Related papers: Inverting cosmic ray propagation by Convolutional …

We develop a deep learning technique to infer the non-linear velocity field from the dark matter density field. The deep learning architecture we use is an "U-net" style convolutional neural network, which consists of 15 convolution layers…

Interactions between cosmic ray protons and the photons of the cosmic microwave background radiation, as well as the expansion of the universe, cause cosmic rays to lose energy in a way that depends on the distance from the cosmic nray…

The determination of the physical parameters of gravitational wave events is a fundamental pillar in the analysis of the signals observed by the current ground-based interferometers. Typically, this is done using Bayesian inference…

Transformer networks excel in scientific applications. We explore two scenarios in ultra-high-energy cosmic ray simulations to examine what these network architectures learn. First, we investigate the trained positional encodings in air…

The abundance of Li, Be, and B isotopes in galactic cosmic rays (GCR) between E=50-200 MeV/nucleon has been observed by the Cosmic Ray Isotope Spectrometer (CRIS) on NASA's ACE mission since 1997 with high statistical accuracy. Precise…

In the near-future, dedicated telescopes observe Earth-like exoplanets in reflected light, allowing their characterization. Because of the huge distances, every exoplanet will be a single pixel, but temporal variations in its spectral flux…

In this paper we introduce a reliable, fully automated and fast algorithm to detect extended extragalactic radio sources (cluster of galaxies, filaments) in existing and forthcoming surveys (like LOFAR and SKA). The proposed solution is…

Ray tracing algorithms that compute pulse profiles from rotating neutron stars are essential tools for constraining neutron-star properties with data from missions such as NICER. However, the high computational cost of these simulations…

Upcoming cosmological surveys will provide unprecedented amount of data, which will require innovative statistical methods to maximize the scientific exploitation. Standard cosmological analyses based on abundances, two-point and…

We present a novel method to search for structures of coherently aligned patterns in ultra-high energy cosmic-ray arrival directions simultaneously across the entire sky. This method can be used to obtain information on the Galactic…

We train deep learning models on thousands of galaxy catalogues from the state-of-the-art hydrodynamic simulations of the CAMELS project to perform regression and inference. We employ Graph Neural Networks (GNNs), architectures designed to…

The precise spectra of Cosmic Ray (CR) electrons and positrons have been published by the measurement of AMS-02. It is reasonable to regard the difference between the electrons and positrons spectra ( $\triangle \Phi= \Phi_{e^-}-\Phi_{e^+}$…

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…

Dark matter cannot be observed directly, but its weak gravitational lensing slightly distorts the apparent shapes of background galaxies, making weak lensing one of the most promising probes of cosmology. Several observational studies have…

Until fairly recently, it was widely accepted that local cosmic ray spectra were largely featureless power laws, containing limited information on their acceleration and transport. This viewpoint is currently being revised in the light of…

Simulating the irradiation of planetary atmospheres by cosmic ray particles requires, among others, the ability to understand and to quantify the interactions of charged particles with planetary magnetic fields. Here we present a process…

The galactic propagation of cosmic ray strangelets is described and the resulting flux is calculated for a wide range of parameters as a prerequisite for strangelet searches in lunar soil and with an Earth orbiting magnetic spectrometer,…

The flux of ultrahigh energy cosmic rays reaching the Earth is affected by the interactions with the cosmic radiation backgrounds as well as with the magnetic fields that are present along their trajectories. We combine the SimProp cosmic…

Context. Supernova remnants (SNRs) are thought to be the primary candidates for the sources of Galactic cosmic rays. According to the diffusive shock acceleration theory, SNR shocks produce a power-law spectrum with an index of s = 2,…

Despite their successes in the field of self-learning AI, Convolutional Neural Networks (CNNs) suffer from having too many trainable parameters, impacting computational performance. Several approaches have been proposed to reduce the number…