate their analysis pipeline using mock catalogs of BOSS-like galaxies and find that their model reproduces the observed power spectra well. They obtain values for cosmological parameters such as Omega(m), H-0, and sigma(8) that are consistent with the Planck CMB results.

PHYSICAL REVIEW D (2022)

Add to Collection
Article Astronomy & Astrophysics

Percent-level constraints on baryonic feedback with distortion measurements

Leander Thiele et al.

Summary: High-significance measurements of the monopole thermal Sunyaev-Zel'dovich cosmic microwave background spectral distortions have the potential to tightly constrain poorly understood baryonic feedback processes. By utilizing hydrodynamic simulations and machine learning, we explore possible constraints on parameters describing feedback from active galactic nuclei and supernovae, which is of great significance.

PHYSICAL REVIEW D (2022)

Add to Collection
Review Astronomy & Astrophysics

Dark Energy Survey Year 3 results: Cosmology from cosmic shear and robustness to modeling uncertainty

L. F. Secco et al.

Summary: This paper presents cosmic shear measurements and cosmological constraints from the Darki Energy Survey (DES) Year 3 data, using over 100 million source galaxies. The lensing amplitude parameter S-8 is constrained at the 3% level in the ΛCDM model, and the robustness of the results to modeling of intrinsic alignments is explored. Constraints from other weak lensing experiments and the Cosmic Microwave Background (CMB) are compared, and the statistical preference for different complexity intrinsic alignment models is examined.

PHYSICAL REVIEW D (2022)

Add to Collection
Article Astronomy & Astrophysics

KiDS-1000 cosmology: Cosmic shear constraints and comparison between two point statistics

Marika Asgari et al.

Summary: The study presents cosmological constraints using the fourth data release of the Kilo-Degree Survey (KiDS-1000), revealing tension with the Planck Legacy analysis predictions. The results from the fiducial COSEBIs analysis align well with other complementary analyses, indicating robust S-8 constraints dominated by statistical errors.

ASTRONOMY & ASTROPHYSICS (2021)

Add to Collection
Review Astronomy & Astrophysics

Photometric Redshifts With Machine Learning, Lights and Shadows on a Complex Data Science Use Case

Massimo Brescia et al.

Summary: The importance of data-driven science in Astrophysics is increasing, especially in achieving the main science goals of future large survey projects. Recent data challenges have pushed the optimization of photometric redshift prediction and statistical characterization, as well as the exploration of hybrid and deep learning techniques.

FRONTIERS IN ASTRONOMY AND SPACE SCIENCES (2021)

Add to Collection
Article Astronomy & Astrophysics

PS1-STRM: neural network source classification and photometric redshift catalogue for PS1 3π DR1

Robert Beck et al.

Summary: The Pan-STARRS1 (PS1) 3 pi survey is a comprehensive optical imaging survey covering three quarters of the sky, using neural networks trained on spectroscopic data to classify sources and estimate photometric redshifts. The final catalogue contains 2902 054 648 objects, with classification accuracy of 98.1% for galaxies, 97.8% for stars, and 96.6% for quasars on the validation data set.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Deblending galaxies with variational autoencoders: A joint multiband, multi-instrument approach

Bastien Arcelin et al.

Summary: The study introduces a generative model based on deep neural networks to address the impact of galaxy blending in weak-lensing studies. By training the networks on simulated images and testing the method, satisfactory results in galaxies deblending and reconstruction errors were obtained.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Probing dark energy with tomographic weak-lensing aperture mass statistics

Nicolas Martinet et al.

Summary: Exploration of complementary cosmological information through non-Gaussian M-ap map statistics has the potential to improve constraints on recent tension in cosmic structure and dark energy, offering a pathway to understanding accelerated expansion.

ASTRONOMY & ASTROPHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier

R. Carrasco-Davis et al.

Summary: This paper introduces a real-time stamp classifier of astronomical events based on a convolutional neural network, which can accurately classify various types of astronomical events. By designing and deploying a visualization tool called SN Hunter and using the ability of reporting targets with only a single detection, it holds significant importance for the study of astronomical events.

ASTRONOMICAL JOURNAL (2021)

Add to Collection
Article Astronomy & Astrophysics

High-quality Strong Lens Candidates in the Final Kilo-Degree Survey Footprint

R. Li et al.

Summary: Using a new convolutional neural network (CNN) classifier, 97 new high-quality strong lensing candidates were discovered in the KiDS optical survey area, bringing the total to 268 systems. The complementarity of morphology and color information in multi-band composites successfully identified these candidates.

ASTROPHYSICAL JOURNAL (2021)

Add to Collection
Article Astronomy & Astrophysics

Deep-learning Reconstruction of Three-dimensional Galaxy Distributions with Intensity Mapping Observations

Kana Moriwaki et al.

Summary: Line-intensity mapping is a new method to measure intensity fluctuations of atomic/molecular line emission from distant galaxies, but faces the challenge of line confusion. A generative adversarial network is developed to extract emission-line signals from noisy data, which can reconstruct the three-dimensional distribution of emission-line galaxies at specific redshifts after training. The deep-learning method achieves a precision of 84% in identifying bright galaxies and high cross correlation coefficients between true and reconstructed intensity maps.

ASTROPHYSICAL JOURNAL LETTERS (2021)

Add to Collection
Article Astronomy & Astrophysics

Cosmological forecast for non-Gaussian statistics in large-scale weak lensing surveys

Dominik Zurcher et al.

Summary: The study compared the constraining power of three map-based non-Gaussian statistics with the angular power spectrum in the Omega(m)-sigma(8) plane, finding that non-Gaussian statistics provide tighter constraints. A combination of non-Gaussian statistics and the angular power spectrum increased the constraining power and reduced the error on S8.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Using artificial neural networks to extract the 21-cm global signal from the EDGES data

Madhurima Choudhury et al.

Summary: The redshifted 21-cm signal of neutral hydrogen is a useful tool for studying the evolution of the Universe, but its faint signal is easily perturbed and thus requires simulation using different physical models and processing with artificial neural networks. By reconstructing signal parameters from simulated data and observations, it is possible to infer the physical state of the gas at high redshifts.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Mind the gap: the power of combining photometric surveys with intensity mapping

Chirag Modi et al.

Summary: By adding external galaxy distribution data to the 21-cm surveys, the lost long wavelength modes can be partially recovered. The spectroscopic sample performs better in reconstructing the largest modes, despite having lower number density.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Alert Classification for the ALeRCE Broker System: The Light Curve Classifier

P. Sanchez-Saez et al.

Summary: The study introduces the first version of the ALeRCE broker light curve classifier, which classifies various stellar objects using data from ZTF alert stream and different photometric sources. The classifier shows high precision and recall scores, providing updated classifications accessible through the ALeRCE Explorer website.

ASTRONOMICAL JOURNAL (2021)

Add to Collection
Article Astronomy & Astrophysics

Discovering New Strong Gravitational Lenses in the DESI Legacy Imaging Surveys

X. Huang et al.

Summary: Using deep residual neural networks, a research team has identified 1210 new strong lens candidates in survey data covering approximately one-third of the sky visible from the Northern Hemisphere, reaching a similar z-band AB magnitude threshold.

