Determining Subsurface Formation Boundaries

Abstract

Systems and methods for determining formation boundaries in a subsurface formation include receiving log data from a set of reference wells in a subsurface formation. A model is calibrated based on the log data to detect formation boundaries. receiving log data from a set of target wells in the subsurface formation. Log data from the set of target wells is reconstructed based on a machine learning model. Depths of formation boundaries are determined based on the calibrated model. Similarities between are determined between log data in intervals defined by the determined depths of formation boundaries from two or more wells. Formation boundaries are correlated between the two or more wells in the subsurface formation based on the determined similarities; and a visual representation of the depth of formation boundaries in the subsurface formation is generated based on the correlated formation boundaries.

What is claimed is: 
     
         1 . A method for determining formation boundaries in a subsurface formation, the method comprising:
 receiving log data from a set of reference wells in a subsurface formation;   calibrating a model to detect formation boundaries, the calibrating being based on the log data from the set of reference wells;   receiving log data from a set of target wells in the subsurface formation, the set of target wells being different than the set of reference wells;   reconstructing log data from the set of target wells based on a machine learning model, the machine learning model being trained on the log data from the set of reference wells;   determining depths of formation boundaries based on the model;   determining similarities between log data in intervals defined by the determined depths of formation boundaries from two or more wells of the set of reference wells and the set of target wells;   correlating formation boundaries between the two or more wells in the subsurface formation based on the determined similarities; and   generating a visual representation of the depth of formation boundaries in the subsurface formation based on the correlated formation boundaries.   
     
     
         2 . The method of  claim 1 , further comprising:
 determining a location in the subsurface formation comprising hydrocarbons based on the correlated formation boundaries; and   drilling a well at the determined location.   
     
     
         3 . The method of  claim 1 , wherein calibrating the model comprises determining a set of log data for each well that minimizes an uncertainty of determined locations of formation boundaries. 
     
     
         4 . The method of  claim 3 , wherein the model comprises a change point detection model. 
     
     
         5 . The method of  claim 4 , wherein the change point detection model comprises a dynamic programming change point detection model, a change point detection model with linear computation cost, a multiple change-point detection model with a reproducing kernel, a binary segmentation change point detection model, a bottom-up segmentation change point detection model, or a sliding window change point detection algorithm. 
     
     
         6 . The method of  claim 1 , wherein the machine learning model comprises an ensemble-based regression model or an artificial neural network model. 
     
     
         7 . The method of  claim 1 , further comprising: training the machine learning model based on well log data, cuttings-based lithology data, drilling data, and mud gas data from the set of reference wells. 
     
     
         8 . The method of  claim 1 , wherein the machine learning model is trained on well log data, cuttings-based lithology data, drilling data, and mud gas data from the set of reference wells. 
     
     
         9 . The method of  claim 1 , wherein the log data comprises formation tops data, cuttings-based lithology data, and well logging data. 
     
     
         10 . The method of  claim 1 , wherein reconstructing log data comprises:
 providing cuttings-based lithology data, drilling data, and mud gas data from the set of target wells as input to the machine learning model; and   receiving the reconstructed log data as output from the machine learning model.   
     
     
         11 . The method of  claim 1 , wherein determining similarities between identified intervals comprises determining similarities based on an adjusted Rand index, an adjusted mutual information metric, an area under a receiver operating characteristic curve, or an area under a precision-recall curve. 
     
     
         12 . A system for determining formation boundaries in a subsurface formation, the system comprising:
 at least one processor; and   a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
 receiving log data from a set of reference wells in a subsurface formation; 
 calibrating a model to detect formation boundaries, the calibrating being based on the log data from the set of reference wells; 
 receiving log data from a set of target wells in the subsurface formation, the set of target wells being different than the set of reference wells; 
 reconstructing log data from the set of target wells based on a machine learning model, the machine learning model being trained on the log data from the set of reference wells; 
 determining depths of formation boundaries based on the calibrated model; 
 determining similarities between log data in intervals defined by the determined depths of formation boundaries from two or more wells of the set of reference wells and the set of target wells; 
 correlating formation boundaries between the two or more wells in the subsurface formation based on the determined similarities; and 
 generating a visual representation of the depth of formation boundaries in the subsurface formation based on the correlated formation boundaries. 
   
     
     
         13 . The system of  claim 12 , wherein the model comprises a dynamic programming change point detection model, a change point detection model with linear computation cost, a multiple change-point detection model with a reproducing kernel, a binary segmentation change point detection model, a bottom-up segmentation change point detection model, or a sliding window change point detection algorithm. 
     
     
         14 . The system of  claim 12 , wherein the machine learning model comprises an ensemble-based regression model or an artificial neural network model. 
     
     
         15 . The system of  claim 12 , wherein the log data comprises formation tops data, cuttings-based lithology data, and well logging data. 
     
     
         16 . The system of  claim 12 , wherein reconstructing log data comprises:
 providing cuttings-based lithology data, drilling data, and mud gas data from the set of target wells as input to the machine learning model; and   receiving the reconstructed log data as output from the machine learning model.   
     
     
         17 . One or more non-transitory machine-readable storage devices storing instructions for determining formation boundaries in a subsurface formation, the instructions being executable by one or more processors, to cause performance of operations comprising:
 receiving log data from a set of reference wells in a subsurface formation;   calibrating a model to detect formation boundaries, the calibrating being based on the log data from the set of reference wells;   receiving log data from a set of target wells in the subsurface formation, the set of target wells being different than the set of reference wells;   reconstructing log data from the set of target wells based on a machine learning model, the machine learning model being trained on the log data from the set of reference wells;   determining depths of formation boundaries based on the model;   determining similarities between log data in intervals defined by the determined depths of formation boundaries from two or more wells of the set of reference wells and the set of target wells;   correlating formation boundaries between the two or more wells in the subsurface formation based on the determined similarities; and   generating a visual representation of the depth of formation boundaries in the subsurface formation based on the correlated formation boundaries.   
     
     
         18 . The non-transitory, machine-readable storage devices of  claim 17 , wherein the model comprises a dynamic programming change point detection model, a change point detection model with linear computation cost, a multiple change-point detection model with a reproducing kernel, a binary segmentation change point detection model, a bottom-up segmentation change point detection model, or a sliding window change point detection algorithm. 
     
     
         19 . The non-transitory, machine-readable storage devices of  claim 17 , wherein the machine learning model comprises an ensemble-based regression model or an artificial neural network model. 
     
     
         20 . The non-transitory, machine-readable storage devices of  claim 17 , wherein reconstructing log data comprises:
 providing cuttings-based lithology data, drilling data, and mud gas data from the set of target wells as input to the machine learning model; and   receiving the reconstructed log data as output from the machine learning model.