activity
20222025
most citedPhysical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)

42 citations · 52 across the 5 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

physics.flu-dyn2022

Early- and late-time prediction of counter-current spontaneous imbibition, scaling analysis and estimation of the capillary diffusion coefficient

Pål Østebø Andersen

Solutions are investigated for 1D linear counter-current spontaneous imbibition (COUSI). The diffusion problem is scaled to depend only on a normalized coefficient Λ_n (S_n ) with…

cs.LG2022★ 42 cited

Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)

Jassem Abbasi, Pål Østebø Andersen

In recent years, the gap between Deep Learning (DL) methods and analytical or numerical approaches in scientific computing is tried to be filled by the evolution of Physics-Informe…