ASTROPHYSICAL JOURNAL (2021)

Add to Collection
Article Astronomy & Astrophysics

The EFT likelihood for large-scale structure in redshift space

Giovanni Cabass

Summary: The study focuses on the EFT likelihood for biased tracers in redshift space, highlighting the importance of the bias expansion of the galaxy velocity field. The principle of equivalence restricts stochastic contributions to the galaxy velocity field to survive at small k. Consequently, the form of the likelihood function to observe a redshift-space galaxy overdensity is fixed by the rest-frame noise, which is Gaussian with a constant power spectrum. The analysis demonstrates that redshift-space distortions only affect the covariance in terms of the rest-frame matter and velocity fields.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Filling in Cosmic Microwave Background map missing regions via Generative Adversarial Networks

Alireza Vafaei Sadr et al.

Summary: This study introduces a new method for filling in the CMB signal masked out during a point source extraction process using a modified GAN. The GAN is trained to effectively reconstruct masking for about 1500 pixels with 1% error, down to angular scales corresponding to about 5 arcminutes. Additionally, the GAN is able to accurately mimic the PDF and number density of peaks for both Gaussian and non-Gaussian data with less than 0.5% relative error.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Photometric redshift estimation with a convolutional neural network: NetZ

S. Schuldt et al.

Summary: This study developed a new method using convolutional neural networks to predict photo-z based on galaxy images, achieving good performance across a wide redshift range and showing potential for future surveys.

ASTRONOMY & ASTROPHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

FlowPM: Distributed TensorFlow implementation of the FastPM cosmological N-body solver

C. Modi et al.

Summary: FlowPM is a Particle-Mesh (PM) cosmological N-body code implemented in Mesh-TensorFlow for GPU-accelerated, distributed, and differentiable simulations. A novel multi-grid scheme based on multiresolution pyramids is implemented to compute large-scale forces efficiently on distributed platforms, achieving significant speed-up compared to Python-based PM code. This tool can be used for efficiently solving large scale cosmological inference problems, including the reconstruction of cosmological fields in a forward model Bayesian framework with hybrid PM and neural network forward model.

ASTRONOMY AND COMPUTING (2021)

Add to Collection
Article Astronomy & Astrophysics

Inpainting CMB maps using partial convolutional neural networks

Gabriele Montefalcone et al.

Summary: This study introduces a novel application of partial convolutional neural networks (PCNN) for inpainting masked images of the cosmic microwave background, achieving map and power spectra reconstruction accuracy to a few percent with circular and irregularly shaped masks covering up to 10% of the image area. Kolmogorov-Smirnov tests demonstrate the indistinguishability of the reconstructed maps and power spectra from the input data at a 99.9% confidence level, highlighting the potential of PCNNs as an important tool in cosmological data analysis.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

An emulator for the Lyman-α forest in beyond-ΛCDM cosmologies

Christian Pedersen et al.

Summary: Interpreting observations of the Lyman-alpha forest flux power spectrum requires interpolation between simulations. A Gaussian process emulator has been presented to model the 1D flux power spectrum, enabling predictions in extended cosmological models without the need for bespoke emulators. This approach is suitable for cosmologies where the linear matter power spectrum is accurately described by an amplitude and slope across a specific epoch, and in the regime probed by eBOSS/DESI data.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

deep21: a deep learning method for 21 cm foreground removal

T. Lucas Makinen et al.

Summary: A deep convolutional neural network (CNN) with UNet architecture is used to effectively separate cosmic neutral hydrogen (HI) signals and foreground contaminants in 21 cm intensity mapping observations. The cleaned maps recover cosmological clustering amplitude and phase accurately, showing significant improvement compared to standard Principal Component Analysis (PCA) methods.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Sigma-eight at the percent level: the EFT likelihood in real space

Fabian Schmidt

Summary: The paper presents results and implementation details on the real-space formulation of the likelihood for the density field of biased tracers, allowing for cosmology inference using all available information at a given order in perturbation theory. The implementation includes a Lagrangian forward model for biased tracers, demonstrating unbiased inference of sigma(8) at the 2% level for halo samples over a range of masses and redshifts. The inferred value converges to the ground truth in the low-cutoff limit, representing a substantial improvement over previous results based on the EFT likelihood.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Noise reduction for weak lensing mass mapping: an application of generative adversarial networks to Subaru Hyper Suprime-Cam first-year data

Masato Shirasaki et al.

Summary: In this study, a deep-learning approach based on generative adversarial networks (GANs) was proposed to reduce noise in weak lensing mass maps, which was successfully applied to real data. The effectiveness of the method was confirmed through the study of one-point distribution functions and matching analysis. The PDFs in denoised maps show stronger cosmological dependence, increasing the reliability of cosmological research.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Transient-optimized real-bogus classification with Bayesian convolutional neural networks - sifting the GOTO candidate stream

T. L. Killestein et al.

Summary: This paper introduces a new real-bogus classifier based on a Bayesian convolutional neural network for nuanced classification and uncertainty-aware evaluation of transient candidates. The approach achieves competitive classification accuracy with classifiers trained with fully human-labelled data sets, through fully automated training set generation and data-driven augmentation methods.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

The cosmology dependence of galaxy clustering and lensing from a hybrid N-body-perturbation theory model

Nickolas Kokron et al.

Summary: The researchers developed a model that combines dark matter dynamics with analytic bias expansion for analyzing the two-point statistics of biased tracers. They demonstrated the accuracy and applicability of their emulation procedure, showing its ability to describe complex tracer samples and fit clustering and lensing statistics effectively. The emulator is shown to be a promising tool for cosmological parameter inference and analysis of data from galaxy surveys.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Euclid preparation: IX. EuclidEmulator2-power spectrum emulation with massive neutrinos and self-consistent dark energy perturbations

M. Knabenhans et al.

Summary: EuclidEmulator2 is a fast and accurate predictor for the nonlinear correction of the matter power spectrum, achieving 2% accuracy in an eight-dimensional parameter space. By improving the quality of N-body simulations and conducting high fidelity tests, it has been successfully applied in various comparisons and blind tests, showing superior accuracy of nonlinear correction factors at z <= 3 compared to high-resolution dark-matter-only simulations.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Hybrid analytic and machine-learned baryonic property insertion into galactic dark matter haloes

Ben Moews et al.

Summary: The study explores the merging of an equilibrium model with a machine learning framework to create a high-speed hydrodynamic simulation emulator, which can populate galactic dark matter haloes with baryonic properties in cosmological simulations. The results demonstrate that this hybrid system enables the fast completion of dark matter information while discussing the advantages and disadvantages of hybrid versus machine learning-only frameworks.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Multidisciplinary Sciences

AI-assisted superresolution cosmological simulations

Yin Li et al.

Summary: This study utilizes artificial intelligence to generate super-resolution versions of low-resolution cosmological Nbody simulations, enhancing the resolution and accurately replicating the high-resolution matter power spectrum and dark matter halo mass function in large-scale environments.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2021)

Add to Collection
Article Astronomy & Astrophysics

HOLISMOKES VI. New galaxy-scale strong lens candidates from the HSC-SSP imaging survey

R. Canameras et al.

Summary: The study identified 206 new galaxy-scale strong lens candidates using an automated pipeline and recovered 173 known systems. The results demonstrate that deep learning pipelines can be powerful tools for identifying rare strong lenses from large catalogs with low false positive rates.

ASTRONOMY & ASTROPHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

HInet: Generating Neutral Hydrogen from Dark Matter with Neural Networks

Digvijay Wadekar et al.

Summary: Upcoming 21 cm surveys will map the spatial distribution of cosmic neutral hydrogen, and accurate theoretical predictions are essential. Using convolutional neural networks to find the mapping between matter distribution and Hi yields better results than traditional theoretical models, allowing the generation of 21 cm mocks over large cosmological volumes similar to hydrodynamic simulations.

