Reliable predictions of oil formation volume factor based on transparent and auditable machine learning approaches (original) (raw)
Related papers
Transparent Machine Learning Algorithm Offers Useful Prediction Method for Natural Gas Density
2018
Machine-learning algorithms aid predictions for complex systems with multiple influencing variables. However, many neural-network related algorithms behave as black boxes in terms of revealing how the prediction of each data record is performed. This drawback limits their ability to provide detailed insights concerning the workings of the underlying system, or to relate predictions to specific characteristics of the underlying variables. The recently proposed transparent open box (TOB) learning network algorithm successfully addresses these issues by revealing the exact calculation involved in the prediction of each data record. That algorithm, described in summary, can be applied in a spreadsheet or fully-coded configurations and offers significant benefits to analysis and prediction of many natural gas systems. The algorithm is applied to the prediction of natural gas density using a published dataset of 693 data records involving 14 variables (temperature and pressure plus the m...
International Journal of Frontiers in Engineering and Technology Research
Bubble point pressure (BPP) is a key parameter for oil and gas reservoir identification, characterization, and management. An accurate correlation of this property with the evolving digital technology of machine learning, in the absence of experimental PVT analysis, serves as guidance in the development and recovery of reservoir fluids. In this study, a predictive BPP correlation was derived by intrinsically linearizing a nonlinear multiple regression, with the best coefficients (global minimum) extracted using White-box (Linear Regression, Ridge Regression, and Lasso Regression) Machine Learning models. The new correlation was developed, validated, and tested using 314 measured PVT data points from the Niger Delta Region. The data were subdivided into four classes: extra-light crude for API > 45, light crude for 31.1 < API ≤ 45, medium crude for 22.3 < API ≤ 31.1, and heavy crude for API ≤ 22.3. Statistical evaluation metrics such as root mean squared error, average absolu...
Chemical Engineering & Technology, 2008
The phase performance of hydrocarbons is a very complicated behavior that hydrocarbons show at the time of phase change or when they remain in a particular phase. Process design is almost impossible without a good understanding of this behavior. Artificial Neural Networks have been widely utilized for engineering applications during the last two decades. Two models are presented for the prediction of the bubble point pressure and the oil formation volume factor for hydrocarbon mixtures using the Artificial Neural Networks (ANNs) approach. For this purpose, five-layer neural networks were designed and trained using 106 experimental data points. After the training step, 9 experimental data points were also used for the model evaluation step and as a reliability check. The output of the models for both the training and predicted data are compared with the empirical equations of Standing, Glaso and Marhoun. It is concluded that the ANNs approach has an excellent capability for these purposes compared to the conventional methods.
Petroleum & Petrochemical Engineering Journal
One of the key factors that analysts consider when calculating the economics of oil field development is the amount of oil in place (OIP). Conventional methods used for its estimation have some features affecting their predictive capabilities and applications. In addition, Oil bidders have limited time to evaluate and rank reservoirs from complex and large reservoir data packages - which sometimes fees are paid for their access. In this study, data-driven machine learning models - artificial neural network (ANN), support vector regression (SVR) and multiple linear regression (MLR) were developed for quick estimation of OIP for oil rim reservoirs in the Niger Delta. The models were evaluated using statistical error tools, and the results showed reasonable predictions. The sensitivity analysis performed on the selected input parameters showed that areal extent has the greatest impact on the estimation of the OIP with 29.94 %, oil formation volume factor has 22.74 % impact, oil column ...
Petroleum, 2018
Bubble point pressure is one of the most important pressure–volume–temperature properties of crude oil, and it plays an important role in reservoir and production engineering calculations. It can be precisely determined experimentally. Although, experimental methods present valid and reliable results, they are expensive, time-consuming, and require much care when taking test samples. Some equations of state and empirical correlations can be used as alternative methods to estimate reservoir fluid properties (e.g., bubble point pressure); however, these methods have a number of limitations. In the present study, a novel numerical model based on artificial neural network (ANN) is proposed for the prediction of bubble point pressure as a function of solution gas–oil ratio, reservoir temperature, oil gravity (API), and gas specific gravity in petroleum systems. The model was developed and evaluated using 760 experimental data sets gathered from oil fields around the world. An optimizatio...
