A hybrid IGA-ADS-CRVPINN solver for Darcy-based CO2 sequestration simulation runs over three times faster than the IGA-ADS plus MUMPS baseline while using only 100 Adam iterations per pressure update after pretraining.
Kevrekidis, Lu Lu, Paris Perdikaris, Sifan Wang, and Liu Yang
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CO$_2$ sequestration hybrid solver using isogeometric alternating-directions and collocation-based robust variational physics informed neural networks (IGA-ADS-CRVPINN)
A hybrid IGA-ADS-CRVPINN solver for Darcy-based CO2 sequestration simulation runs over three times faster than the IGA-ADS plus MUMPS baseline while using only 100 Adam iterations per pressure update after pretraining.