Conveners
Machine Learning in Astronomy: AGN, Transient Events, Cosmology and Others: Block 1
- Yu Wang ()
- Rahim Moradi (ICRANet and ICRA-Sapienza)
Description
In recent years, machine learning (ML) and deep learning (DL) have become increasingly popular in astronomy and astrophysics. The advancements of observational detectors have led to the immense growth of astronomical data. The richness of the data has brought new opportunities for scientific discoveries, where astronomers develop intelligent tools and interfaces to deal with data sets and extract novel information. DL/ML aims to seek and recognize, by the optimization procedure, all available common characteristics and patterns in data, which helps in turn to accelerate the simulation, to promote the observation and to infer the physics. The ML/DL have been widely used for a variety of tasks, including classification of galaxies, evaluation of redshift, stellar atmospheric parameters estimation, large-scale structure and dark matter simulation, reionization sources identification, transient sources detection, gravitational lensing discrimination and cosmic microwave background inpainting.
Study the cosmological sources at their cosmological rest-frames are crucial in order to track the cosmic history and properties of the compact objects. In view of increasing data volume of existing and upcoming telescopes/detectors we here apply the 1--dimensional convolutional neural network (CNN) to estimate the redshift of quasars in Sloan Digital Sky Survey IV (SDSS-IV) catalog from DR16...
After recent technological advancements in astronomical surveys, modern astrophysics is concerned with the study and characterization of distant objects such as galaxies, stars and quasars. Obtaining the optical spectrum and consequently deriving the redshift could instantly classify these astronomical sources but as long as spectroscopic observations are not available for many galaxies and...
Searching continuous gravitational waves from unseen objects is computationally expensive and relies on hierarchies of follow-up stages for candidates above a given significance threshold. Clustering is a powerful technique that bunds together nearby candidates in a single follow-up to simplify the follow-ups and reduce the computational cost. We used deep learning methods to automate the...
Abstract.
We discuss the possibility that the topological structure of the Universe may possess fractal properties.
Relic wormholes and their fractal distribution are predicted in a natural way by lattice quantum gravity models.
This gives a new approach to some long-standing problems. Those are the nature of dark matter phenomena, the origin of Faber-Jackson and Tully-Fisher...
Recent progresses in Machine Learning have unlocked new possibilities to tackle scientific problems by means of neural networks, and already many applications have been developed both in astrophysics and cosmology. In this presentation, using a Generative Adversarial Network (GAN), an unsupervised learning model, we demonstrate the possibility to learn the distribution of dark matter of the...
Two major challenges in modern cosmology are the understanding of the origin and growth of cosmic structure and the progenitors of Gravitational Waves. Both scenarios require heavy computational resources to perform simulations and inference. In this work, we propose to adopt Machine Learning to alleviate these requirements, to enable significantly faster sampling and inference. We show that...
Galaxy Clusters are essential to study galaxy evolution and sensitive probes of cosmology and the dynamics of the Universe Dark sector. Large galaxy surveys, such as Euclid, DES, LSST/Rubin will provide a wealth of information that can be used to detect many new clusters. For example, the Euclid mission survey may reveal more than 60000 clusters with S/N>3 up to redshift 2, representing a...
The fourth Fermi Large Area Telescope source catalog contains 5065 gamma-ray sources. Among these sources, 694 are flat-spectrum radio quasars (FSRQs), 1131 are BL Lac-type objects (BL Lacs), and 1312 are blazar candidates of an unknown type (BCUs). Using as a training sample the spectral energy distributions and the light curves of classified blazars, a supervised machine learning method...
