English
Related papers

Related papers: Application of Neural Ordinary Differential Equati…

200 papers

Nuclear fusion is a promising clean energy source in which deuterium and tritium fuse inside a magnetically confined plasma in a tokamak, releasing energy. A key challenge on the route to practical nuclear fusion is the control of the…

Systems and Control · Electrical Eng. & Systems 2026-04-30 L. L. T. C. Jansen , E. Petri , M. van Berkel , W. P. M. H. Heemels

Accurate aircraft trajectory prediction is critical for air traffic management, airline operations, and environmental assessment. This paper introduces NODE-FDM, a Neural Ordinary Differential Equations-based Flight Dynamics Model trained…

Machine Learning · Computer Science 2025-09-30 Gabriel Jarry , Ramon Dalmau , Xavier Olive , Philippe Very

We present a method that employs physics-informed deep learning techniques for parametrically solving partial differential equations. The focus is on the steady-state heat equations within heterogeneous solids exhibiting significant phase…

Machine Learning · Computer Science 2024-01-05 Shahed Rezaei , Ahmad Moeineddin , Michael Kaliske , Markus Apel

In this study, we propose parameter-varying neural ordinary differential equations (NODEs) where the evolution of model parameters is represented by partition-of-unity networks (POUNets), a mixture of experts architecture. The proposed…

Machine Learning · Computer Science 2022-10-04 Kookjin Lee , Nathaniel Trask

An experimental program is currently underway at the National Ignition Facility (NIF) to compress deuterium and tritium (DT) fuel to densities and temperatures sufficient to achieve fusion and energy gain. The primary approach being…

Plasma Physics · Physics 2021-11-09 J. S. Ross , J. E. Ralph , A. B. Zylstra , A. L. Kritcher , H. F. Robey , C. V. Young , O. A. Hurricane , D. A. Callahan , K. L. Baker , D. T. Casey , T. Doeppner , L. Divol , M. Hohenberger , S. Le Pape , A. Pak , P. K. Patel , R. Tommasini , S. J. Ali , P. A. Amendt , L. J. Atherton , B. Bachmann , D. Bailey , L. R. Benedetti , L. Berzak Hopkins , R. Betti , S. D. Bhandarkar , R. M. Bionta , N. W. Birge , E. J. Bond , D. K. Bradley , T. Braun , T. M. Briggs , M. W. Bruhn , P. M. Celliers , B. Chang , T. Chapman , H. Chen , C. Choate , A. R. Christopherson , D. S. Clark , J. W. Crippen , E. L. Dewald , T. R. Dittrich , M. J. Edwards , W. A. Farmer , J. E. Field , D. Fittinghoff , J. Frenje , J. Gaffney , M. Gatu Johnson , S. H. Glenzer , G. P. Grim , S. Haan , K. D. Hahn , G. N. Hall , B. A. Hammel , J. Harte , E. Hartouni , J. E. Heebner , V. J. Hernandez , H. Herrmann , M. C. Herrmann , D. E. Hinkel , D. D. Ho , J. P. Holder , W. W. Hsing , H. Huang , K. D. Humbird , N. Izumi , L. C. Jarrott , J. Jeet , O. Jones , G. D. Kerbel , S. M. Kerr , S. F. Khan , J. Kilkenny , Y. Kim , H. Geppert Kleinrath , V. Geppert Kleinrath , C. Kong , J. M. Koning , J. J. Kroll , O. L. Landen , S. Langer , D. Larson , N. C. Lemos , J. D. Lindl , T. Ma , M. J. MacDonald , B. J. MacGowan , A. J. Mackinnon , S. A. MacLaren , A. G. MacPhee , M. M. Marinak , D. A. Mariscal , E. V. Marley , L. Masse , K. Meaney , N. B. Meezan , P. A. Michel , M. Millot , J. L. Milovich , J. D. Moody , A. S. Moore , J. W. Morton , T. Murphy , K. Newman , J. -M. G. Di Nicola , A. Nikroo , R. Nora , M. V. Patel , L. J. Pelz , J. L. Peterson , Y. Ping , B. B. Pollock , M. Ratledge , N. G. Rice , H. Rinderknecht , M. Rosen , M. S. Rubery , J. D. Salmonson , J. Sater , S. Schiaffino , D. J. Schlossberg , M. B. Schneider , C. R. Schroeder , H. A. Scott , S. M. Sepke , K. Sequoia , M. W. Sherlock , S. Shin , V. A. Smalyuk , B. K. Spears , P. T. Springer , M. Stadermann , S. Stoupin , D. J. Strozzi , L. J. Suter , C. A. Thomas , R. P. J. Town , E. R. Tubman , P. L. Volegov , C. R. Weber , K. Widmann , C. Wild , C. H. Wilde , B. M. Van Wonterghem , D. T. Woods , B. N. Woodworth , M. Yamaguchi , S. T. Yang , G. B. Zimmerman

