Estimating shear wave velocity in carbonate reservoirs from petrophysical logs using intelligent algorithms

Robust computational approach to determine the safe mud weight window using well-log data from a large gas reservoir

Ongoing anthropogenic carbon dioxide (CO2) emissions to the atmosphere cause severe air pollution that leads to complex changes in the climate, which pose threats to human life and ecosystems more generally. Geological CO2 storage (GCS) offers a promising solution to overcome this critical environmental issue by removing some of the CO2 emissions. The performance of GCS projects depends directly on the solubility and residual trapping efficiency of CO2 in a saline aquifer. This study models the solubility trapping index (STI) and residual trapping index (RTI) of CO2 in saline aquifers by applying four robust machine learning (ML) and deep learning (DL) algorithms. Extreme learning machine (ELM), least square support vector machine (LSSVM), general regression neural network (GRNN), and convolutional neural network (CNN) are applied to 6811 compiled simulation records from published studies to provide accurate STI and RTI predictions. Employing different statistical error metrics coupled with supplementary evaluations, involving score and robustness analyses, the prediction accuracy of the models proposed is comparatively assessed. The findings of the study revealed that the LSSVM model delivers the lowest RMSE values: 0.0043 (STI) and 0.0105 (RTI) with few outlying predictions. Presenting the highest STI and RTI prediction scores the LSSVM is distinguished as the most credible model among all the four models studied. The models consider eight input variables, of which the time elapsed and injection rate displays the strongest correlations with STI and RTI, respectively. The results suggest that the proposed LSSVM model is best suited for monitoring CO2 sequestration efficiency from the data variables considered. Applying such models avoids time-consuming complex simulations and offers the potential to generate fast and reliable assessments of GCS project feasibility. Accurate modeling of CO2 storage trapping indexes guarantees successful geological CO2 storage operation, which is, in fact, the cornerstone of properly controlling and managing environmentally polluting gases. 

Machine-learning predictions of solubility and residual trapping indexes of carbon dioxide from global geological storage sites

The need to determine permeability at different stages of evaluation, completion, optimization of Enhanced Oil Recovery (EOR) operations, and reservoir modeling and management is reflected. Therefore, various methods with distinct efficiency for the evaluation of permeability have been proposed by engineers and petroleum geologists. The oil industry uses acoustic and Nuclear Magnetic Resonance (NMR) loggings extensively to determine permeability quantitatively. However, because the number of available NMR logs is not enough and there is a significant difficulty in their interpreting and evaluation, the use of acoustic logs to determine the permeability has become very important. Direct, continuous, and in-reservoir condition estimation of permeability is a unique feature of the Stoneley waves analysis as an acoustic technique. In this study, five intelligent mathematical methods, including Adaptive Network-Based Fuzzy Inference System (ANFIS), Least-Square Support Vector Machine (LSSVM), Radial Basis Function Neural Network (RBFNN), Multi-Layer Perceptron Neural Network (MLPNN), and Committee Machine Intelligent System (CMIS), have been performed for calculating permeability in terms of Stoneley and shear waves travel-time, effective porosity, bulk density and lithological data in one of the naturally-fractured and low-porosity carbonate reservoirs located in the Southwest of Iran. Intelligent models have been improved with three popular optimization algorithms, including Coupled Simulated Annealing (CSA), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA). Among the developed models, the CMIS is the most accurate intelligent model for permeability forecast as compared to the core permeability data with a determination coefficient (R2) of 0.87 and an average absolute deviation (AAD) of 3.7. Comparing the CMIS method with the NMR techniques (i.e., Timur-Coates and Schlumberger-Doll-Research (SDR)), the superiority of the Stoneley method is demonstrated. With this model, diverse types of fractures in carbonate formations can be easily identified. As a result, it can be claimed that the models presented in this study are of great value to petrophysicists and petroleum engineers working on reservoir simulation and well completion. 

/pdf/new-insights-into-permeability-determination-by-coupling-6bqzsqre.pdf

Mohammad Hossein Gandomgoun

Papers

A novel approach to pore pressure modeling based on conventional well logs using convolutional neural network

A new robust predictive model for lost circulation rate using convolutional neural network: A case study from Marun Oilfield