ASTROPHYSICAL JOURNAL (2021)

Add to Collection
Article Astronomy & Astrophysics

The CAMELS Project: Cosmology and Astrophysics with Machine-learning Simulations

Francisco Villaescusa-Navarro et al.

Summary: The CAMELS project consists of 4233 cosmological simulations designed to provide theory predictions for different observables and train machine-learning algorithms. It includes various cosmological and astrophysical models, tracking the evolution of over 100 billion particles and fluid elements, and providing valuable data for studying matter power spectrum and cosmic star formation rate density, among others.

ASTROPHYSICAL JOURNAL (2021)

Add to Collection
Article Astronomy & Astrophysics

The Dark Energy Survey Data Release 2

T. M. C. Abbott et al.

Summary: The second public data release of the Dark Energy Survey, DES DR2, includes reduced single-epoch and coadded images, a source catalog and associated data products assembled from 6 years of DES science operations. Covering approximately 5000 deg(2) of the southern Galactic cap in five broad photometric bands, DES DR2 offers photometric uniformity and accuracy, with a median delivered point-spread function FWHM and internal astrometric precision. The dataset includes data from 691 million distinct astronomical objects accessible through various interfaces, making it the largest photometric data set to date at the achieved depth and photometric precision.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2021)

Add to Collection
Article Astronomy & Astrophysics

A Deep-learning Approach for Live Anomaly Detection of Extragalactic Transients

V. Ashley Villar et al.

Summary: Astronomers face a shortage of follow-up capabilities for transient astrophysical events discovered through wide-field surveys, but a neural network has been developed to encode and rank these events, successfully identifying rare types of transients.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2021)

Add to Collection
Article Astronomy & Astrophysics

MeerCRAB: MeerLICHT classification of real and bogus transients using deep learning

Zafiirah Hosenie et al.

Summary: Astronomers need efficient automated detection and classification pipelines for large-scale surveys. They presented a deep learning pipeline called MeerCRAB to filter out true astrophysical sources. The pipeline integrates with the MeerLICHT transient vetting pipeline for accurate and efficient classification of detected transients.

EXPERIMENTAL ASTRONOMY (2021)

Add to Collection
Article Astronomy & Astrophysics

Hefty enhancement of cosmological constraints from the DES Y1 data using a hybrid effective field theory approach to galaxy bias

Boryana Hadzhiyska et al.

Summary: This study reanalyzes cosmic shear and galaxy clustering data from the first year of the Dark Energy Survey, using a Hybrid Effective Field Theory (HEFT) approach to model the galaxy-matter relation on weakly non-linear scales. The results show an improvement in cosmological constraints by extending the galaxy clustering scale range and using the HEFT model to explain the data up to certain wavenumbers. Constraints on parameters such as (S-8, Omega(m)) and Hubble parameter are derived, but the results are investigative and subject to caveats discussed in the text.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Galaxy morphological classification catalogue of the Dark Energy Survey Year 3 data with convolutional neural networks

Ting-Yun Cheng et al.

Summary: In this study, a galaxy morphological classification catalogue with over 20 million galaxies is presented, based on DES Year 3 data and CNN technology, achieving an accuracy of over 99% for bright galaxies. The researchers found that the Gini coefficient is the best parameter discriminator between elliptical and spiral galaxies.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

A sparse regression approach to modelling the relation between galaxy stellar masses and their host haloes

M. Icaza-Lizaola et al.

Summary: Sparse regression algorithms have been used to model the relationship between the stellar mass of central galaxies and host dark matter halo properties without prior knowledge of physics. The model accurately reproduces the stellar mass function and central galaxy correlation function in EAGLE simulations with a root mean square error of 0.167log(10) (M*/M_sun), demonstrating promising potential for populating galaxies in dark matter-only simulations.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Benchmarking and scalability of machine-learning methods for photometric redshift estimation

Ben Henghes et al.

Summary: The study focused on the performance and scalability of various supervised machine-learning methods for photometric redshift estimation, with Random Forest algorithm demonstrating the best results. Introducing a new optimization method and exploring the impact of error concessions on efficiency, benchmarks showed how different algorithms could excel in different scenarios. Benchmarks like this will be crucial for future surveys, such as LSST, with billions of galaxies requiring photometric redshifts.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

AI-assisted superresolution cosmological simulations - II. Halo substructures, velocities, and higher order statistics

Yueying Ni et al.

Summary: The study focuses on expanding and testing the capabilities of a superresolution model for generating high-resolution realizations of matter distribution, and demonstrates its potential in modeling small-scale galaxy formation physics in large cosmological volumes.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

The BACCO simulation project: exploiting the full power of large-scale structure for cosmology

Raul E. Angulo et al.

Summary: The BACCO project presents a simulation framework designed for accurate predictions of mass, galaxies, and gas distribution based on cosmological parameters. The gravity-only simulations and cosmology-rescaling technique used in the project demonstrate high accuracy in predicting the non-linear mass power spectrum over a wide redshift range and scales. The emulator built for efficient interpolation of results shows promising accuracy levels, making predictions at the 2-3% level for various cosmological models.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks

Kate Storey-Fisher et al.

Summary: In the study, an unsupervised anomaly detection method using a Wasserstein generative adversarial network (WGAN) was applied to nearly one million optical galaxy images in the Hyper Suprime-Cam (HSC) survey. The discriminator was found to be more sensitive to potentially interesting anomalies compared to the generator. By using a convolutional autoencoder to reduce dimensionality of differences between real and WGAN-reconstructed images and performing UMAP clustering, various interesting anomalies were detected including galaxy mergers, tidal features, and extreme star-forming galaxies.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

GalaxyNet: connecting galaxies and dark matter haloes with deep neural networks and reinforcement learning in large volumes

Benjamin P. Moster et al.

Summary: GalaxyNet is a novel wide and deep neural network, which is trained directly on observed galaxy statistics using reinforcement learning. The model accurately reproduces observed data and predicts a stellar-to-halo mass relation with a lower normalization and shallower low-mass slope at high redshift. Additionally, GalaxyNet is used to populate a cosmic volume and predict various galaxy properties up to z = 4, which can be tested with next-generation surveys.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Cosmic shear cosmology beyond two-point statistics: a combined peak count and correlation function analysis of DES-Y1

Joachim Harnois-Deraps et al.

Summary: In this study, cosmological parameters are constrained through a joint analysis of peak counts and two-point shear correlation functions from the Dark Energy Survey (DES-Y1). The structure growth parameter S-8 is determined to be 0.766(-0.038)(+0.033), providing one of the tightest constraints on S-8 from DES-Y1 weak lensing data with 4.8 percent precision. Through simulations, the expected DES-Y1 peak-count signal for various cosmologies is determined, and the impact of photometric redshift and shear calibration uncertainty is calibrated in the cosmological analysis.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

The BACCO simulation project: a baryonification emulator with neural networks

Giovanni Arico et al.

Summary: The study introduces a neural network emulator for baryonic effects in the non-linear matter power spectrum. By calibrating the emulator in a wide parameter space, the precision of the emulator is estimated to be 2-3% at specific scales and redshift ranges. Through comparison with various cosmological simulations, the accuracy of the emulator is validated.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Deep learning approach for identification of H II regions during reionization in 21-cm observations

Michele Bianco et al.

Summary: The study presents a method called SegU-Net for identifying neutral and ionized regions in images, providing accurate image segmentation of data produced by SKA-Low. Through simulated observations of SKA, it is possible to accurately estimate the ionization history, and SegU-Net can also recover size distributions and Betti numbers with a relative difference of only a few percent.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

ABACUSSUMMIT: a massive set of high-accuracy, high-resolution N-body simulations

Nina A. Maksimova et al.