A surrogate model for particle-in-cell plasma simulations based on a graph neural network is presented. The graph is constructed in such a way as to enable the representation of electromagnetic fields on a fixed spatial grid. The model is…

Plasma Physics · Physics 2025-03-04 Marin Mlinarević , George K. Holt , Adriano Agnello

Deep learning has an increasing impact to assist research, allowing, for example, the discovery of novel materials. Until now, however, these artificial intelligence techniques have fallen short of discovering the full differential equation…

Efficient removal of helium ash is a critical requirement for the operation of fusion power plants, as its accumulation can dilute the core fuel and degrade plasma performance. While past studies suggested that helium exhaust in burning…

Plasma Physics · Physics 2025-07-25 Rebecca Masline , Michael Wigram , Dennis Whyte

The ultrashort time-integrated diagnosis of ions plays a vital role in high energy density physics research. However, it is extremely challenging to measure in experiment. Here, we demonstrate a reliable approach for investigating the…

Tokamak start-up is characterized by low electron densities and strong electric fields, in order to quickly raise the plasma current and temperature, allowing the plasma to fully ionize and magnetic flux surfaces to form. Such conditions…

Plasma Physics · Physics 2022-06-30 M. Hoppe , I. Ekmark , E. Berger , T. Fülöp

The confinement of Neutral Beam Injection (NBI) particles in the presence of n=3 Resonant Magnetic Perturbations (RMPs) in 15 MA ITER DT plasmas has been studied using full orbit ASCOT simulations. Realistic NBI distribution functions, and…

A local turbulence model is developed to study energy cascades in the heliosheath and outer heliosphere (OH) based on self-consistent two-dimensional fluid simulations. The model describes a partially ionized magnetofluid OH that couples a…

Space Physics · Physics 2015-05-14 Dastgeer Shaikh , G. P. Zank

In this study, we consider a numerical implementation of the nonlinear Rosenbluth-Trubnikov collision operator for particle simulations in plasma physics in the framework of the finite element method (FEM). The relevant particle evolution…

Plasma Physics · Physics 2024-02-07 Zhixin Lu , Guo Meng , Tomasz Tyranowski , Alex Chankin

Neural Ordinary Differential Equations (NODEs) have proven to be a powerful modeling tool for approximating (interpolation) and forecasting (extrapolation) irregularly sampled time series data. However, their performance degrades…

Machine Learning · Computer Science 2020-04-29 Hammad A. Ayyubi , Yi Yao , Ajay Divakaran

Accurate modeling of runaway electron generation and losses during tokamak disruptions is crucial for the development of reactor-scale tokamak devices. In this paper we present a reduced model for runaway electron losses due to flux surface…

Plasma Physics · Physics 2024-10-07 Oskar Vallhagen , Lise Hanebring , Tünde Fülöp , Mathias Hoppe , Istvan Pusztai

A tutorial introduction to the technique of Molecular Dynamics (MD) is given, and some characteristic examples of applications are described. The purpose and scope of these simulations and the relation to other simulation methods is…

Disordered Systems and Neural Networks · Physics 2009-11-10 Kurt Binder , Jurgen Horbach , Walter Kob , Wolfgang Paul , Fathollah Varnik

Accurate forecasting of energy demand and supply is critical for optimizing sustainable energy systems, yet it is challenged by the variability of renewable sources and dynamic consumption patterns. This paper introduces a neural framework…

Machine Learning · Computer Science 2025-07-15 Usman Gani Joy

The Multi-Mode Model (MMM) for turbulent transport was applied to a large set of well-analyzed discharges from the National Spherical Torus Experiment (NSTX) in order to evaluate its sensitivities to a wide range of plasma conditions. MMM…

Microturbulence in magnetic confined plasmas contributes to energy exchange between particles of different species as well as the particle and heat fluxes. Although the effect of turbulent energy exchange has not been considered significant…

Plasma Physics · Physics 2024-06-18 T. Kato , H. Sugama , T. -H. Watanabe , M. Nunami

End-to-end learning of dynamical systems with black-box models, such as neural ordinary differential equations (ODEs), provides a flexible framework for learning dynamics from data without prescribing a mathematical model for the dynamics.…

Machine Learning · Statistics 2022-06-20 Paidamoyo Chapfuwa , Sherri Rose , Lawrence Carin , Edward Meeds , Ricardo Henao