# US 12,007,516 B2 · Geological feature search engine > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,007,516 B2 - Document ID: US12007516B2 - Status: Granted - Kind: B2 - Application number: 15/734,081 - Filed: 2019-05-29 - Published: 2021-07-22 - Granted: 2024-06-11 - Earliest claimed: 2018-06-06 - Assignees: Schlumberger Technology Corporation - Applicants: Schlumberger Technology Corporation - Inventors: Tracy Dorrington; Chiao-Fang Hsu - Web page: https://patentgrep.com/patent/US12007516B2 ## CPC - G01V 1/345: {Visualisation of seismic data or attributes, e.g. in 3D cubes} - G01V 1/30: Analysis (G01V1/50 takes precedence) - G01V 1/306: {for determining physical properties of the subsurface, e.g. impedance, porosity or attenuation profiles} - G06F 16/535: Filtering based on additional data, e.g. user or group profiles - G06F 16/5854: {using shape and object relationship} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G01V 2210/64: Geostructures, e.g. in 3D data cubes - G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A computer-implemented method includes receiving a geological feature search query identifying one or more geological features, executing, based on receiving the geological feature search query, a search of database storing a plurality of seismic data images. The seismic data images are labeled with geological features present in each of the plurality of seismic data images as part of a machine learning process. The method further includes determining, based on executing the search, search results, wherein the search results identify one more of the plurality of seismic data images having the one or more geological features identified in the geological feature search query, and outputting information regarding the search results. ## Claims ### Claim 1 A computer-implemented method comprising: receiving a geological feature search query identifying one or more geological features and one or more constraints associated with the one or more geological features, wherein the one or more constraints include geological attributes, and wherein the geological attributes comprise a depth below a mudline; executing, based on receiving the geological feature search query, a search of a database storing a plurality of seismic data images, wherein executing the search further comprises searching images from a volume model or a basin model; determining rock types present in the seismic data images, and selecting and implementing at least one of a plurality of noise removal techniques for the seismic data images based upon the determined rock types wherein the seismic data images are labeled with the one or more geological features present in each of the plurality of seismic data images as part of a machine learning process; determining, based on executing the search, search results, wherein the search results identify one more of the plurality of seismic data images having the one or more geological features identified in the geological feature search query; and outputting information regarding the search results to facilitate performing at least one of exploration of at least one geographical area having the features of interest and avoidance of at least one geographical area comprising features representing hazardous areas. ### Claim 2 (depends on 1) The method of claim 1, wherein the machine learning processes comprises using a multi-layer neural network. ### Claim 3 (depends on 1) The method of claim 1, wherein the machine learning process further comprises identifying the geological features present in each of the plurality of seismic data images based on identification of object edges and identification of portions of objects representing the geological features. ### Claim 4 (depends on 1) The method of claim 1, wherein the geological attributes also comprise drilling hazards. ### Claim 5 (depends on 4) The method of claim 4, wherein the constraints comprise non-geological attributes, the non-geological attributes comprising at least one of: client behavior analysis information; news insights; regulation information; fiscal terms of exploration; or license requirements. ### Claim 6 (depends on 1) The method of claim 1, further comprising ranking the search results based on at least one of: a value representing the relevancy of the search results; weightings of the one or more geological features; constraints included in the geological search query; user search preferences; or collaborative filtering information. ### Claim 7 (depends on 1) The method of claim 1, wherein the geological feature search query comprises an identification of geological features of interest. ### Claim 8 (depends on 1) The method of claim 1, wherein the outputting information comprises presenting the search results as a geographic map, wherein the geographic map includes colors, patterns, or shadings representing varying levels of relevancy of the search results. ### Claim 9 (depends on 1) The method of claim 1, wherein the volume model or the basin model comprises a gravity model, a magnetic model, a pore pressure model, or a combination thereof. ### Claim 10 (depends on 1) The method of claim 1, wherein executing the search comprises searching areas of the seismic data images that comprise noise that is greater than a noise threshold, and wherein the noise comprises residual multiple or diffractions. ### Claim 11 (depends on 1) The method of claim 1, wherein executing the search comprises searching areas of the seismic data images that comprise imaging that is less than an imaging threshold, and wherein the imaging is less than the imaging threshold due to fault shadows or salt. ### Claim 12 (depends on 1) The method of claim 1, wherein executing the search comprises searching areas of the seismic data images where an incorrect parameterization of seismic processing occurred. ### Claim 13 (depends on 1) The method of claim 1, further comprising: accessing a user profile to determine a user's search preferences and