Summary: The ABACUSSUMMIT cosmological N-body simulation suite is released publicly, produced using the ABACUS N-body code on the Summit supercomputer. It achieves a high accuracy of O(10(-5)) and high speeds, with a total of 60 trillion particles and coverage for 97 cosmological models across 33 epochs.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

Predicting 21cm-line map from Lyman-α emitter distribution with generative adversarial networks

Shintaro Yoshiura et al.

Summary: The research explores the evolution of galaxies and intergalactic medium in the early Universe through radio observations of 21cm-line signals from the epoch of reionization (EoR). A new approach is proposed to increase the detectability of the 21cm-line signal by taking a cross correlation between observed data and images generated through machine learning. Results show that the method can effectively reproduce brightness temperature maps and neutral fraction maps at large scales.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2021)

Add to Collection
Article Astronomy & Astrophysics

MADLens, a python package for fast and differentiable non-Gaussian lensing simulations

V. Bohm et al.

Summary: MADLens is a Python package designed to produce non-Gaussian lensing convergence maps with unprecedented precision at arbitrary source redshifts. It achieves high accuracy through a combination of highly parallelizable algorithms, a sub-evolution scheme in the lensing projection, and a machine-learning inspired sharpening step. MADLens is fully differentiable with respect to initial conditions and cosmological parameters, making it useful for Bayesian inference algorithms and large, high-resolution simulation sets for deep-learning-based lensing analysis tools.

ASTRONOMY AND COMPUTING (2021)

Add to Collection
Article Astronomy & Astrophysics

Deep learning simulations of the microwave sky

Dongwon Han et al.

Summary: In this work, a procedure is developed to mass produce independent full-sky realizations from a single expensive full-sky simulation, circumventing common limitations of high-resolution DL simulations. By taking a full-sky lensing convergence map as input, the network can generate corresponding lensed CMB and correlated foreground components at millimeter wavelengths.

PHYSICAL REVIEW D (2021)

Add to Collection
Article Astronomy & Astrophysics

Extracting cosmological parameters from N-body simulations using machine learning techniques

Andrei Lazanu

Summary: Machine learning techniques accurately extract cosmological parameters Omega(m) and sigma(8) from N-body simulations, and also find these parameters from the non-linear matter power spectrum using random forest regressors and deep neural networks. The power spectrum provides competitive results in terms of accuracy compared to using simulations, and the scalar spectral index ns can also be estimated from the power spectrum with lower precision.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2021)

Add to Collection
Article Astronomy & Astrophysics

Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Cosmological implications from two decades of spectroscopic surveys at the Apache Point Observatory

Shadab Alam et al.

Summary: Based on the final measurements of clustering using galaxies, quasars, and Ly alpha forests from the SDSS lineage, this study provides comprehensive cosmological implications. The BAO data alone can rule out dark-energy-free models, and when combined with other measurements, significant improvements are made on constraining cosmological parameters within the ΛCDM model. The results indicate that various parameter extensions remain consistent with a ΛCDM model in a combined analysis, showing precision changes of less than 0.6% in key parameters.

PHYSICAL REVIEW D (2021)

Add to Collection
Article Astronomy & Astrophysics

Removing Astrophysics in 21 cm Maps with Neural Networks

Pablo Villanueva-Domingo et al.

Summary: Studying temperature fluctuations in the 21 cm signal is a promising way to explore the universe at high redshifts, but the signal is influenced by cosmology and astrophysical processes. Researchers conducted numerous numerical simulations and trained a convolutional neural network to remove astrophysical effects from the 21 cm maps, generating maps of the underlying matter field.

ASTROPHYSICAL JOURNAL (2021)

Add to Collection
Article Astronomy & Astrophysics

Galaxy morphological classification in deep-wide surveys via unsupervised machine learning

G. Martin et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Cosmology inference from a biased density field using the EFT-based likelihood

Franz Elsner et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2020)

Add to Collection
Article Physics, Applied

Updated Design of the CMB Polarization Experiment Satellite LiteBIRD

H. Sugai et al.

JOURNAL OF LOW TEMPERATURE PHYSICS (2020)

Add to Collection
Article Astronomy & Astrophysics

Cosmology with galaxy-galaxy lensing on non-perturbative scales: emulation method and application to BOSS LOWZ

Benjamin D. Wibking et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Simulations and symmetries

Chirag Modi et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Photometry of high-redshift blended galaxies using deep learning

Alexandre Boucaud et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Deep learning dark matter map reconstructions from DES SV weak lensing data

Niall Jeffrey et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

A unified framework for 21 cm tomography sample generation and parameter inference with progressively growing GANs

Florian List et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Editorial Material Multidisciplinary Sciences

Big telescope, big data: towards exascale with the Square Kilometre Array

A. M. M. Scaife

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2020)

Add to Collection
Article Astronomy & Astrophysics

Planck 2018 results: VI. Cosmological parameters

N. Aghanim et al.

ASTRONOMY & ASTROPHYSICS (2020)

Add to Collection
Article Astronomy & Astrophysics

The EFT likelihood for large-scale structure

Giovanni Cabass et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2020)

Add to Collection
Article Multidisciplinary Sciences

The frontier of simulation-based inference

Kyle Cranmer et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

Add to Collection
Article Astronomy & Astrophysics

Super-resolution emulator of cosmological simulations using deep physical models

Doogesh Kodi Ramanah et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Generating synthetic cosmological data with GalSampler

Andrew Hearin et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Deep learning for strong lensing search: tests of the convolutional neural networks and new candidates from KiDS DR3

Zizhao He et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Using machine learning for transient classification in searches for gravitational-wave counterparts

Cosmin Stachie et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Parameter inference for weak lensing using Gaussian Processes and MOPED

Arrykrishna Mootoovaloo et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Vetting the optical transient candidates detected by the GWAC network using convolutional neural networks

Damien Turpin et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Evaluation of probabilistic photometric redshift estimation approaches for The Rubin Observatory Legacy Survey of Space and Time (LSST)

S. J. Schmidt et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Analysing the Epoch of Reionization with three-point correlation functions and machine learning techniques

W. D. Jennings et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Cosmological parameter estimation via iterative emulation of likelihoods

Marcos Pellejero-Ibanez et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

Photometric classification of Hyper Suprime-Cam transients using machine learning

Ichiro Takahashi et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2020)

Add to Collection
Article Astronomy & Astrophysics

Euclid preparation: X. The Euclid photometric-redshift challenge

G. Desprez et al.

ASTRONOMY & ASTROPHYSICS (2020)

Add to Collection
Article Astronomy & Astrophysics

Inpainting Galactic Foreground Intensity and Polarization Maps Using Convolutional Neural Networks

Giuseppe Puglisi et al.

ASTROPHYSICAL JOURNAL (2020)

Add to Collection
Editorial Material Physics, Applied

Electromagnetic counterparts of gravitational wave sources at the Very Large Telescope

Andrew J. Levan et al.

NATURE REVIEWS PHYSICS (2020)

Add to Collection
Article Astronomy & Astrophysics

Interpreting deep learning models for weak lensing

Jose Manuel Zorrilla Matilla et al.

PHYSICAL REVIEW D (2020)

Add to Collection
Article Astronomy & Astrophysics

Unbiased cosmology inference from biased tracers using the EFT likelihood

Fabian Schmidt et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2020)

Add to Collection
Article Astronomy & Astrophysics

SuperRAENN: A Semisupervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium-Deep Survey Supernovae

V. Ashley Villar et al.

ASTROPHYSICAL JOURNAL (2020)

Add to Collection
Article Astronomy & Astrophysics

First Cosmology Results using Supernovae Ia from the Dark Energy Survey: Survey Overview, Performance, and Supernova Spectroscopy

M. Smith et al.

ASTRONOMICAL JOURNAL (2020)

Add to Collection
Article Astronomy & Astrophysics

Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning

Matthew A. Petroff et al.

