Atakan Aygün

E-mail

atakana@metu.edu.tr

Department

Department of Mechanical Engineering

GPU-Accelerated ILES of Weakly Compressible Flows Using a Galerkin–Boltzmann Formulation Ata, Onur; Aygün, Atakan; Karakuş, Ali (2026-06-03) We present a high-order implicit large-eddy simulation (ILES) approach for nearly incompressible flows based on a nodal discontinuous Galerkin (DG) discretization of the continuous Boltzmann equations. The compact, low-dis...
GPU Accelerated Discontinuous Galerkin Solutions of Galerkin-Boltzmann Formulations for Nearly Incompressible Flows on Moving Meshes Aygün, Atakan; Ata, Onur; Karakuş, Ali (2026-03-06) In this talk, we introduce an arbitrary Lagrangian-Eulerian (ALE) formulation of the Galerkin-Boltzmann method, which recovers the Navier–Stokes equations in the nearly incompressible regime. A perfectly matched laye...
Physics-Informed Neural Networks for Heat Transfer and Fluid Flow problems Aygün, Atakan; Ata, Onur; Karakuş, Ali (2025-05-21) Physics-informed neural networks (PINN) have emerged as a viable alternative to the classicalnumerical methods while solving partial differential equations. Their ability to obtain the solutionwithout generating any mesh o...
Discontinuous Galerkin Solutions of Moving Boundary Problems Using Arbitrary Lagrangian-Eulerian Method on GPUs Aygün, Atakan; Karakuş, Ali (2025-03-03) Flow problems with moving boundaries and interfaces appear naturally in many applications, such as turbine flow, flapping flight, etc. Numerical modeling of these flows poses additional challenges since the numerical...
Physics-informed neural networks for mesh deformation with exact boundary enforcement Aygün, Atakan; Maulik, Romit; Karakuş, Ali (2023-10-01) In this work, we have applied physics-informed neural networks (PINN) for solving mesh deformation problems. We used the collocation PINN method to capture the new positions of the vertex nodes while preserving the connect...
Physics-Informed Neural Networks for Mesh Deformation with Exact Boundary Enforcement Aygün, Atakan; Karakuş, Ali (2023-03-03) In this work, we have applied physics-informed neural networks (PINN) for solving mesh deformation problems. We used the collocation PINN method to capture the new positions of the vertex nodes while preserving the connect...
PHYSICS INFORMED NEURAL NETWORKS FOR TWO DIMENSIONAL INCOMPRESSIBLE THERMAL CONVECTION PROBLEMS Aygün, Atakan; Karakuş, Ali (Turk Isi Bilimi Ve Teknigi Dernegi, 2022-10-31) Abstract: Physics-informed neural networks (PINNs) have drawn attention in recent years in engineering problems due to their effectiveness and ability to tackle problems without generating complex meshes. PINNs use automat...
PHYSICS INFORMED NEURAL NETWORKS FOR TWO DIMENSIONAL INCOMPRESSIBLE THERMAL CONVECTION PROBLEMS Aygün, Atakan; Karakuş, Ali (2022-10-01) Physics-informed neural networks (PINNs) have drawn attention in recent years in engineering problems due to their effectiveness and ability to tackle problems without generating complex meshes. PINNs use automatic differe...
SIKIŞTIRILABİLİR EULER DENKLEMLERİNİN FİZİKLE ÖĞRENEN YAPAY SİNİR AĞLARI İLE ÇÖZÜMÜ Karakuş, Ali; Aygün, Atakan (2022-09-16)
Sıkıştırılabilir Euler Denklemlerinin Fizikle Öğrenen Yapay Sinir Ağları ile Çözümü Aygün, Atakan (2022-09-14)

Citation Formats