In this work we present an hybrid algorithm that includes a neural network in a global elastic FWI for misfit prediction purposes. In order to asses the algorithm performances, we have compared it against a standard global FWI over three synthetic models with increasingly challenging features. Results are consistently similar, and show that the proposed algorithm is more time-efficient than the standard one.
Neural network for misfit prediction in 2D elastic global FWI
Pierini, S.
;Balestri, M.;Stucchi, E.
2021-01-01
Abstract
In this work we present an hybrid algorithm that includes a neural network in a global elastic FWI for misfit prediction purposes. In order to asses the algorithm performances, we have compared it against a standard global FWI over three synthetic models with increasingly challenging features. Results are consistently similar, and show that the proposed algorithm is more time-efficient than the standard one.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
