Automatic salt geometry update using deep learning in iterative FWI-RTM workflows

Zhao, Tao; Zhao, Chunpeng; Kaul, Anisha; Abubakar, Aria

doi:10.1190/segam2021-3582052.1

Cited by 4 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gramstad and Nickel (2018) proposed to train two CNNs: one to detect the top of the salt for flooding and the other to detect the base for unflooding. Even with these advancements, salt detection during the velocity model building stage is seldom easy due to noise and inaccurate positioning of the reflectors, thus, Zhao et al (2021) used U-net multiple times in an iterative manner between FWI and reverse time migration (RTM) images. However, a drawback of this approach is that it requires advanced high resolution imaging, which is often expensive.…”

Section: Introductionmentioning

confidence: 99%

“…Due to the erroneous velocity at the beginning of the velocity model building, the reflectors are likely to appear in innacurate positions within the image, which leads to inaccurate detection for salt bodies. Thus, Zhao et al (2021) suggested an iterative salt picking from reverse time migrated (RTM) images followed by FWI. Generally, this class of methods requires advanced imaging, which is often applied using high frequencies, fine grids, and higher wavefield solution costs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%