US 12,442,946 B2
Seismic navigation data quality analysis
Samiran Roy, Bangalore (IN); Shreshth Srivastav, Bangalore (IN); Bhaskar Mandapaka, Bangalore (IN); and Satyam Priyadarshy, Houston, TX (US)
Assigned to Landmark Graphics Corporation, Inc., Houston, TX (US)
Filed by Landmark Graphics Corporation, Houston, TX (US)
Filed on Dec. 16, 2021, as Appl. No. 17/553,091.
Prior Publication US 2023/0194738 A1, Jun. 22, 2023
Int. Cl. G01V 1/30 (2006.01); E21B 49/00 (2006.01); G06N 20/00 (2019.01)
CPC G01V 1/30 (2013.01) [E21B 49/00 (2013.01); G06N 20/00 (2019.01); E21B 2200/20 (2020.05); E21B 2200/22 (2020.05); G01V 2210/61 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method to train a machine learning system to associate seismic data with cartographic reference systems, comprising:
receiving seismic data from a national data repository or a data storage, relating to a location of interest;
parsing meta data of the seismic data to determine a name, an area, or a code;
associating the seismic data with two or more cartographic reference systems (CRSs), using the meta data, to generate a seismic data-CRS match, wherein the seismic data-CRS match is communicated to a user system and a user selects a primary CRS from the two or more CRSs; and
training the machine learning system by updating a CRS model with the seismic data-CRS match, wherein the seismic data-CRS match is utilized to determine a first location of a reservoir field and a second location of a borehole for hydrocarbon production, and the seismic data-CRS match includes an indicator for a selected CRS from the two or more CRSs, where the borehole is placed at the second location in the reservoir field using the seismic data-CRS match.