Related papers: Deep Learning Classification in Asteroseismology

Red-giant stars are emerging as one of the most interesting areas of space asteroseismology. Even a relatively basic analysis leads to the determination of the global parameters of the stars, such as their mass and radius, and the very…

Of the more than 150000 targets followed by the Kepler Mission, about 10% were selected as red giants. Due to their high scientific value, in particular for Galaxy population studies and stellar structure and evolution, their Kepler light…

Machine learning has been widely applied to clearly defined problems of astronomy and astrophysics. However, deep learning and its conceptual differences to classical machine learning have been largely overlooked in these fields. The broad…

Asteroseismic investigations based on the wealth of data now available,in particular from the CoRoT and Kepler missions, require a good understanding of the relation between the observed quantities and the properties of the underlying…

Thanks to the recent very high-precision photometry of red giants from satellites such as Kepler, precise mass and radius values as well as accurate information of evolutionary stages are already established by asteroseismic approach for a…

Convolutional Neural Networks (CNNs) currently achieve state-of-the-art accuracy in image classification. With a growing number of classes, the accuracy usually drops as the possibilities of confusion increase. Interestingly, the class…

Based on the DUSTGRAIN-pathfinder suite of simulations, we investigate observational degeneracies between nine models of modified gravity and massive neutrinos. Three types of machine learning techniques are tested for their ability to…

The Kepler mission has been a success in both exoplanet search and stellar physics studies. Red giants have actually been quite a highlight in the Kepler scene. The Kepler long and almost continuous four-year observations allowed us to…

There is a great need for accurate and autonomous spectral classification methods in astrophysics. This thesis is about training a convolutional neural network (ConvNet) to recognize an object class (quasar, star or galaxy) from…

A star expands to become a red giant when it has fused all the hydrogen in its core into helium. If the star is in a binary system, its envelope can overflow onto its companion or be ejected into space, leaving a hot core and potentially…

The advent of space-based observatories such as CoRoT and Kepler has enabled the testing of our understanding of stellar evolution on thousands of stars. Evolutionary models typically require five input parameters, the mass, initial Helium…

Due to the ever-expanding volume of observed spectroscopic data from surveys such as SDSS and LAMOST, it has become important to apply artificial intelligence (AI) techniques for analysing stellar spectra to solve spectral classification…

With several new large-scale surveys on the horizon, including LSST, TESS, ZTF, and Evryscope, faster and more accurate analysis methods will be required to adequately process the enormous amount of data produced. Deep learning, used in…

The Kepler mission observed many thousands of red giants. The long time series, some as long as the mission itself, have allowed us to study red giants with unprecedented detail. Given that red giants are intrinsically luminous, and hence…

Forthcoming imaging surveys will potentially increase the number of known galaxy-scale strong lenses by several orders of magnitude. For this to happen, images of tens of millions of galaxies will have to be inspected to identify potential…

Clear power excess in a frequency range typical for solar-type oscillations in red giants has been detected in more than 1000 stars, which have been observed during the first 138 days of the science operation of the NASA Kepler satellite.…

The importance of using fast and automatic methods to classify variable stars for large amounts of data is undeniable. There have been many attempts to classify variable stars by traditional algorithms like Random Forest. In recent years,…

We introduce QuasarNET, a deep convolutional neural network that performs classification and redshift estimation of astrophysical spectra with human-expert accuracy. We pose these two tasks as a \emph{feature detection} problem: presence or…

Oscillating red-giant stars in binary systems are an ideal testbed for investigating the structure and evolution of stars in the advanced phases of evolution. With 83 known red giants in binary systems, of which only ~40 have determined…

The unparalleled photometric data obtained by NASA's Kepler Space Telescope has led to improved understanding of red-giant stars and binary stars. We discuss the characterization of known eccentric system, containing a solar-like…