The Mining-Geology-Petroleum Engineering Bulletin, 2019
Driven by advancements in technology, tight-gas field development has become a significant source of hydrocarbon to the energy industry. The amount of data generated in the process is immense as most platforms are now being digitized. Machine learning tools can be used to analyze this data in order to build patterns between several dependent and independent variables. Forecasting initial gas production rates has important implications in the planning production/processing facilities for new wells, affects investment decisions, and is an important component of reporting to regulatory agencies. This study is based on the analysis of reservoir rock/fluid properties and selected well parameters to build decision-based models that can predict initial gas production rates for tight gas formations. In this study, two machine learning predictive models; Artificial Neural Network (ANN) and Generalized Linear Model (GLM), were used to determine the expected recovery rate of planned new wells. Production data was retrieved from 224 wells and used in developing the model. The results obtained from these models were then compared to the actual recorded initial gas production rate from the wells. Results from the analysis carried out revealed a Mean Square Error (MSE) of 1.57 on a GLM model whereas the ANN model gave an MSE of 1.24. Key Performance Index for the ANN model revealed that reservoir thickness had the highest (36.5%) contribution to the initial gas production rate followed by the flow back rate (29%). The reservoir/fluid properties contribution to the initial gas production rate was 53% while the hydraulic fracture parameters contribution to the initial gas production rate was 47%.
Prediction of oil PVT properties using neural networks
SPE Middle East Oil …, 2001
Reservoir fluid properties are very important in reservoir engineering computations such as material balance calculations, well test analysis, reserve estimates, and numerical reservoir simulations. Ideally, these properties should be obtained from actual measurements. Quite often, however, these measurements are either not available, or very costly to obtain. In such cases, empirically derived correlations are used to predict the needed properties. All computations, therefore, will depend on the accuracy of the correlations used for predicting the fluid properties. This study presents Artificial Neural Networks (ANN) model for predicting the formation volume factor at the bubble point pressure. The model is developed using 803 published data from the Middle East, Malaysia, Colombia, and Gulf of Mexico fields. One-half of the data was used to train the ANN models, one quarter to cross-validate the relationships established during the training process and the remaining one quarter to test the models to evaluate their accuracy and trend stability. The results show that the developed model provides better predictions and higher accuracy than the published empirical correlations. The present model provides predictions of the formation volume factor at the bubble point pressure with an absolute average percent error of 1.789%, a standard deviation of 2.2053% and correlation coefficient of 0.988. Trend tests were performed to check the behavior of the predicted values of B ob for any change in reservoir temperature, Gas Oil Ratio (GOR), gas gravity and oil gravity. The trends were found to obey the physical laws.
Artificial Neural Network Surrogate Modeling of Oil Reservoir: A Case Study
Advances in Neural Networks – ISNN 2019, 2019
We develop a data-driven model, introducing recent advances in machine learning to reservoir simulation. We use a conventional reservoir modeling tool to generate training set and a special ensemble of artificial neural networks (ANNs) to build a predictive model. The ANN-based model allows to reproduce the time dependence of fluids and pressure distribution within the computational cells of the reservoir model. We compare the performance of the ANN-based model with conventional reservoir modeling and illustrate that ANN-based model (1) is able to capture all the output parameters of the conventional model with very high accuracy and (2) demonstrate much higher computational performance. We finally elaborate on further options for research and developments within the area of reservoir modeling.
Numerical simulations and decline curve analysis are classic tools used for predicting reservoir performance. Numerical simulations are a very complex tool, offering a nonunique solution with a high degree of uncertainty. Decline curve analysis does not take into account opening or closing intervals and variable injection rates. In this study, the authors designed a feedforward backpropagation neural network model as an alternative technique for predicting oil reservoir production performance. Real historical production data obtained from a Libyan oil field was used to train the network. This training network can serve as a practical reservoir production management tool.
Journal of Petroleum Science and Engineering, 2016
Accurate predictions of fluid properties, such as density, oil formation volume factor and bubble point pressure, are essentials for all reservoir engineering calculations. In this paper, an approach based on nonlinear system identification modeling; Nonlinear ARX (NARX) and Hammerstein-Wiener (HW) predictive model, is proposed for forecasting the pressure/volume/temperature (PVT) properties of crude oil systems. To this end, two datasets; one containing 168 PVT samples from different Iranian oil reservoirs and other a databank containing 755 data from various geographical locations, were employed to construct (i.e. train) and evaluate (i.e. test) the models. Simulation results demonstrate that the proposed NARX and HW models outperform previously employed methods including three types of artificial neural networks models (committee machine, multilayer perceptron and radial basis function), two types of ANFIS models (grid partition and fuzzy c-mean) and several empirical correlations with the smallest prediction error, and that they are reliable models for predicting the oil properties in reservoirs engineering among other soft computing approaches.