DeepMerge: Classifying high-redshift merging galaxies with deep neural networks

Ćiprijanović, Aleksandra; Snyder, Gregory F.; Nord, B.; Peek, J. E. G.

doi:10.1016/j.ascom.2020.100390

Cited by 47 publications

(18 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simet et al (2019) used neural networks trained on semi-analytic catalogs tuned to the CANDELS (Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey, Grogin et al (2011)) survey to predict stellar mass, metallicity, and average star formation rate. Owing to their superior ability in capturing non-linearity in data, ML-based models have seen applications in almost every field of astronomical study, including identification of supernovae (D'Isanto et al 2016), classification of galaxy images (Cheng et al 2020a,b;Hausen & Robertson 2020;Ćiprijanović et al 2020;Barchi et al 2020), and categorization of signals observed in a radio SETI experiment (Harp et al 2019). With the exponential growth of astronomical datasets, ML based models are slowly becoming an integral part of all major data processing pipelines (Siemiginowska et al 2019).…”

Section: Machine Learning and Sed Fittingmentioning

confidence: 99%

{\sc mirkwood:} Fast and Accurate SED Modeling Using Machine Learning

Gilda,

Lower,

Narayanan

2021

Preprint

View full text Add to dashboard Cite

Traditional spectral energy distribution (SED) fitting codes used to derive galaxy physical properties are often uncertain at the factor of a few level owing to uncertainties in galaxy star formation histories and dust attenuation curves. Beyond this, Bayesian fitting (which is typically used in SED fitting software) is an intrinsically compute-intensive task, often requiring access to expensive hardware for long periods of time. To overcome these shortcomings, we have developed mirkwood: a user-friendly tool comprising of an ensemble of supervised machine learning-based models capable of non-linearly mapping galaxy fluxes to their properties. By stacking multiple models, we marginalize against any individual model's poor performance in a given region of the parameter space. We demonstrate mirkwood's significantly improved performance over traditional techniques by training it on a combined data set of mock photometry of z=0 galaxies from the Simba, EAGLE and IllustrisTNG cosmological simulations, and comparing the derived results with those obtained from traditional SED fitting techniques. mirkwood is also able to account for uncertainties arising both from intrinsic noise in observations, and from finite training data and incorrect modeling assumptions. To increase the added value to the observational community, we use Shapley value explanations (SHAP) to fairly evaluate the relative importance of different bands to understand why particular predictions were reached. We envisage mirkwood to be an evolving, open-source framework that will provide highly accurate physical properties from observations of galaxies as compared to traditional SED fitting.

show abstract

Section: Machine Learning and Sed Fittingmentioning

confidence: 99%

{\sc mirkwood:} Fast and Accurate SED Modeling Using Machine Learning

Gilda,

Lower,

Narayanan

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Automated methods that employ deep learning techniques, a sub-field of machine learning based on artificial neural networks with representation learning, to classify galaxy morphology are promising due to their ability to classify quickly and their model independence (for example Dieleman et al 2015;Ackermann et al 2018;Pearson et al 2019;Ćiprijanović et al 2020). In particular, a variety of deep learning merger morphology studies train their algorithms on data-sets that have been visually classified by humans or test the accuracy of their schema compared to visually classified "truth" data-sets.…”

Section: Introductionmentioning

confidence: 99%

Merger or Not: Accounting for Human Biases in Identifying Galactic Merger Signatures

Lambrides,

Watts,

Chiaberge

et al. 2021

Preprint

View full text Add to dashboard Cite

Significant galaxy mergers throughout cosmic time play a fundamental role in theories of galaxy evolution. The widespread usage of human classifiers to visually assess whether galaxies are in merging systems remains a fundamental component of many morphology studies. Studies that employ human classifiers usually construct a control sample, and rely on the assumption that the bias introduced by using humans will be evenly applied to all samples. In this work, we test this assumption and develop methods to correct for it. Using the standard binomial statistical methods employed in many morphology studies, we find that the merger fraction, error, and the significance of the difference between two samples are dependent on the intrinsic merger fraction of any given sample. We propose a method of quantifying merger biases of individual human classifiers and incorporate these biases into a full probabilistic model to determine the merger fraction and the probability of an individual galaxy being in a merger. Using 14 simulated human responses and accuracies, we are able to correctly label a galaxy as "merger" or "isolated" to within 1% of the truth. Using 14 real human responses on a set of realistic mock galaxy simulation snapshots our model is able to recover the pre-coalesced merger fraction to within 10%. Our method can not only increase the accuracy of studies probing the merger state of galaxies at cosmic noon, but also can be used to construct more accurate training sets in machine learning studies that use human classified data-sets.

show abstract

“…Tiling requires many inputs and intermediate values to be stored rather than streamed, which increases data movement. Thus, tiling restricts the use of DNNs in high-throughput applications such as the observation of new phenomena in fundamental physics [10][11][12][13][14], and reduces the throughput of large DNN models such as recommender systems [15], vision [8] and natural language processing [16]. Though the current trend is to scale up conventional electronic hardware, these efforts are impeded by communication [17], clocking [18], thermal management [19] and power delivery [20].…”

Section: Introductionmentioning

confidence: 99%

Freely scalable and reconfigurable optical hardware for deep learning

Bernstein¹,

Sludds²,

Hamerly³

et al. 2020

Preprint

View full text Add to dashboard Cite

As deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic processors are impeded by the costs of communication, thermal management, power delivery and clocking. To improve scalability, we propose a digital optical neural network (DONN) with intralayer optical interconnects and reconfigurable input values. The near path-length-independence of optical energy consumption enables information locality between a transmitter and arbitrarily arranged receivers, which allows greater flexibility in architecture design to circumvent scaling limitations. In a proof-of-concept experiment, we demonstrate optical multicast in the classification of 500 MNIST images with a 3-layer, fully-connected network. We also analyze the energy consumption of the DONN and find that optical data transfer is beneficial over electronics when the spacing of computational units is on the order of >10 µm.

show abstract

DeepMerge: Classifying high-redshift merging galaxies with deep neural networks

Cited by 47 publications

References 48 publications

{\sc mirkwood:} Fast and Accurate SED Modeling Using Machine Learning

{\sc mirkwood:} Fast and Accurate SED Modeling Using Machine Learning

Merger or Not: Accounting for Human Biases in Identifying Galactic Merger Signatures

Freely scalable and reconfigurable optical hardware for deep learning

Contact Info

Product

Resources

About