Integration of Multiple Bayesian Optimized Machine Learning Techniques and Conventional Well Logs for Accurate Prediction of Porosity in Carbonate Reservoirs

Abstract

The accurate estimation of reservoir porosity plays a vital role in estimating the amount of hydrocarbon reserves and evaluating the economic potential of a reservoir. It also aids decision making during the exploration and development phases of oil and gas fields. This study evaluates the integration of artificial intelligence techniques, conventional well logs, and core analysis for the accurate prediction of porosity in carbonate reservoirs. In general, carbonate reservoirs are characterized by their complex pore systems, with the wide spatial variation and highly nonlinear nature of their petrophysical properties. Therefore, they require detailed well-log interpretations to accurately estimate their properties, making them good candidates for the application of machine learning techniques. Accordingly, a large database of (2100) well-log records and core-porosity measurements were integrated with four state-of-the-art machine learning techniques (multilayer perceptron artificial neural network, MLP-ANN; Gaussian process regression, GPR; least squares gradient boosting ensemble, LS-Boost; and radial basis function neural network, RBF-NN) for the prediction of reservoir porosity. The well-log data used in this study include sonic acoustic travel time, Gamma-ray, and bulk density log records, which were carefully collected from five wells in a carbonate reservoir. This study revealed that all the artificial intelligence models achieved high accuracy, with R-squared values exceeding 90% during both the training and blind-testing phases. Among the AI models examined, the GPR model outperformed the others in terms of the R-squared values, root-mean-square error (RMSE), and coefficient of variation of the root-mean-square error (CVRMSE). Furthermore, this study introduces an artificially intelligent AI-based correlation for the estimation of reservoir porosity from well-log data; this correlation was developed using an in-house, Fortran-coded MLP-ANN model presented herein. This AI-based correlation gave a promising level of accuracy, with R-squared values of 92% and 90% for the training and blind-testing datasets, respectively. This correlation can serve as an accurate and easy-to-use tool for porosity prediction without any prior experience in utilizing or implementing machine learning models.

An Explicit Data-Driven Model for Estimation of Free and Absorbed Gas Volumes in Shale Gas Reservoirs

“…Pseudocode of the utilized in-house ANN model: Randomly assign initial weights and biases to the network. Conduct a forward pass, calculating the output of the network using the input vector, weights, biases, and transfer functions. Compare the network’s output to the desired response and compute the global error using the following formula: normalError = false ∑ 1 n 1 false ∑ 1 n 2 false( y t − y p false) n 1 · n 2 Update the weights and biases by propagating backward through one of several gradient-based algorithms (scaled conjugate gradient, one-step secant, or Levenberg–Marquardt algorithm). The following convergence technique with an added acceleration term is used to speed up the network optimization process: w false( t + 1 false) = w false( t false) + β false[ normalΔ w false( t false) false] + α false[ w false( t − 1 false) false] where α is the momentum constant, w is the weight value, Δ w is the weight change, t is the training epoch, and β is the learning constant. (α and β) constant are employed to increase the step size and decrease abrupt gradient changes, these learning and momentum constants are confined between 0 and 1. Recalculate the network output using the updated weights and biases by repeating steps 2–4. Report the final optimized set of weights and biases when the model achieves a predetermined level of accuracy or reaches the maximum number of iterations. …”

“…Pseudocode of the utilized in-house ANN model: 37 Randomly assign initial weights and biases to the network. Conduct a forward pass, calculating the output of the network using the input vector, weights, biases, and transfer functions.…”

“…Pseudocode of the utilized in-house ANN model: 37 1. Randomly assign initial weights and biases to the network.…”

Deep dive into net pay layers: An in-depth study in Abadan Plain, South Iran

“…An integrative approach is adopted, leveraging core analysis data, conventional logs, and geological characteristics. Our work, which builds on recent advancements in productive zone determination using conventional logs [ [32] , [33] , [34] , [35] , [36] ], presents an innovative method for integrating diverse datasets to assess the quality of productive reservoir sections in carbonate reservoirs. The study's limitations due to the absence of advanced log data, such as DSI and NMR, and production tests like PLT and flowmeter, are acknowledged.…”

Machine Learning Algorithms That Emulate Controllers Based on Particle Swarm Optimization—An Application to a Photobioreactor for Algal Growth

“…The learning process is split at the level of each sampling period, and consequently, new data structures are derived for each of them. With each new data structure, which is a collection of couples (state; control value), a generic regression function [22,27,28] is associated. The latter is materialized through an ML regression model devoted to the sampling period at hand, which must be capable of giving accurate predictions.…”