Search

Shear wave velocity (VS) data from sedimentary rock sequences is a prerequisite for implementing most mathematical models of petroleum engineering geomechanics. Extracting such data by analyzing finite reservoir rock cores is very costly and limited. The high cost of sonic dipole advanced wellbore logging service and its implementation in a few wells of a field has placed many limitations on geomechanical modeling. On the other hand, shear wave velocity VS tends to be nonlinearly related to many of its influencing variables, making empirical correlations unreliable for its prediction. Hybrid machine learning (HML) algorithms are well suited to improving predictions of such variables. Recent advances in deep learning (DL) algorithms suggest that they too should be useful for predicting VS for large gas and oil field datasets but this has yet to be verified. In this study, 6622 data records from two wells in the giant Iranian Marun oil field (MN#163 and MN#225) are used to train HML and DL algorithms. 2072 independent data records from another well (MN#179) are used to verify the VS prediction performance based on eight well-log-derived influencing variables. Input variables are standard full-set recorded parameters in conventional oil and gas well logging data available in most older wells. DL predicts VS for the supervised validation subset with a root mean squared error (RMSE) of 0.055 km/s and coefficient of determination (R2) of 0.9729. It achieves similar prediction accuracy when applied to an unseen dataset. By comparing the VS prediction performance results, it is apparent that the DL convolutional neural network model slightly outperforms the HML algorithms tested. Both DL and HLM models substantially outperform five commonly used empirical relationships for calculating VS from Vp relationships when applied to the Marun Field dataset. Concerns regarding the model's integrity and reproducibility were also addressed by evaluating it on data from another well in the field. The findings of this study can lead to the development of knowledge of production patterns and sustainability of oil reservoirs and the prevention of enormous damage related to geomechanics through a better understanding of wellbore instability and casing collapse problems. [ABSTRACT FROM AUTHOR]

Two-phase flow rate estimation of liquid and gas flow through wellhead chokes is essential for determining and monitoring production performance from oil and gas reservoirs at specific well locations. Liquid flow rate (QL) tends to be nonlinearly related to these influencing variables, making empirical correlations unreliable for predictions applied to different reservoir conditions and favoring machine learning (ML) algorithms for that purpose. Recent advances in deep learning (DL) algorithms make them useful for predicting wellhead choke flow rates for large field datasets and suitable for wider application once trained. DL has not previously been applied to predict QL from a large oil field. In this study, 7245 multi-well data records from Sorush oil field are used to compare the QL prediction performance of traditional empirical, ML and DL algorithms based on four influencing variables: choke size (D64), wellhead pressure (Pwh), oil specific gravity (γo) and gas–liquid ratio (GLR). The prevailing flow regime for the wells evaluated is critical flow. The DL algorithm substantially outperforms the other algorithms considered in terms of QL prediction accuracy. The DL algorithm predicts QL for the testing subset with a root-mean-squared error (RMSE) of 196 STB/day and coefficient of determination (R2) of 0.9969 for Sorush dataset. The QL prediction accuracy of the models evaluated for this dataset can be arranged in the descending order: DL > DT > RF > ANN > SVR > Pilehvari > Baxendell > Ros > Glbert > Achong. Analysis reveals that input variable GLR has the greatest, whereas input variable D64 has the least relative influence on dependent variable QL. [ABSTRACT FROM AUTHOR]

The casing-collapse hazard is one that drilling engineers seek to mitigate with careful well design and operating procedures. However, certain rock formations and their fluid pressure and stress conditions are more prone to casing-collapse risks than others. The Gachsaran Formation in south west Iran, is one such formation, central to oil and gas resource exploration and development in the Zagros region and consisting of complex alternations of anhydrite, marl and salt. The casing-collapse incidents in this formation have resulted over decades in substantial lost production and remedial costs to mitigate the issues surrounding wells with failed casing string. High and vertically-varying horizontal stresses across the Gachsaran formation are the challenge to predict and overcome. This study investigates casing collapse in wellbores from an established petroleum geomechanics perspective to develop and compare two hybrid neural-network models, multilayer perceptron's tuned, respectively, with a genetic algorithm (MLP-GA) and a particle swarm algorithm (MLP-PSO). These machine-learning algorithms are configured to predict Poisson's ratio (ϑ) and maximum horizontal stress (σ H) from available well-log input data. A large dataset from three wellbores drilled though the Gachsaran Formation in the Marun oil field, the second largest in Iran, is used to construct and validate the hybrid MLP models. In the first step, 22323 data records from a collapsed wellbore are divided into training (15626 records; 70%) and independent testing subsets (6697 records; 30%). In the next step, in order to test whether the suggested algorithms could be generalized, the data sets of the other two wells in the field were tested. Those tests confirmed that the algorithms achieved high prediction accuracy for Poisson's ratio and maximum horizontal stress in other wellbores. Image 1 • Casing-collapse prone Gascharan formation evaluated at Marun Oil Field Iran. • Geomechanical model reveals high and variable lithology-related horizontal stresses. • Particle swarm driven multi-layer perceptron accurately predicts casing collapse. • Combined assessment of static Poisson's ratio (ϑ) and maximum horizontal stress (σ H). • 22323 data records of four well-log variables from one well used to predict (ϑ) and (σ H). [ABSTRACT FROM AUTHOR]

Rock shear and strain behaviors deep in the sub-surface are dependent on several geomechanical variables. These include various types of stress and rock formation moduli. Deformations of specific rock formations are usually quantified in a series of laboratory tests, which are costly and time-consuming and can only be performed on the few rock formation samples and cores available. Consequently, indirect estimates of geomechanical metrics from well-log data are required to measure variations throughout the entire length of a wellbore. Such measurements and detailed geomechanical models are required to identify zones at risk of casing collapse due to shear stress buildups. Such zones tend to occur in problematic ductile formations such as salt and swelling clays that are prone to creep. Machine-learning algorithms coupled with optimizers, and calibrated with a few mechanical rock test measurements, offer a practical method for predicting geomechanical characteristics along an entire wellbore. Hybrid models combining the optimizers, imperialist competitive (ICA) and gravitation search (GSA) algorithms, with the machine-learning algorithms, distance-weighted K-nearest neighbor (DWKNN) and multi-layer perceptron (MLP) are shown to achieve high prediction accuracy of shear modulus (G s) from a large dataset (22,325 data records) crossing the problematic salt-rich Gachsaran formation in a wellbore from the Marun oil field (Iran). ICA-MLP, GSA-MLP, ICA-DWKNN and GSA-DWKNN models applied to four independent variables recorded by well logs were calibrated with some laboratory-derived G s measurements. These models predict G s with high levels of accuracy achieving coefficients of determination (R2) > 0.96. The GSA-DWKNN hybrid algorithm (R2 = 1) provided the highest prediction accuracy. G s predictions can then be used to accurately identify zones at risk of casing collapse. • Casing-collapse-prone Gachsaran formation evaluated at Marun Oil Field Iran. • Geomechanical model reveals high shear stress at boundaries of salt layers. • Gravitational search coupled with k- nearest-neighbor provide best Gs predictions. • Static shear modulus predictions help to identify wellbore zone prone to casing collapse. • 22,325 data records of four well-log variables from one well used to predict shear modulus. [ABSTRACT FROM AUTHOR]