job roles; and ranking the search results based upon the user's search preferences and job roles. ### Claim 14 (depends on 1) The method of claim 1, further comprising: determining rock types in the plurality of seismic images; selecting one of a plurality of noise removal techniques for the plurality of seismic images, wherein the selection is based upon the rock types; accessing a user profile to determine a user's search preferences and job roles; and ranking the search results based upon the user's search preferences and job roles, wherein the geological attributes also comprise geohazards and drilling hazards to avoid when drilling a wellbore, and wherein the one or more geological features comprise: areas of noise; areas of poor imaging due to a fault shadow and salt, and incorrect parameterization of seismic processing. ### Claim 15 A computer system, comprising: one or more processors; and a memory system comprising one or more non-transitory computer-readable media storing instructions thereon that, when executed, cause the computer system to perform operations, the operations comprising: identifying one or more geological features included in each of a plurality of seismic data images by executing a machine learning process; storing, in a database, information identifying the one or more geological features included in each of the plurality of seismic data images; receiving a geological feature search query identifying one or more geological features of interest and one or more constraints associated with the one or more geological features of interest, wherein the one or more constraints include geological attributes, and wherein the geological attributes comprise a depth below a mudline; executing, based on receiving the geological feature search query, a search of the database storing the information identifying the one or more geological features included in each of the plurality of seismic data images, wherein executing the search comprises searching the seismic data images and images from a volume model or a basin model; determining rock types present in the seismic data images, and selecting and implementing at least one of a plurality of noise removal techniques for the seismic data images based upon the determined rock types; determining, based on executing the search, search results, wherein the search results identify one more of the plurality of seismic data images having the one or more geological features of interest identified in the geological feature search query; and outputting information regarding the search results to facilitate performing at least one of exploration of at least one geographical area having the features of interest and avoidance of at least one geographical area comprising features representing hazardous areas. ### Claim 16 A non-transitory computer-readable medium storing instructions thereon that, when executed, cause a computer system to perform operations, the operations comprising: receiving a plurality of training images that are each labeled with information identifying geological features present in each of the plurality of training images; identifying one or more geological features included in each of a plurality of operational seismic data images by executing a machine learning process using the plurality of training images; storing, in a database, information identifying the one or more geological features included in each of the plurality of operational seismic data images; receiving a geological feature search query identifying one or more geological features of interest and one or more constraints associated with the one or more geological features of interest, wherein the one or more constraints include geological attributes, and wherein the geological attributes comprise a depth below a mudline; executing, based on receiving the geological feature search query, a search of the database storing the information identifying the one or more geological features included in each of the plurality of operational seismic data images, wherein executing the search comprises searching the operational seismic data images and images from a volume model or a basin model; determining rock types present in the operational seismic data images, and selecting and implementing at least one of a plurality of noise removal techniques for the operational seismic data images based upon the determined rock types; determining, based on executing the search, search results, wherein the search results identify one more of the plurality of operational seismic data images having the one or more geological features of interest identified in the geological feature search query; and outputting information regarding the search results to facilitate performing at least one of exploration of at least one geographical area having the features of interest and avoidance of at least one geographical area comprising features representing hazardous areas. ### Claim 17 (depends on 16) The non-transitory computer-readable media of claim 16, wherein the machine learning process further comprises identifying the geological features present in each of the plurality of training images based on identification of object edges and identification of portions of objects representing the geological features. ### Claim 18 (depends on 16) The non-transitory computer-readable media of claim 16, wherein the operations further comprise ranking the search results based on at least one of: a value representing the relevancy of the search results; weightings of the one or more geological features; constraints included in the geological search query; user search preferences; or collaborative filtering information. ### Claim 19 (depends on 16) The non-transitory computer-readable media of claim 16, wherein the outputting information comprises presenting the search results as a geographic map, wherein the geographic map includes colors, patterns, or shadings representing varying levels of relevancy of the search results.