Physics-constrained 3d convolutional neural networks for electrodynamics

HIGHLIGHTS

• who: Alexander Scheinker and colleagues from the Los Alamos National Laboratory, Los Alamos, New Mexico, USA have published the research work: Physics-constrained 3D convolutional neural networks for electrodynamics, in the Journal: (JOURNAL)
• what: The authors demonstrate the PCNN method with numerical studies of relativistic (5 MeV), short (u03c3 t=800 fs), high charge (2 nC) electron bunches represented by N=50 u00d7 106 macro particles. The authors compare the three neural_network approaches to map J to B, as shown in Fig 1: A standard NN using as the cost function for training, a PINN . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.