ASTROPHYSICAL JOURNAL (2020)

Add to Collection
Article Astronomy & Astrophysics

The Mira-Titan Universe. III. Emulation of the Halo Mass Function

Sebastian Bocquet et al.

ASTROPHYSICAL JOURNAL (2020)

Add to Collection
Article Astronomy & Astrophysics

Accurate emulator for the redshift-space power spectrum of dark matter halos and its application to galaxy power spectrum

Yosuke Kobayashi et al.

PHYSICAL REVIEW D (2020)

Add to Collection
Article Astronomy & Astrophysics

The Quijote Simulations

Francisco Villaescusa-Navarro et al.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2020)

Add to Collection
Article Astronomy & Astrophysics

A Hybrid Deep Learning Approach to Cosmological Constraints from Galaxy Redshift Surveys

Michelle Ntampaka et al.

ASTROPHYSICAL JOURNAL (2020)

Add to Collection
Article Astronomy & Astrophysics

Finding Strong Gravitational Lenses in the DESI DECam Legacy Survey

X. Huang et al.

ASTROPHYSICAL JOURNAL (2020)

Add to Collection
Review Physics, Applied

Cosmological simulations of galaxy formation

Mark Vogelsberger et al.

NATURE REVIEWS PHYSICS (2020)

Add to Collection
Article Astronomy & Astrophysics

Deep learning for intensity mapping observations: component extraction

Kana Moriwaki et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2020)

Add to Collection
Article Astronomy & Astrophysics

The Simons Observatory: science goals and forecasts

Peter Ade et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2019)

Add to Collection
Article Astronomy & Astrophysics

An emulator for the Lyman-α forest

Simeon Bird et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2019)

Add to Collection
Article Astronomy & Astrophysics

Separating the EoR signal with a convolutional denoising autoencoder: a deep-learning-based method

Weitian Li et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

Cosmology from cosmic shear power spectra with Subaru Hyper Suprime-Cam first-year data

Chiaki Hikage et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2019)

Add to Collection
Article Multidisciplinary Sciences

Unmasking Clever Hans predictors and assessing what machines really learn

Sebastian Lapuschkin et al.

NATURE COMMUNICATIONS (2019)

Add to Collection
Article Astronomy & Astrophysics

The fourth data release of the Kilo-Degree Survey: ugri imaging and nine-band optical-IR photometry over 1000 square degrees

K. Kuijken et al.

ASTRONOMY & ASTROPHYSICS (2019)

Add to Collection
Article Astronomy & Astrophysics

The strong gravitational lens finding challenge

R. B. Metcalf et al.

ASTRONOMY & ASTROPHYSICS (2019)

Add to Collection
Article Astronomy & Astrophysics

Constraining neutrino mass with the tomographic weak lensing bispectrum

William R. Coulton et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2019)

Add to Collection
Article Astronomy & Astrophysics

UNIVERSEMACHINE: The correlation between galaxy growth and dark matter halo assembly from z=0-10

Peter Behroozi et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

The Hyper Suprime-Cam SSP transient survey in COSMOS: Overview

Naoki Yasuda et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2019)

Add to Collection
Article Astronomy & Astrophysics

The Zwicky Transient Facility: Surveys and Scheduler

Eric C. Bellm et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC (2019)

Add to Collection
Article Astronomy & Astrophysics

Constraining neutrino mass with weak lensing Minkowski Functionals

Gabriela A. Marques et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2019)

Add to Collection
Article Multidisciplinary Sciences

Learning to predict the cosmological structure formation

Siyu He et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2019)

Add to Collection
Article Astronomy & Astrophysics

DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks

J. Caldeira et al.

ASTRONOMY AND COMPUTING (2019)

Add to Collection
Article Astronomy & Astrophysics

Machine-assisted semi-simulation model (MSSM): estimating galactic baryonic properties from their dark matter using a machine trained on hydrodynamic simulations

Yongseok Jo et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

Real-bogus classification for the Zwicky Transient Facility using deep learning

Dmitry A. Duev et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

On the road to per cent accuracy - II. Calibration of the non-linear matter power spectrum for arbitrary cosmologies

Benjamin Giblin et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

Improved supervised learning methods for EoR parameters reconstruction

Aristide Doussot et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

RAPID: Early Classification of Explosive Transients Using Deep Learning

Daniel Muthukrishna et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC (2019)

Add to Collection
Article Astronomy & Astrophysics

Cosmic shear covariance matrix in wCDM: Cosmology matters

J. Harnois-Deraps et al.

ASTRONOMY & ASTROPHYSICS (2019)

Add to Collection
Article Astronomy & Astrophysics

Weak lensing cosmology with convolutional neural networks on noisy data

Dezso Ribli et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

Cosmological inference from Bayesian forward modelling of deep galaxy redshift surveys

Doogesh Kodi Ramanah et al.

ASTRONOMY & ASTROPHYSICS (2019)

Add to Collection
Article Astronomy & Astrophysics

Deep learning from 21-cm tomography of the cosmic dawn and reionization

Nicolas Gillet et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

Identifying reionization sources from 21 cm maps using Convolutional Neural Networks

Sultan Hassan et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

LinKS: discovering galaxy-scale strong lenses in the Kilo-Degree Survey using convolutional neural networks

C. E. Petrillo et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

Euclid preparation: II. The EUCLIDEMULATOR - a tool to compute the cosmology dependence of the nonlinear matter power spectrum

Mischa Knabenhans et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

An improved cosmological parameter inference scheme motivated by deep learning

Dezso Ribli et al.

NATURE ASTRONOMY (2019)

Add to Collection
Article Astronomy & Astrophysics

DASH: Deep Learning for the Automated Spectral Classification of Supernovae and Their Hosts

Daniel Muthukrishna et al.

ASTROPHYSICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

The Photometric LSST Astronomical Time-series Classification Challenge PLAsTiCC: Selection of a Performance Metric for Classification Probabilities Balancing Diverse Science Goals

A. Malz et al.

ASTRONOMICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-deep Survey

V. A. Villar et al.

ASTROPHYSICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

Painting with baryons: augmenting N-body simulations with gas using deep generative models

Tilman Troester et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2019)

Add to Collection
Article Astronomy & Astrophysics

The AEMULUS Project. I. Numerical Simulations for Precision Cosmology

Joseph DeRose et al.

ASTROPHYSICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

Constraining neutrino mass with the tomographic weak lensing one-point probability distribution function and power spectrum

Jia Liu et al.

PHYSICAL REVIEW D (2019)

Add to Collection
Article Astronomy & Astrophysics

Dark Quest. I. Fast and Accurate Emulation of Halo Clustering Statistics and Its Application to Galaxy Clustering

Takahiro Nishimichi et al.

ASTROPHYSICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

Constraining neutrino mass with tomographic weak lensing peak counts

Zack Li et al.

PHYSICAL REVIEW D (2019)

Add to Collection
Article Astronomy & Astrophysics

The Aemulus Project. III. Emulation of the Galaxy Correlation Function

Zhongxu Zhai et al.

ASTROPHYSICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

A Framework for Telescope Schedulers: With Applications to the Large Synoptic Survey Telescope

Elahesadat Naghib et al.

ASTRONOMICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation

Kyle Boone

ASTRONOMICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

LSST: From Science Drivers to Reference Design and Anticipated Data Products

Zeljko Ivezic et al.

ASTROPHYSICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

The Aemulus Project. II. Emulating the Halo Mass Function

Thomas Mcclintock et al.

ASTROPHYSICAL JOURNAL (2019)

Add to Collection
Article Astronomy & Astrophysics

STACCATO: a novel solution to supernova photometric classification with biased training sets

E. A. Revsbech et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2018)

Add to Collection
Article Astronomy & Astrophysics

Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks

C. J. Schmit et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2018)

Add to Collection
Article Astronomy & Astrophysics

Hyper Suprime-Cam: System design and verification of image quality

Satoshi Miyazaki et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2018)

Add to Collection
Article Astronomy & Astrophysics

Photometric redshifts for Hyper Suprime-Cam Subaru Strategic Program Data Release 1

Masayuki Tanaka et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2018)

Add to Collection
Article Astronomy & Astrophysics

MassiveNuS: cosmological massive neutrino simulations

Jia Liu et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2018)

Add to Collection
Article Astronomy & Astrophysics

Exploring the posterior surface of the large scale structure reconstruction

Yu Feng et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2018)

Add to Collection
Article Astronomy & Astrophysics

The skewed weak lensing likelihood: why biases arise, despite data and theory being sound

Elena Sellentin et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2018)

Add to Collection
Article Astronomy & Astrophysics

Painting galaxies into dark matter haloes using machine learning

Shankar Agarwal et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2018)

Add to Collection
Article Astronomy & Astrophysics

Predicting the neutral hydrogen content of galaxies from optical data using machine learning

Mika Rafieferantsoa et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2018)

Add to Collection
Review Physics, Multidisciplinary

Large-scale galaxy bias

Vincent Desjacques et al.

PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS (2018)

Add to Collection
Review Astronomy & Astrophysics

Weak Lensing for Precision Cosmology

Rachel Mandelbaum

ANNUAL REVIEW OF ASTRONOMY AND ASTROPHYSICS, VOL 56 (2018)

Add to Collection
Article Astronomy & Astrophysics

Photometric redshifts for the Kilo-Degree Survey Machine-learning analysis with artificial neural networks

M. Bilicki et al.

ASTRONOMY & ASTROPHYSICS (2018)

Add to Collection
Article Astronomy & Astrophysics

Star-galaxy classification in the Dark Energy Survey Y1 data set

I. Sevilla-Noarbe et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2018)

Add to Collection
Article Astronomy & Astrophysics

Learning from the machine: interpreting machine learning algorithms for point- and extended-source classification

Xan Morice-Atkinson et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2018)

Add to Collection
Article Astronomy & Astrophysics

Photometric redshifts from SDSS images using a convolutional neural network

Johanna Pasquet et al.

ASTRONOMY & ASTROPHYSICS (2018)

Add to Collection
Article Astronomy & Astrophysics

The Abacus Cosmos: A Suite of Cosmological N-body Simulations

Lehman H. Garrison et al.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2018)

Add to Collection
Article Astronomy & Astrophysics

Non-Gaussian Information from weak lensing data via deep learning

Arushi Gupta et al.

PHYSICAL REVIEW D (2018)

Add to Collection
Article Astronomy & Astrophysics

Bayesian optimization for likelihood-free cosmological inference

Florent Leclercq

PHYSICAL REVIEW D (2018)

Add to Collection
Proceedings Paper Computer Science, Interdisciplinary Applications

Transfer Learning in Astronomy: A New Machine-Learning Paradigm

Ricardo Vilalta

18TH INTERNATIONAL WORKSHOP ON ADVANCED COMPUTING AND ANALYSIS TECHNIQUES IN PHYSICS RESEARCH (ACAT2017) (2018)

Add to Collection
Article Astronomy & Astrophysics

Cosmological constraints from noisy convergence maps through deep learning

Janis Fluri et al.

PHYSICAL REVIEW D (2018)

Add to Collection
Article Astronomy & Astrophysics

CFHTLenS revisited: assessing concordance with Planck including astrophysical systematics

Shahab Joudaki et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2017)

Add to Collection
Article Astronomy & Astrophysics

Towards optimal extraction of cosmological information from nonlinear data

Uros Seljak et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2017)

Add to Collection
Article Astronomy & Astrophysics

Finding strong gravitational lenses in the Kilo Degree Survey with Convolutional Neural Networks

C. E. Petrillo et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2017)

Add to Collection
Article Astronomy & Astrophysics

Convolutional neural networks for transient candidate vetting in large-scale surveys

Fabian Gieseke et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2017)

Add to Collection
Article Astronomy & Astrophysics

Approximate Bayesian computation in large-scale structure: constraining the galaxy-halo connection

ChangHoon Hahn et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2017)

Add to Collection
Article Astronomy & Astrophysics

Analysing the 21 cm signal from the epoch of reionization with artificial neural networks

Hayato Shimabukuro et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2017)

Add to Collection
Article Astronomy & Astrophysics

The clustering of galaxies in the completed SDSS-III Baryon Oscillation Spectroscopic Survey: cosmological analysis of the DR12 galaxy sample

Shadab Alam et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2017)

Add to Collection
Article Multidisciplinary Sciences

Fast automated analysis of strong gravitational lenses with convolutional neural networks

Yashar D. Hezaveh et al.

NATURE (2017)

Add to Collection
Article Astronomy & Astrophysics

Automated novelty detection in the WISE survey with one-class support vector machines

A. Solarz et al.

ASTRONOMY & ASTROPHYSICS (2017)

Add to Collection
Article Astronomy & Astrophysics

The VIMOS Public Extragalactic Redshift Survey (VIPERS) The growth of structure at 0.5 < z < 1.2 from redshift-space distortions in the clustering of the PDR-2 final sample

A. Pezzotta et al.

ASTRONOMY & ASTROPHYSICS (2017)

Add to Collection
Article Astronomy & Astrophysics

The third data release of the Kilo-Degree Survey and associated data products

Jelte T. A. de Jong et al.

ASTRONOMY & ASTROPHYSICS (2017)

Add to Collection
Article Astronomy & Astrophysics

Emulating Simulations of Cosmic Dawn for 21cm Power Spectrum Constraints on Cosmology, Reionization, and X-Ray Heating

Nicholas S. Kern et al.

ASTROPHYSICAL JOURNAL (2017)

Add to Collection
Article Astronomy & Astrophysics

The Mira-Titan Universe. II. Matter Power Spectrum Emulation

Earl Lawrence et al.

ASTROPHYSICAL JOURNAL (2017)

Add to Collection
Article Astronomy & Astrophysics

The Electromagnetic Counterpart of the Binary Neutron Star Merger LIGO/Virgo GW170817. I. Discovery of the Optical Counterpart Using the Dark Energy Camera

M. Soares-Santos et al.

ASTROPHYSICAL JOURNAL LETTERS (2017)

Add to Collection
Article Astronomy & Astrophysics

Limits on the Ultra-bright Fast Radio Burst Population from the CHIME Pathfinder

M. Amiri et al.

ASTROPHYSICAL JOURNAL (2017)

Add to Collection
Article Astronomy & Astrophysics

Deep Recurrent Neural Networks for Supernovae Classification

Tom Charnock et al.

