1

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

Inversion workflow for salt bodies from poor inital model, limited offsets and with frequencies starting from 5 Hz. Multistage flooding and unflooding is implimented using U-net networks within the multiscale approach in the FWI.

Abdullah Alali, Tariq Alkhalifah

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

Learning to Unflood the Salt in Full-Waveform Inversion, Application on Vintage GOM Data

Building a velocity model in salt provinces is a challenging task. Traditionally the salt boundaries is manually interpreted by an …

Abdullah Alali, Tariq Alkalifah

Time-lapse seismic cross-equalization using temporal convolutional networks

Monitoring of geological reservoirs using 4D seismic faces many challenges. The repeatability between different surveys needs to be …

Abdullah Alali, Robert Smith, Philippe Nivelet, Andrey Bakulin, Tariq Alkalifah

Time-lapse Cross-equalization by deep learning

Ideally, time-lapse seismic data from different vintages should be identical except at the target area (i.e., the reservoir). However, …

Abdullah Alali, Vladimir Kazei, Bingbing Sun, Basmah Altaf, Xiangliang Zhang, Tariq Alkalifah

Cross-equalization of time-lapse seismic data using recurrent neural networks

Time-lapse seismic uses repetitive seismic surveys to monitor the fluid in the subsurface. Ideally, the time-lapse data should be …

Abdullah Alali, Vladimir Kazei, Bingbing Sun, Robert Smith, Phlippe Nivlet, Andrey Bakulin, Tariq Alkalifah