Hydrocarbon Index Identification in Lateral Section of Horizontal WellsUsing Machine Learning

摘要

Machine learning is a powerful tool that has become an essential part of the oil and gas industry that providesadditional insights at limited data availability.In the vertical section,representative samples can be obtained,but in the horizontal section,core and well log data are extremely rare.With machine learning,mineralogydata can be trained to predict Total Organic Conten(TOC)and amount of free hydrocarbons(S1)andimplemented in the lateral section of a well.X-Ray Diffraction(XRD)data were used to train the MachineLearning Model to predict TOC & Flowable Hydrocarbon Index(FHI).For training,the vertical sectionof a well along with data from other wells nearby was used.It was then tested on the horizontal sectionof the same well to make certain that the model had learned meaningful relationships.The data were pre-processed to remove outliers,clean string variables,and missing values.New features were then added usingdomain knowledge,as some features are non linearly correlated with TOC.For example,certain mineralscorrelate with TOC and S1 differently in different flow units.Because of this,we made sure to collect datafor training and testing within the same flow unit.The features were then standardized to ensure that theresulting distribution had a mean of 0 and a standard deviation of 1.This was done for two reasons,firstly,itmakes sure the Machine Learning algorithm gives equal weightage to all features irrespective of their units,and range of values.Secondly,it helps the algorithm to converge faster,taking less time to train.The datawas then fed to the model to train on.Once the model was trained,the hyperparameters of the model werethen tuned using a suitable error metric.This was done in order to make certain that the model performs wellon test data,and does not overfit on the training data.Results of the trained model were compared to actualmeasured results from the rock along the horizontal wellbore.The predicted and measured results show agreat match based on several metrics such as coefficient of determination,mean absolute error,mean squarederror,and root mean squared error.The key observation was the importance of the sample acquisition,sample handling,eliminating human error during measurements in the lab,and data handling when applyingthe model.In conclusion,when the data is properly clustered using geological understanding it is meaningfulto apply machine learning algorithms to find multivariate relationships among different parameters.Thispaper presents a novel approach of obtaining volumetrics data based on"ground truth"measurements such as saturations along the horizontal wellbore without operational risks,potential downtime,and chances tolose tools.