ASTROPHYSICAL JOURNAL LETTERS (2017)

Add to Collection
Article Astronomy & Astrophysics

Exploring the spectroscopic diversity of Type Ia supernovae with DRACULA: a machine learning approach

M. Sasdelli et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2016)

Add to Collection
Article Astronomy & Astrophysics

Machine learning and cosmological simulations - II. Hydrodynamical simulations

Harshil M. Kamdar et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2016)

Add to Collection
Article Astronomy & Astrophysics

Machine-learning selection of optical transients in the Subaru/Hyper Suprime-Cam survey

Mikio Morii et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2016)

Add to Collection
Article Astronomy & Astrophysics

The Subaru FMOS galaxy redshift survey (FastSound). IV. New constraint on gravity theory from redshift space distortions at z ∼ 1.4

Teppei Okumura et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2016)

Add to Collection
Article Astronomy & Astrophysics

THE MIRA-TITAN UNIVERSE: PRECISION PREDICTIONS FOR DARK ENERGY SURVEYS

Katrin Heitmann et al.

ASTROPHYSICAL JOURNAL (2016)

Add to Collection
Proceedings Paper Astronomy & Astrophysics

The LSST Scheduler from design to construction

Francisco Delgado et al.

OBSERVATORY OPERATIONS: STRATEGIES, PROCESSES, AND SYSTEMS VI (2016)

Add to Collection
Article Astronomy & Astrophysics

PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING

Michelle Lochner et al.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2016)

Add to Collection
Review Astronomy & Astrophysics

Physical Models of Galaxy Formation in a Cosmological Framework

Rachel S. Somerville et al.

ANNUAL REVIEW OF ASTRONOMY AND ASTROPHYSICS, VOL 53 (2015)

Add to Collection
Article Astronomy & Astrophysics

A new model to predict weak-lensing peak counts II. Parameter constraint strategies

Chieh-An Lin et al.

ASTRONOMY & ASTROPHYSICS (2015)

Add to Collection
Article Astronomy & Astrophysics

Approximate Bayesian computation for forward modeling in cosmology

Joel Akeret et al.

JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS (2015)

Add to Collection
Article Astronomy & Astrophysics

Machine learning for transient discovery in Pan-STARRS1 difference imaging

D. E. Wright et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2015)

Add to Collection
Article Astronomy & Astrophysics

CFHTLenS: a Gaussian likelihood is a sufficient approximation for a cosmological analysis of third-order cosmic shear statistics

P. Simon et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2015)

Add to Collection
Article Astronomy & Astrophysics

Data augmentation for machine learning redshifts applied to Sloan Digital Sky Survey galaxies

Ben Hoyle et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2015)

Add to Collection
Article Astronomy & Astrophysics

An accurate halo model for fitting non-linear cosmological power spectra and baryonic feedback models

A. J. Mead et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2015)

Add to Collection
Article Astronomy & Astrophysics

Emulating the CFHTLenS weak lensing data: Cosmological constraints from moments and Minkowski functionals

Andrea Petri et al.

PHYSICAL REVIEW D (2015)

Add to Collection
Article Astronomy & Astrophysics

Cosmology constraints from the weak lensing peak counts and the power spectrum in CFHTLenS data

Jia Liu et al.

PHYSICAL REVIEW D (2015)

Add to Collection
Article Statistics & Probability

Optimal Sliced Latin Hypercube Designs

Shan Ba et al.

TECHNOMETRICS (2015)

Add to Collection
Article Astronomy & Astrophysics

A new model to predict weak-lensing peak counts II. Parameter constraint strategies

Chieh-An Lin et al.

ASTRONOMY & ASTROPHYSICS (2015)

Add to Collection
Article Astronomy & Astrophysics

COSMOABC: Likelihood-free inference via Population Monte Carlo Approximate Bayesian Computation

E. E. O. Ishida et al.

ASTRONOMY AND COMPUTING (2015)

Add to Collection
Article Astronomy & Astrophysics

Matter power spectrum covariance matrix from the DEUS-PUR Λ CDM simulations: mass resolution and non-Gaussian errors

L. Blot et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2015)

Add to Collection
Article Astronomy & Astrophysics

A CATALOG OF VISUAL-LIKE MORPHOLOGIES IN THE 5 CANDELS FIELDS USING DEEP LEARNING

M. Huertas-Company et al.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2015)

Add to Collection
Article Astronomy & Astrophysics

COSMIC EMULATION: FAST PREDICTIONS FOR THE GALAXY POWER SPECTRUM

Juliana Kwan et al.

ASTROPHYSICAL JOURNAL (2015)

Add to Collection
Article Astronomy & Astrophysics

A MACHINE LEARNING APPROACH FOR DYNAMICAL MASS MEASUREMENTS OF GALAXY CLUSTERS

M. Ntampaka et al.

ASTROPHYSICAL JOURNAL (2015)

Add to Collection
Article Astronomy & Astrophysics

THE COYOTE UNIVERSE EXTENDED: PRECISION EMULATION OF THE MATTER POWER SPECTRUM

Katrin Heitmann et al.

ASTROPHYSICAL JOURNAL (2014)

Add to Collection
Article Astronomy & Astrophysics

pkann - II. A non-linear matter power spectrum interpolator developed using artificial neural networks

Shankar Agarwal et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2014)

Add to Collection
Article Astronomy & Astrophysics

Seeing in the dark - II. Cosmic shear in the Sloan Digital Sky Survey

Eric M. Huff et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2014)

Add to Collection
Review Astronomy & Astrophysics

Extragalactic science, cosmology, and Galactic archaeology with the Subaru Prime Focus Spectrograph

Masahiro Takada et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN (2014)

Add to Collection
Article Astronomy & Astrophysics

On the assumption of Gaussianity for cosmological two-point statistics and parameter dependent covariance matrices (Research Note)

J. Carron

ASTRONOMY & ASTROPHYSICS (2013)

Add to Collection
Article Astronomy & Astrophysics

COSMIC EMULATION: THE CONCENTRATION-MASS RELATION FOR wCDM UNIVERSES

Juliana Kwan et al.

ASTROPHYSICAL JOURNAL (2013)

Add to Collection
Article Astronomy & Astrophysics

A FIRST LOOK AT CREATING MOCK CATALOGS WITH MACHINE LEARNING TECHNIQUES

Xiaoying Xu et al.

ASTROPHYSICAL JOURNAL (2013)

Add to Collection
Article Astronomy & Astrophysics

LIKELIHOOD-FREE COSMOLOGICAL INFERENCE WITH TYPE Ia SUPERNOVAE: APPROXIMATE BAYESIAN COMPUTATION FOR A COMPLETE TREATMENT OF UNCERTAINTY

Anja Weyant et al.

ASTROPHYSICAL JOURNAL (2013)

Add to Collection
Review Physics, Particles & Fields

Cosmology and Fundamental Physics with the Euclid Satellite

Luca Amendola et al.

LIVING REVIEWS IN RELATIVITY (2013)

Add to Collection
Article Astronomy & Astrophysics

Bayesian physical reconstruction of initial conditions from large-scale structure surveys

Jens Jasche et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2013)

Add to Collection
Article Astronomy & Astrophysics

The effective number density of galaxies for weak lensing measurements in the LSST project

C. Chang et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2013)

Add to Collection
Article Astronomy & Astrophysics

Galaxy Zoo 2: detailed morphological classifications for 304 122 galaxies from the Sloan Digital Sky Survey

Kyle W. Willett et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2013)

Add to Collection
Article Astronomy & Astrophysics

Using machine learning for discovery in synoptic survey imaging data

Henrik Brink et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2013)

Add to Collection
Article Astronomy & Astrophysics

Photometric redshifts with the quasi Newton algorithm (MLPQNA) Results in the PHAT1 contest

S. Cavuoti et al.

ASTRONOMY & ASTROPHYSICS (2012)

Add to Collection
Article Astronomy & Astrophysics

EFFECT OF MODEL-DEPENDENT COVARIANCE MATRIX FOR STUDYING BARYON ACOUSTIC OSCILLATIONS

A. Labatie et al.

ASTROPHYSICAL JOURNAL (2012)

Add to Collection
Article Astronomy & Astrophysics

REVISING THE HALOFIT MODEL FOR THE NONLINEAR MATTER POWER SPECTRUM

Ryuichi Takahashi et al.

