Neural neZtworks in astronomy

Tagliaferri, Roberto; Longo, Giuseppe; Milano, L.; Acernese, F.; Barone, F.; Ciaramella, Angelo; Rosa, R. De; Donalek, C.; Eleuteri, A.; Raiconi, Giancarlo; Sessa, Salvatore; Staiano, Antonino; Volpicelli, A.

doi:10.1016/s0893-6080(03)00028-5

Cited by 46 publications

(34 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This quality allows the use of NNs for forecasting and inference. While arXiv:1802.01212v3 [astro-ph.CO] 1 May 2018 we do not have a full understanding on what drives NNs predictive power [32], they have been successfully used in Astronomy, from source detection and classification, to light curve analyses and even adaptive optics control (see reviews on NNs in astronomy in [33,34]).…”

Section: Introductionmentioning

confidence: 99%

Non-Gaussian information from weak lensing data via deep learning

et al. 2018

View full text Add to dashboard Cite

Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and apply a 2D convolutional neural network to simulated noiseless lensing maps covering 96 different cosmological models over a range of {Ωm, σ8}. Using the area of the confidence contour in the {Ωm, σ8} plane as a figure-of-merit, derived from simulated convergence maps smoothed on a scale of 1.0 arcmin, we show that the neural network yields ≈ 5× tighter constraints than the power spectrum, and ≈ 4× tighter than the lensing peaks. Such gains illustrate the extent to which weak lensing data encode cosmological information not accessible to the power spectrum or even other, non-Gaussian statistics such as lensing peaks.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-Gaussian information from weak lensing data via deep learning

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Similar approaches have been successfully used for a number of scientific applications333435363738 including stabilizing feedback loops at particle accelerator facilities39. Using data from LCLS, we found that much of the information usually extracted from slow, complex diagnostics such as the pump-probe delay in the twin bunch mode, the photon energy or even the spectral shape of the X-ray pulses, is strongly correlated to electron bunch and X-ray properties measured by fast diagnostics.…”

mentioning

confidence: 82%

Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning

et al. 2017

View full text Add to dashboard Cite

Free-electron lasers providing ultra-short high-brightness pulses of X-ray radiation have great potential for a wide impact on science, and are a critical element for unravelling the structural dynamics of matter. To fully harness this potential, we must accurately know the X-ray properties: intensity, spectrum and temporal profile. Owing to the inherent fluctuations in free-electron lasers, this mandates a full characterization of the properties for each and every pulse. While diagnostics of these properties exist, they are often invasive and many cannot operate at a high-repetition rate. Here, we present a technique for circumventing this limitation. Employing a machine learning strategy, we can accurately predict X-ray properties for every shot using only parameters that are easily recorded at high-repetition rate, by training a model on a small set of fully diagnosed pulses. This opens the door to fully realizing the promise of next-generation high-repetition rate X-ray lasers.

show abstract

“…There have been many reviews of the use of data mining in astronomy (Zhang, Zhao, & Cui, 2002;Zhang, Zheng, & Zhao, 2008;Borne, 2009;Ball, & Brunner, 2010;Zhang & Zhao, 2011). Other reviews include the application of neural networks in astronomy (Tagliaferri, Longo Milano, et al, 2003;Li, Zhang, Zhao, Yang, 2006) and outlier detection in astronomical data (Zhang, Luo, & Zhao, 2004). In summary, Table 2 shows the approaches and applications most often used in astronomy to do major data mining tasks.…”

Section: Data Miningmentioning

confidence: 99%

Astronomy in the Big Data Era

Zhang

Zhao

2015

CODATA

View full text Add to dashboard Cite

The fields of Astrostatistics and Astroinformatics are vital for dealing with the big data issues now faced by astronomy. Like other disciplines in the big data era, astronomy has many V characteristics. In this paper, we list the different data mining algorithms used in astronomy, along with data mining software and tools related to astronomical applications. We present SDSS, a project often referred to by other astronomical projects, as the most successful sky survey in the history of astronomy and describe the factors influencing its success. We also discuss the success of Astrostatistics and Astroinformatics organizations and the conferences and summer schools on these issues that are held annually. All the above indicates that astronomers and scientists from other areas are ready to face the challenges and opportunities provided by massive data volume.

show abstract

Neural neZtworks in astronomy

Cited by 46 publications

References 61 publications

Non-Gaussian information from weak lensing data via deep learning

Non-Gaussian information from weak lensing data via deep learning

Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning

Astronomy in the Big Data Era

Contact Info

Product

Resources

About