Seismic navigation data quality analysis

Patent metadata

Field	Value
Publication number	US-2023194738-A1
Application number	US-202117553091-A
Country	US
Kind code	A1
Filing date	Dec 16, 2021
Priority date	Dec 16, 2021
Publication date	Jun 22, 2023
Grant date	—

Abstract

The disclosure presents processes to select cartographic reference system (CRS) recommendations from a CRS model where the CRS recommendations are matched to received seismic data. A learning mode can be used to build the CRS model where seismic data is matched to CRS. The learning mode can be automated using natural language processing system to parse the meta data for the seismic data, such as the name, area, or code, or label. The CRS model can be updated using an output from a user system, such as when a user manually matches a CRS to seismic data. The matched seismic data to CRS, e.g., seismic data-CRS match, can be used as input to a user system or a computing system, such as a borehole operation system.

First claim

What is claimed is:

1 . A method to train a machine learning system to associate seismic data with cartographic reference systems, comprising:
receiving seismic data 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 one or more cartographic reference systems (CRSs), using the meta data, to generate a seismic data-CRS match; and updating a CRS model of the machine learning system with the seismic data-CRS match, wherein the seismic data-CRS match is utilized to determine a first location of a reservoir field or a second location of a borehole for hydrocarbon production.

2 . The method as recited in claim 1 , wherein the parsing utilizes a natural language processing system.

3 . The method as recited in claim 1 , wherein the associating utilizes a rank or a weight for each CRS in the one or more CRS.

4 . The method as recited in claim 1 , wherein the name, the area, or the code is a file name or a label.

5 . The method as recited in claim 1 , wherein the updating utilizes a user input to update the CRS model.

6 . A method of using a machine learning system for matching seismic data to cartographic reference systems, comprising:
receiving seismic data relating to a location of interest; parsing meta data of the seismic data to determine a name, an area, or a code; and utilizing a cartographic reference system (CRS) model to associate the seismic data with one or more CRS, utilizing the meta data, to generate a seismic data-CRS match, wherein the seismic data-CRS match is utilized to determine a first location of a reservoir field or a second location of a borehole for hydrocarbon production.

7 . The method as recited in claim 6 , further comprising:
communicating the seismic data-CRS match to one or more borehole operation systems.

8 . The method as recited in claim 6 , wherein there is more than one CRS in the one or more CRS, and the seismic data-CRS match includes an indicator for a primary CRS.

9 . The method as recited in claim 6 , wherein there is more than one CRS in the one or more CRS, and the seismic data-CRS match includes a rank or a weight for each CRS in the one or more CRS.

10 . The method as recited in claim 6 , wherein there is more than one CRS, and the seismic data-CRS match is communicated to a user system, where, using the user system, a user selects a primary CRS from the one or more CRS.

11 . The method as recited in claim 10 , wherein an output from the user system is utilized to update the CRS model.

12 . The method as recited in claim 10 , wherein the user system utilizes a statistical infographic to interpret the seismic data-CRS match.

13 . The method as recited in claim 10 , wherein the user system utilizes a geographic information system (GIS) system.

14 . The method as recited in claim 6 , wherein the CRS model utilizes a statistics-based CRS recommendation.

15 . A system, comprising:
a data transceiver, capable of receiving seismic data, wherein the seismic data relates to a location of interest for a reservoir field or a borehole; a machine learning system, capable of parsing meta data of the seismic data to generate a label, associating, using the label, seismic data to a cartographic reference system (CRS) to generate a seismic data-CRS match, and updating a CRS model using the seismic data-CRS match; and a seismic data analyzer, capable of communicating with the data transceiver and the machine learning system, and using the CRS model to select one or more CRS recommendations for the seismic data.

16 . The system as recited in claim 15 , further comprising:
a result transceiver, capable of communicating results, interim outputs, and the seismic data-CRS match to a user system, a data store, or a computing system.

17 . The system as recited in claim 16 , wherein the computing system is a borehole operation system.

18 . The system as recited in claim 16 , wherein an output from the user system is used to update the CRS model.

19 . The system as recited in claim 15 , wherein the label is one or more of a name, an area, or a code.

20 . The system as recited in claim 15 , wherein the seismic data analyzer is further capable of using ranks, weights, or statistical algorithms to select the one or more CRS recommendations.

Assignees

• Landmark Graphics Corp

Inventors

• Roy Samiran
• Srivastav Shreshth
• Mandapaka Bhaskar
• Priyadarshy Satyam

Classifications

• G01V1/30 Primary

  Analysis (G01V1/50 takes precedence) · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• E21B49/00

  Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells · CPC title

• E21B2200/20

  Computer models or simulations, e.g. for reservoirs under production, drill bits · CPC title

• E21B2200/22

  Fuzzy logic, artificial intelligence, neural networks or the like · CPC title