Gabon Offshore - New Technology Enhancing Imaging of Complex Subsurface in Gabon

Gabrielli, Paolo; Drummie, S.; Kaszycka, E.; Thompson, Samuel C.; Zhan, Yuting; Hover, R.; Mannem, S.; Ubik, M.; Morandini, N.; Upadhyay, Priyanka; Bosbach, B.; Sulaiman, M. Shah; Slind, C.L.

doi:10.3997/2214-4609.202011633

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To mitigate the cycle-skipping, it is common to perform the inversion using a multi-scale strategy, where the low frequencies are used first in the inversion, and the higher ones are included progressively (Bunks et al, 1995). FWI shows high potential in reconstructing salt bodies in various fields such as in the Gulf of Mexico (GOM) (Shen et al, 2017;Wang et al, 2019), in Brazil (Gans et al, 2021), and in West of Africa (Gabrielli et al, 2021). The success of FWI in salt regions relies on two main procedures.…”

Section: Introductionmentioning

confidence: 99%

Integrating U-net with full-waveform inversion for an efficient salt body construction

Alaliand

Alkhalifah

2022

Second International Meeting for Applied Geoscience &Amp; Energy

View full text Add to dashboard Cite

Full waveform inversion (FWI) often faces a lot of difficulty inverting for the subsurface when starting with a poor initial model, especially in complex subsurface regions, such as those containing salt bodies. Thus, human intervention is often needed to pick the salt boundary and improve the starting model for the inversion, which can be erroneous and time consuming. Recently, machine learning has greatly assisted us in interpreting the salt body from seismic images, which helps automate the salt building process. However, such ML algorithms require seismic images, which in turn requires a reasonable good velocity model. Here, we build the salt body using low frequency FWI with the aid of neural networks, specifically U-net. The inversion is implemented in a multi-scale fashion and the networks for flooding and unflooding the salt are applied after each scale. We start the inversion from a constant velocity model using low frequencies of 3-7 Hz. Then, we apply a U-net to improve the inversion and flood the salt. We repeat this process of FWI and flooding in the next frequency bandwidth. In the last frequency bandwidth, we use a U-net for unflooding and impliment a final FWI. The networks were trained in a supervised manner using 1D inverted velocity models. We show the potential of the approach on the center part of BP 2004 salt model.

show abstract