Formation resistivity is crucial for calculating water saturation, which, in turn, is used to estimate the stock-tank oil initially in place. However, obtaining a complete resistivity log can be challenging due to high costs, equipment failure, or data loss. To overcome this issue, this study introduces novel machine learning models that can be used to predict the electrical resistivity of oil wells, using conventional well logs. The analysis utilized gamma-ray (GR), delta time compressional logs (DTC), sonic shear log (DSTM), neutron porosity, and bulk density. The study utilized a dataset of 3529 logging data points from horizontal oil carbonate wells which were used to develop different machine learning models using random forest (RF) and decision tree (DT) algorithms. The obtained results showed that both models can predict electrical resistivity with high accuracy, over 0.94 for training and testing data. Comparing the models based on accuracy and consistency revealed that the RF model had a slight advantage over the DT model. Based on the data analysis, it was found that the formation resistivity is more significantly impacted by GR logs compared to DTC logs. These new ML models offer a low-cost and practical alternative to estimate well resistivity in oil wells, providing valuable information for geophysical and geological interpretation.
This study presents a new model to predict the static formation temperature at multiple oil fields using multiple machine learning algorithms. Results are compared with the real temperatures obtained from two wells. The model developed in this study predicts static formation temperature according to several machine learning algorithms including artificial neural networks, fuzzy logic, k-nearest neighbors, and random forest algorithms. The following are the key findings: various geothermal wells in distinct fields or formations may have different machine learning connections. However, if a connection is defined using adequate field data, it is clear that static formation temperature can be approximated with great accuracy. Based on machine learning models we developed a novel model for forecasting static formation temperature, examined the modeling data and outcomes, and found that Random Forest, Fuzzy logic, and K-nearest neighbors outperformed Artificial Neural Network. Therefore, the performance of the proposed model for estimating static well temperature achieved a mean absolute percentage (AAPE) of 0.003%, and the coefficient of determination (R 2 ) is 0.99%. When the classical (mathematical) methods were compared to the artificial intelligence methods, the artificial intelligence methods produced more accurate results with varying percentages. The findings generated by the unique new model computation and the measured test data are substantially matched when compared to computed data and observed temperature data. The novelty of this newly developed AI model is that it will serve as a practical and inexpensive tool for SFT determination in geothermal and petroleum wells.
This study presents a new model to predict the static formation temperature at multiple oil fields using multiple machine learning algorithms. Results are compared with the real temperatures obtained from two wells. The model developed in this study predicts static formation temperature according to several machine learning algorithms including artificial neural networks, fuzzy logic, k-nearest neighbors, and random forest algorithms. The following are the key findings: various geothermal wells in distinct fields or formations may have different machine learning connections. However, if a connection is defined using adequate field data, it is clear that static formation temperature can be approximated with great accuracy. Based on machine learning models, we developed a novel model for forecasting static formation temperature, examined the modeling data and outcomes, and found that Random Forest, Fuzzy logic, and K-nearest neighbors outperformed Artificial Neural Network. Therefore, the performance of the proposed model for estimating static well temperature achieved a mean absolute percentage (AAPE) of 0.003%, and the coefficient of determination (R 2 ) is 0.99%. When the classical (mathematical) methods were compared to the artificial intelligence methods, the artificial intelligence methods produced more accurate results with varying percentages. The findings generated by the unique new model computation and the measured test data are substantially matched when compared to computed data and observed temperature data. The novelty of this newly developed AI model is that it will serve as a practical and inexpensive tool for SFT determination in geothermal and petroleum wells.
This study presents a new model to predict the static formation temperature at multiple oil fields using multiple machine learning algorithms. Results are compared with the real obtained temperatures from two wells. The model developed in this study uses Python and Matlab to predict static formation temperature according to several machine learning algorithms including artificial neural networks, fuzzy logic, k-nearest neighbors, and random forest algorithms. Also, we used well-known analytical methods called line-source-Horner and spherical & radial heat-flow (SRF). The following are the key findings: Using well-known analytical methods, we estimated formation hole temperatures, our results demonstrated that The Horner approach overestimates the static temperature of the formation., but the SRF method gives more accurate temperatures. Using Python and MATLAB programming languages, based on machine learning models, we developed a novel model for forecasting static formation temperature., examined the modeling data and outcomes, and found that Random Forest (RF), Fuzzy logic (FL), and K-nearest neighbors (KNN) outperformed Artificial Neural Network (ANN). Therefore, the performance of the proposed model for estimating the static well temperature achieved an error percentage of AAPE 0.003% and R2 is 0.99%. The findings generated by the unique new model computation and the measured test data are substantially matched when compared to computed data and observed temperature data. The novelty of this newly developed AI model is that it will serve as a practical and inexpensive tool for SFT determination in geothermal and petroleum wells. Keywords: Static Formation temperature; artificial intelligence; predicting the static formation temperature at multiple oil fields; Honor method; SRF method
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.