Related papers: PINION: Physics-informed neural network for accele…

The redshifted 21-cm signal is a unique probe of the early universe, particularly the Epoch of Reionization (EoR). While the 21-cm power spectrum has been the primary statistic for parameter inference, it fails to capture the non-Gaussian…

We demonstrate that baryonification algorithms, which displace particles in gravity-only simulations according to physically-motivated prescriptions, can simultaneously capture the impact of baryonic physics on the 2 and 3-point statistics…

The Epoch of Reionization (EoR), when the first luminous sources ionised the intergalactic medium, represents a new frontier in cosmology. The Square Kilometre Array Observatory (SKAO) will offer unprecedented insights into this era through…

We study the topology of reionization using accurate three-dimensional radiative transfer calculations post-processed on outputs from cosmological hydrodynamic simulations. In our simulations, reionization begins in overdense regions and…

We present a new method for modeling inhomogeneous cosmic reionization on large scales. Utilizing high-resolution radiation-hydrodynamic simulations with 2048^3 dark matter particles, 2048^3 gas cells, and 17 billion adaptive rays in a L =…

Modern machine learning will allow for simulation-based inference from reionization-era 21cm observations at the Square Kilometre Array. Our framework combines a convolutional summary network and a conditional invertible network through a…

We propose a self-supervised physics-informed neural network (PINN) framework that adaptively balances physics-based and data-driven supervision for scientific machine learning under data scarcity. Unlike prior PINNs that rely on fixed or…

Upcoming 21cm surveys with the SKA1-LOW telescope will enable imaging of the neutral hydrogen distribution on cosmological scales in the early Universe. These surveys are expected to generate huge imaging datasets that will encode more…

The Epoch of Reionization (EoR) is a unique phase in cosmic history, marked by the ionization of neutral hydrogen by the first luminous sources. The global neutral hydrogen fraction (x_HI) is a key observable for probing this era. This…

Traditional numerical methods often struggle with the complexity and scale of modeling pollutant transport across vast and dynamic oceanic domains. This paper introduces a Physics-Informed Neural Network (PINN) framework to simulate the…

In the next decade, radio telescopes like the Square Kilometer Array (SKA) will explore the Universe at high redshift, and particularly during the Epoch of Reionisation (EoR). The first structures emerged during this epoch, and their…

Real-time, physically-consistent predictions on low-power edge devices is critical for the next generation embodied AI systems, yet it remains a major challenge. Physics-Informed Neural Networks (PINNs) combine data-driven learning with…

Physics-informed neural networks (PINNs) and neural operators (NOs) for solving the problem of diffraction of Extreme Ultraviolet (EUV) electromagnetic waves from a mask are presented. A novel hybrid Waveguide Neural Operator (WGNO) is…

Atomic resolution STEM images often suffer from noise due to low electron doses and instrument imperfections, hence it is challenging to obtain critical structural details required for material analysis. To address the problem, we propose a…

Physics-informed neural networks (PINNs) effectively embed physical principles into machine learning, but often struggle with complex or alternating geometries. We propose a novel method for integrating geometric transformations within…

We present a new hybrid code for large volume, high resolution simulations of cosmic reionization, which utilizes a N-body algorithm for dark matter, physically motivated prescriptions for baryons and star formation, and an adaptive ray…

In this study, we introduce BEoRN (Bubbles during the Epoch of Reionisation Numerical Simulator), a publicly available Python code that generates three-dimensional maps of the 21-cm signal from the cosmic dawn and the epoch of reionisation.…

This paper is a step-by-step, self-contained guide to the complete training cycle of a Physics-Informed Neural Network (PINN) -- a topic that existing tutorials and guides typically delegate to automatic differentiation libraries without…

We present an overview of PION, an open-source software project for solving radiation-magnetohydrodynamics equations on a nested grid, aimed at modelling asymmetric nebulae around massive stars. A new implementation of hybrid OpenMP/MPI…

Rapid reconstruction of 2D plasma profiles from line-integral measurements is important in nuclear fusion. This paper introduces a physics-informed model architecture called Onion, that can enhance the performance of models and be adapted…