US 11,874,419 B2
System and method for automated domain conversion for seismic well ties
Philippe Georges Christophe Nivlet, Alkhobar (SA); Robert James Smith, Dhahran (SA); and Nasher Muqbel AlBinHassan, Dhahran (SA)
Assigned to SAUDI ARABIAN OIL COMPANY, Dhahran (SA)
Filed by SAUDI ARABIAN OIL COMPANY, Dhahran (SA)
Filed on Jun. 30, 2021, as Appl. No. 17/363,660.
Prior Publication US 2023/0003912 A1, Jan. 5, 2023
Int. Cl. G01V 1/32 (2006.01); G01V 1/40 (2006.01); G01V 1/28 (2006.01)
CPC G01V 1/32 (2013.01) [G01V 1/282 (2013.01); G01V 1/40 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for automatically transforming sonic well logs from a depth domain to a seismic two-way travel-time domain, comprising:
obtaining a training well, the training well having a measured sonic well log in the depth domain and a borehole seismic dataset in the depth domain;
obtaining an application well, the application well having a measured sonic well log in the depth domain;
training, using a computer processor, a network to predict a transformed sonic well log for the training well based, at least in part, on the measured sonic well log in the training well and the borehole seismic dataset in the training well,
wherein training the network to predict the transformed sonic well log for the training well, comprises:
dividing the measured sonic well log into a plurality of overlapping segments of measured sonic well log in the depth domain,
transforming the plurality of overlapping segments into a plurality of transformed segments in a time domain based, at least in part on the borehole seismic dataset,
training an artificial network to predict the plurality of transformed segments in the time domain based, at least in part, on the plurality of overlapping segments of the measured sonic well log in the depth domain, and
combining the plurality of transformed segments to form the transformed sonic well log; and
predicting, using a computer processor and with the network, the transformed sonic well log for the application well.