ASTROPHYSICAL JOURNAL (2012)

Add to Collection
Article Astronomy & Astrophysics

Unsupervised self-organized mapping: a versatile empirical tool for object selection, classification and redshift estimation in large surveys

James E. Geach

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2012)

Add to Collection
Article Astronomy & Astrophysics

PkANN - I. Non-linear matter power spectrum interpolation through artificial neural networks

Shankar Agarwal et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2012)

Add to Collection
Article Astronomy & Astrophysics

The 6dF Galaxy Survey: z∼ 0 measurements of the growth rate and s8

Florian Beutler et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2012)

Add to Collection
Article Astronomy & Astrophysics

The WiggleZ Dark Energy Survey: Final data release and cosmological results

David Parkinson et al.

PHYSICAL REVIEW D (2012)

Add to Collection
Article Astronomy & Astrophysics

Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era

J. S. Bloom et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC (2012)

Add to Collection
Review Physics, Nuclear

Supernova Cosmology: Legacy and Future

Ariel Goobar et al.

ANNUAL REVIEW OF NUCLEAR AND PARTICLE SCIENCE, VOL 61 (2011)

Add to Collection
Article Astronomy & Astrophysics

INTELLIGENT DESIGN: ON THE EMULATION OF COSMOLOGICAL SIMULATIONS

Michael D. Schneider et al.

ASTROPHYSICAL JOURNAL (2011)

Add to Collection
Article Astronomy & Astrophysics

Galaxy Zoo 1: data release of morphological classifications for nearly 900 000 galaxies

Chris Lintott et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2011)

Add to Collection
Article Astronomy & Astrophysics

Weak-lensing statistics from the Coyote Universe

Tim Eifler

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2011)

Add to Collection
Article Astronomy & Astrophysics

Copula cosmology: Constructing a likelihood function

Masanori Sato et al.

PHYSICAL REVIEW D (2011)

Add to Collection
Article Astronomy & Astrophysics

THE COYOTE UNIVERSE. III. SIMULATION SUITE AND PRECISION EMULATOR FOR THE NONLINEAR MATTER POWER SPECTRUM

Earl Lawrence et al.

ASTROPHYSICAL JOURNAL (2010)

Add to Collection
Article Astronomy & Astrophysics

THE COYOTE UNIVERSE. I. PRECISION DETERMINATION OF THE NONLINEAR MATTER POWER SPECTRUM

Katrin Heitmann et al.

ASTROPHYSICAL JOURNAL (2010)

Add to Collection
Article Astronomy & Astrophysics

Fast Hamiltonian sampling for large-scale structure inference

Jens Jasche et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2010)

Add to Collection
Article Astronomy & Astrophysics

Bayesian non-linear large-scale structure inference of the Sloan Digital Sky Survey Data Release 7

Jens Jasche et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2010)

Add to Collection
Article Multidisciplinary Sciences

An intensity map of hydrogen 21-cm emission at redshift z ≈ 0.8

Tzu-Ching Chang et al.

NATURE (2010)

Add to Collection
Article Astronomy & Astrophysics

Results from the Supernova Photometric Classification Challenge

Richard Kessler et al.

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC (2010)

Add to Collection
Article Astronomy & Astrophysics

Dependence of cosmic shear covariances on cosmology Impact on parameter estimation

T. Eifler et al.

ASTRONOMY & ASTROPHYSICS (2009)

Add to Collection
Article Astronomy & Astrophysics

The core-collapse rate from the Supernova Legacy Survey

G. Bazin et al.

ASTRONOMY & ASTROPHYSICS (2009)

Add to Collection
Article Astronomy & Astrophysics

THE COYOTE UNIVERSE. II. COSMOLOGICAL MODELS AND PRECISION EMULATION OF THE NONLINEAR MATTER POWER SPECTRUM

Katrin Heitmann et al.

ASTROPHYSICAL JOURNAL (2009)

Add to Collection
Article Astronomy & Astrophysics

EXPLOITING LOW-DIMENSIONAL STRUCTURE IN ASTRONOMICAL SPECTRA

Joseph W. Richards et al.

ASTROPHYSICAL JOURNAL (2009)

Add to Collection
Article Astronomy & Astrophysics

SIMULATIONS OF BARYON ACOUSTIC OSCILLATIONS. II. COVARIANCE MATRIX OF THE MATTER POWER SPECTRUM

Ryuichi Takahashi et al.

ASTROPHYSICAL JOURNAL (2009)

Add to Collection
Article Astronomy & Astrophysics

RICO: A NEW APPROACH FOR FAST AND ACCURATE REPRESENTATION OF THE COSMOLOGICAL RECOMBINATION HISTORY

W. A. Fendt et al.

ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES (2009)

Add to Collection
Article Astronomy & Astrophysics

A measurement of the rate of Type Ia supernovae at redshift z ≈ 0.1 from the first season of the SDSS-II Supernova Survey

Benjamin Dilday et al.

ASTROPHYSICAL JOURNAL (2008)

Add to Collection
Article Astronomy & Astrophysics

COSMONET: fast cosmological parameter estimation in non-flat models using neural networks

T. Auld et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2008)

Add to Collection
Article Astronomy & Astrophysics

The Sloan Digital Sky Survey-II Supernova Survey: Search algorithm and follow-up observations

Masao Sako et al.

ASTRONOMICAL JOURNAL (2008)

Add to Collection
Article Astronomy & Astrophysics

Cosmic calibration: Constraints from the matter power spectrum and the cosmic microwave background

Salman Habib et al.

PHYSICAL REVIEW D (2007)

Add to Collection
Article Astronomy & Astrophysics

How to find more supernovae with less work: Object classification techniques for difference imaging

S. Bailey et al.

ASTROPHYSICAL JOURNAL (2007)

Add to Collection
Article Astronomy & Astrophysics

Fast cosmological parameter estimation using neural networks

T. Auld et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2007)

Add to Collection
Article Astronomy & Astrophysics

Pico: Parameters for the impatient cosmologist

William A. Fendt et al.

ASTROPHYSICAL JOURNAL (2007)

Add to Collection
Article Astronomy & Astrophysics

Cosmic calibration

Katrin Heitmann et al.

ASTROPHYSICAL JOURNAL (2006)

Add to Collection
Article Astronomy & Astrophysics

The 2dF Galaxy Redshift Survey: power-spectrum analysis of the final data set and cosmological implications

S Cole et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2005)

Add to Collection
Article Astronomy & Astrophysics

Stable clustering, the halo model and non-linear cosmological power spectra

RE Smith et al.

MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY (2003)

Add to Collection
Review Physics, Multidisciplinary

Halo models of large scale structure

A Cooray et al.

PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS (2002)

Add to Collection
Article Astronomy & Astrophysics

Spectroscopic target selection for the Sloan Digital Sky Survey: The luminous red galaxy sample

DJ Eisenstein et al.

ASTRONOMICAL JOURNAL (2001)

Add to Collection
Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)

Add to Collection
Webinars Posters Questions Hubs Funding Journals Papers Connect Collections Reviewers About Us FAQs Mobile App Privacy Policy Terms of Use
© Peeref 2019-2024. All rights reserved.