Machine Learning Outlier Detection Algorithms for Enhancing Production Data Analysis of Shale Gas

An accurate total skin factor prediction for an oil well is critical for the evaluation of the inflow performance relationship, and the optimization of the appropriate stimulation treatment such as acidizing and hydraulic fracturing. Performing well testing regularly is not economically feasible, and the equations used for total skin damage may not be accurate. In this work, the goal is to build machine learning (ML) models that can predict the total skin factor in perforated wells using accessible field data. Nine distinct ML algorithms such as Gradient Boosting (GB), Adaptive Boosting (AdaBoost), Random Forest (RF), Support Vector Machines (SVMs), Decision Trees (DT), K-Nearest Neighbor (KNN), Linear Regression (LR), Stochastic Gradient Descent (SGD), and Artificial Neural Network (ANN) are meticulously developed and fine-tuned using a substantial dataset derived from 1,088 wells. The dataset encompasses 19,040 data points, thoughtfully split into two subsets: 70% (13,328 data points) for training the algorithms, and 30% (5,712 data points) for testing their predictions. The parameters used are mostly gathered during well completion and conventional well testing operations, including liquid flow rate, water cut, gas oil ratio, bottomhole flowing pressure, reservoir pressure, reservoir temperature, reservoir permeability, reservoir thickness, perforations diameter, perforations density, perforations penetration depth, well deviation, and penetrated portion of the net pay thickness. In this study, the total skin factor acquired from conventional well test analysis serves as the model's output. K-fold cross-validation and repeated random sampling validation techniques are used to assess the performance of the models against the total skin obtained from the conventional well test analysis. The K-fold cross-validation outcomes of the top-performing ML models, specifically GB, AdaBoost, RF, DT, and KNN, reveal remarkably low mean absolute percentage error values reported as 3.2%, 3.2%, 2.9%, 3.3%, and 3.8%, respectively. Additionally, the correlation coefficients (R2) for these models are notably high, with values of 0.972, 0.968, 0.975, 0.964, and 0.956, respectively. In conclusion, ML models demonstrated their ability to predict total skin factor for different reservoir fluid properties, well geometries, and completion configurations. ML models offer a more efficient, quick, and cost-effective alternative to the conventional well-testing analysis.

show abstract

Machine Learning Models to Predict Production Rate of Sucker Rod Pump Wells

Thabet,

Zidan,

Elhadidy

et al. 2024

SPE Western Regional Meeting

View full text Add to dashboard Cite

The design, operation, and optimization of Sucker Rod Pumping (SRP) systems necessitate the utilization of production data. However, forecasting fluid flow rates at the surface of SRP artificially lifted wells usually poses a challenge, especially in instances where traditional separators and multiphase flowmeters are not universally available. Consequently, this study introduces nine machine learning (ML) models employing real data sourced from 598 wells with a production history exceeding three years. The dataset, comprising 8,372 data points, undergoes a random split allocating around 80% of the data (6,697 data points) for training, while around 20% (1,675 data points) are used for testing. The ML models encompass Gradient Boosting (GB), Adaptive Boosting (AdaBoost), Random Forest (RF), Support Vector Machines (SVMs), Decision Tree (DT), K-Nearest Neighbor (KNN), Linear Regression (LR), Artificial Neural Network (ANN), and Stochastic Gradient Descent (SGD). The chosen input features for the models are readily accessible during any SRP well-lifting process, and these inputs include various variables such as wellhead flowing pressure, casing pressure, predicted bottom hole fluid production rate, predicted bottom hole oil production rate, net liquid head above the pump, pump size, pump clearance, stroke length, pump speed, pump setting depth, the temperature at the pump depth, oil gravity, and water viscosity. Evaluation of the different ML models’ performance is carried out by two methodologies: K-fold cross-validation, and repeated random sampling. The findings reveal that the top-performing models are GB, AdaBoost, RF, LR, and SGD, exhibiting mean absolute percentage errors of 3.6%, 3.4%, 3.4%, 4.0%, and 4.4% respectively, and correlation coefficients (R2) of 0.937, 0.934, 0.935, 0.921, and 0.915, respectively. In practical field application, these models are deployed on a well within Egypt's Western Desert fields, demonstrating excellent agreement between actual fluid rates and model predictions. In conclusion, across diverse pumping scenarios and completion configurations, the ML models could effectively forecast production rates for different SRP wells. This capability facilitates continuous monitoring, optimization, and performance analysis of SRP wells, enabling swift responses to operational challenges since the proposed ML models offer an accessible, rapid, and cost-effective alternative to conventional separators and multiphase flowmeters.

show abstract

Machine Learning Outlier Detection Algorithms for Enhancing Production Data Analysis of Shale Gas

Cited by 3 publications

References 0 publications

Identifying the controlling geological and engineering factors of shale gas production using deep learning models: a case study from Weiyuan, China

Identifying the controlling geological and engineering factors of shale gas production using deep learning models: a case study from Weiyuan, China

Machine Learning Models to Predict Total Skin Factor in Perforated Wells

Machine Learning Models to Predict Production Rate of Sucker Rod Pump Wells

Contact Info

Product

Resources

About