System and method for proactive geosteering to improve well placement

Abstract

A computer-implemented method includes: receiving a plurality of streams of data encoding measurements taken from sensors on a drilling bit during a geosteering operation to place the drilling bit in a reservoir of hydrocarbons; applying a trained artificial intelligence (AI) engine to the measurements as the plurality of streams of data are received; based on, at least in part, applying the trained AI engine, detecting at least one anomaly when placing the drilling bit during the geosteering operation; upon said detecting, generating an automated notification and a recommended action; and in response to a user feedback to the recommended action, adjusting the drilling bit in accordance with the user feedback.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 receiving a plurality of streams of data encoding measurements taken from sensors on a drilling bit during a geosteering operation to place the drilling bit in a reservoir of hydrocarbons;   applying a trained artificial intelligence (AI) engine to the measurements as the plurality of streams of data are received;   based on, at least in part, applying the trained AI engine, detecting at least one drilling anomaly when placing the drilling bit in the reservoir of hydrocarbons during the geosteering operation;   upon detecting the at least one drilling anomaly, generating an automated notification and a recommended action; and   in response to a user feedback to the recommended action, adjusting the drilling bit in accordance with the user feedback.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the trained AI engine is configured to be trigged by a network of conditional logics that include range criteria for a plurality of parameters. 
     
     
         3 . The computer-implemented method of  claim 2 , wherein the range criteria provide ranges for the plurality of parameters, wherein each parameter indicates a respective measurement, or a rage of change of a respective measurement. 
     
     
         4 . The computer-implemented method of  claim 2 , wherein the trained AI engine is generated utilizing historical measurements taken from one or more offset wells of the reservoir of hydrocarbons, wherein the historical measurements include: a measured reservoir parameter at the one or more offset wells, or a configuration parameter of the drilling bit at the one or more offset wells. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein detecting at least one drilling anomaly comprises detecting a trend of forecast reservoir parameters deviating from a target well planning requirement when placing the drill bit for the geosteering operation,
 wherein the trained AI engine generates, using current drilling parameters of the drilling bit and historical measurements taken from one or more offset wells of the reservoir of hydrocarbons, the forecast reservoir parameters.   
     
     
         6 . The computer-implemented method of  claim 5 , wherein generating the automated notification and the recommended action comprises:
 sending, using a user-interactive chatbot interface, the automated notification to participants of the geo-steering operation, and   conducting, using the user-interactive chatbot interface, an interactive session with the participants of the geo-steering operation so that the participants can concur on the recommended action.   
     
     
         7 . The computer-implemented method of  claim 1 , wherein the sensors comprise: a resistivity sensor, a gamma ray sensor, a sonic sensor, a nuclear magnetic resonance (NMR) tool, a pressure sensor, or a temperature sensor. 
     
     
         8 . A computer system comprising one or more hardware computer processors configured to perform operations of:
 receiving a plurality of streams of data encoding measurements taken from sensors on a drilling bit during a geosteering operation to place the drilling bit in a reservoir of hydrocarbons;   applying a trained artificial intelligence (AI) engine to the measurements as the plurality of streams of data are received;   based on, at least in part, applying the trained AI engine, detecting at least one drilling anomaly when placing the drilling bit in the reservoir of hydrocarbons during the geosteering operation;   upon detecting the at least one drilling anomaly, generating an automated notification and a recommended action; and   in response to a user feedback to the recommended action, adjusting the drilling bit in accordance with the user feedback.   
     
     
         9 . The computer system of  claim 8 , wherein the trained AI engine is configured to trigged by a network of conditional logics that include range criteria for a plurality of parameters. 
     
     
         10 . The computer system of  claim 9 , wherein the range criteria provide ranges for the plurality of parameters, wherein each parameter indicates a respective measurement, or a range of change of a respective measurement. 
     
     
         11 . The computer system of  claim 9 , wherein the trained AI engine is generated utilizing historical measurements taken from one or more offset wells of the reservoir of hydrocarbons, wherein the historical measurements include: a measured reservoir parameter at the one or more offset wells, or a configuration parameter of the drilling bit at the one or more offset wells. 
     
     
         12 . The computer system of  claim 8 , wherein detecting at least one anomaly comprises detecting a trend of forecast reservoir parameters deviating from a target well planning requirement when placing the drill bit for the geosteering operation,
 wherein the trained AI engine generates, using current drilling parameters of the drilling bit and historical measurements taken from one or more offset wells of the reservoir of hydrocarbons, the forecast reservoir parameters.   
     
     
         13 . The computer system of  claim 12 , wherein generating the automated notification and the recommended action comprises:
 sending, using a user-interactive chatbot interface, the automated notification to participants of the geo-steering operation, and   conducting, using the user-interactive chatbot interface, an interactive session with the participants of the geo-steering operation so that the participants can concur on the recommended action.   
     
     
         14 . The computer system of  claim 8 , wherein the sensors comprise: a resistivity sensor, a gamma ray sensor, a sonic sensor, a nuclear magnetic resonance (NMR) tool, a pressure sensor, or a temperature sensor. 
     
     
         15 . A non-transitory computer-readable medium comprising software instructions that, when executed, cause a computer processor to perform operations of:
 receiving a plurality of streams of data encoding measurements taken from sensors on a drilling bit during a geosteering operation to place the drilling bit in a reservoir of hydrocarbons;   applying a trained artificial intelligence (AI) engine to the measurements as the plurality of streams of data are received;   based on, at least in part, applying the trained AI engine, detecting at least one drilling anomaly when placing the drilling bit in the reservoir of hydrocarbons during the geosteering operation;   upon detecting the at least one drilling anomaly, generating an automated notification and a recommended action; and   in response to a user feedback to the recommended action, adjusting the drilling bit in accordance with the user feedback.   
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein the trained AI engine is configured to trigged by a network of conditional logics that include range criteria for a plurality of parameters. 
     
     
         17 . The non-transitory computer-readable medium of  claim 16 , wherein the range criteria provide ranges for the plurality of parameters, wherein each parameter indicates a respective measurement, or a range of change of a respective measurement. 
     
     
         18 . The non-transitory computer-readable medium of  claim 16 , wherein the trained AI engine is generated utilizing historical measurements taken from one or more offset wells of the reservoir of hydrocarbons, wherein the historical measurements include: a measured reservoir parameter at the one or more offset wells, or a configuration parameter of the drilling bit at the one or more offset wells. 
     
     
         19 . The non-transitory computer-readable medium  claim 15 , wherein detecting at least one anomaly comprises detecting a trend of forecast reservoir parameters deviating from a target well planning requirement when placing the drill bit for the geosteering operation,
 wherein the trained AI engine generates, using current drilling parameters of the drilling bit and historical measurements taken from one or more offset wells of the reservoir of hydrocarbons, the forecast reservoir parameters.   
     
     
         20 . The non-transitory computer-readable medium of  claim 19 , wherein generating the automated notification and the recommended action comprises:
 sending, using a user-interactive chatbot interface, the automated notification to participants of the geo-steering operation, and   
       conducting, using the user-interactive chatbot interface, an interactive session with the participants of the geo-steering operation so that the participants can concur on the recommended action.