English
Related papers

Related papers: Solving Einstein equations using deep learning

200 papers

A reformulation of the Schwarzschild solution of the linearised Einstein field equations in post-Riemannian Finsler spacetime is derived. The solution is constructed in three stages: the exterior solution, the event-horizon solution and the…

General Relativity and Quantum Cosmology · Physics 2017-03-20 Carringtone Kinyanjui , Dismas S. Wamalwa

The evolution of black-hole binaries in vacuum spacetimes constitutes the two-body problem in general relativity. The solution of this problem in the framework of the Einstein field equations is a substantially more complex exercise than…

General Relativity and Quantum Cosmology · Physics 2015-06-17 Ulrich Sperhake

We propose energy natural gradient descent, a natural gradient method with respect to a Hessian-induced Riemannian metric as an optimization algorithm for physics-informed neural networks (PINNs) and the deep Ritz method. As a main…

Machine Learning · Computer Science 2023-08-16 Johannes Müller , Marius Zeinhofer

There has been rapid progress recently on the application of deep networks to the solution of partial differential equations, collectively labelled as Physics Informed Neural Networks (PINNs). In this paper, we develop Physics Informed…

Machine Learning · Computer Science 2019-07-09 Vikas Dwivedi , Balaji Srinivasan

First formulated by Sir Isaac Newton in his work "Philosophiae Naturalis Principia Mathematica", the concept of the Three-Body Problem was put forth as a study of the motion of the three celestial bodies within the Earth-Sun-Moon system. In…

Machine Learning · Computer Science 2025-03-07 Manuel Santos Pereira , Luís Tripa , Nélson Lima , Francisco Caldas , Cláudia Soares

We linearize the Einstein equations when the metric is Bondi-Sachs, when the background is Schwarzschild or Minkowski, and when there is a matter source in the form of a thin shell whose density varies with time and angular position. By…

General Relativity and Quantum Cosmology · Physics 2009-11-10 Nigel T. Bishop

This paper explores the difficulties in solving partial differential equations (PDEs) using physics-informed neural networks (PINNs). PINNs use physics as a regularization term in the objective function. However, a drawback of this approach…

Machine Learning · Computer Science 2023-06-21 Shamsulhaq Basir

Einstein originally proposed a nonsymmetric tensor field, with its symmetric part associated with the spacetime metric and its antisymmetric part associated with the electromagnetic field, as an approach to a unified field theory. Here we…

General Relativity and Quantum Cosmology · Physics 2018-03-14 J. R. van Meter

How to solve inverse problems is the challenge of many engineering and industrial applications. Recently, physics-informed neural networks (PINNs) have emerged as a powerful approach to solve inverse problems efficiently. However, it is…

Numerical Analysis · Mathematics 2022-09-22 Xinchao Jiang , Xin Wanga , Ziming Wena , Enying Li , Hu Wang

Deep learning has been shown to be an effective tool in solving partial differential equations (PDEs) through physics-informed neural networks (PINNs). PINNs embed the PDE residual into the loss function of the neural network, and have been…

Machine Learning · Computer Science 2022-04-06 Jeremy Yu , Lu Lu , Xuhui Meng , George Em Karniadakis

In this letter we present the first multiparticle solutions to Einstein's field equations in the presence of matter. These solutions are iteratively obtained via the perturbiner method, which can circumvent gravity's infinite number of…

High Energy Physics - Theory · Physics 2021-11-01 Humberto Gomez , Renann Lipinski Jusinskas

Numerical modeling errors are unavoidable in finite element analysis. The presence of model errors inherently reflects both model accuracy and uncertainty. To date there have been few methods for explicitly quantifying errors at points of…

Machine Learning · Computer Science 2024-11-19 Bozhou Zhuang , Sashank Rana , Brandon Jones , Danny Smyl

Novel applications of Numerical Relativity demand for more flexible algorithms and tools. In this paper, I develop and test a multigrid solver, based on the infrastructure provided by the Einstein Toolkit, for elliptic partial differential…

General Relativity and Quantum Cosmology · Physics 2015-06-16 Eloisa Bentivegna

We present the application of a class of deep learning, known as Physics Informed Neural Networks (PINN), to learning and discovery in solid mechanics. We explain how to incorporate the momentum balance and constitutive relations into PINN,…

Machine Learning · Computer Science 2020-05-12 Ehsan Haghighat , Maziar Raissi , Adrian Moure , Hector Gomez , Ruben Juanes

The solution of partial differential equations (PDES) on irregular domains has long been a subject of significant research interest. In this work, we present an approach utilizing physics-informed neural networks (PINNs) to achieve…

Computational Physics · Physics 2025-06-12 Cuizhi Zhou , Kaien Zhu

We propose a method utilizing physics-informed neural networks (PINNs) to solve Poisson equations that serve as control variates in the computation of transport coefficients via fluctuation formulas, such as the Green--Kubo and generalized…

Numerical Analysis · Mathematics 2024-12-20 Grigorios Pavliotis , Renato Spacek , Gabriel Stoltz , Urbain Vaes

We present a novel method to study interacting orbits in a fixed mean gravitational field associated with a solution of the Einstein field equations. The idea is to consider the Newton gravity among the orbiting particles in a geometry…

Astrophysics · Physics 2007-05-23 Eduardo Gueron , Patricio S. Letelier

This is the first of a series of papers describing a numerical implementation of the conformally rescaled Einstein equation, an implementation designed to calculate asymptotically flat spacetimes, especially spacetimes containing black…

General Relativity and Quantum Cosmology · Physics 2009-10-31 Peter Huebner

The Schwarzschild solution was the first exact solution to Einstein's 1915 field equations, found by Karl Schwarzschild as early as 1916. And yet, physicists, mathematicians and philosophers have struggled for decades with the…

History and Philosophy of Physics · Physics 2025-08-04 Dennis Lehmkuhl

Schwarzschild's 'interior solution' is a space-time metric that satisfies Einstein's gravitational field equations with a source term that Einstein created on the basis of an unjustified identification of the conceptually distinct notions…

General Relativity and Quantum Cosmology · Physics 2012-10-18 Homer G. Ellis
‹ Prev 1 4 5 6 7 8 10 Next ›