Tight gas, a category of unconventional natural gas, relies on advanced intelligent monitoring methods for their extraction. Conventional logging for reservoir evaluation relies on logging data and the manual setting of evaluation criteria to classify reservoirs. However, the complexity and heterogeneity of tight reservoirs pose challenges in accurately identifying target layers by using traditional well-logging techniques. Machine learning may hold the key to solving this problem, as it enables computers to learn without being explicitly programmed and manually adding rules. Therefore, it is possible to make reservoir evaluations using machine learning methods. In this paper, the reservoir quality index (RQI) and porous geometric parameters obtained from the optimized inversion of the spherical–tubular model are adopted to evaluate the reservoir. Then, three different machine learning approaches, the random forest (RF) algorithm, support vector machine (SVM) algorithm, and extreme gradient boosting (XGB) algorithm, are utilized for reservoir classification. The selected dataset covers more than 7000 samples from five wells. The data from four wells are arranged as the training dataset, and the data of the remaining one well is designed as the testing dataset to calculate the prediction accuracies of different machine learning algorithms. Among them, accuracies of RF, SVM, and XGB are all higher than 90%, and XGB owns the highest result by reaching 97%. Machine learning based approaches can greatly assist reservoir prediction by implementing the well-logging data. The research highlights the application of reservoir classification with a higher prediction accuracy by combining machine learning algorithms with NMR-logging-based pore structure characterization, which can provide a guideline for sweet spot identification within the tight formation. This not only optimizes resource extraction but also aligns with the global shift towards clean and renewable energy sources, promoting sustainability and reducing the carbon footprint associated with conventional energy production. In summary, the fusion of machine learning and NMR-logging-based reservoir evaluation plays a crucial role in advancing both energy efficiency and the transition to cleaner energy sources.

Tight gas, a category of Deep Green Energy Resources, rely on advanced intelligent monitoring methods for their extraction. Conventional logging for reservoir evaluation relies on logging data and the manual setting of evaluation criteria to classify reservoirs. However, the complexity and heterogeneity of tight reservoirs pose challenges in accurately identifying target layers by using traditional well-logging techniques. Machine learning may hold the key to solving this problem, as it enables computers to learn without being explicitly programmed and manually added rules. Therefore, it is possible to make reservoir evaluation via using machine learning methods. In this paper, the reservoir quality index (RQI) and porous geometric parameters obtained from the optimized inversion of the spherical-tubular model are adopted to evaluate the reservoir. Then, three different machine learning approaches, the random forest (RF) algorithm, support vector machine (SVM) algorithm, and extreme gradient boosting (XGB) algorithm, are utilized for reservoir classification. The selected dataset covers more than 7,000 samples from five wells. The data from four wells are arranged as the training dataset, and the data of the remaining one well is designed as the testing dataset to calculate the prediction accuracies of different machine learning algorithms. Among them, accuracies of RF, SVM, and XGB are all higher than 90%, and XGB owns the highest result by reaching 97%. Machine learning based approaches can greatly assist reservoir prediction by implementing the well-logging data. The research highlights the application of reservoir classification with a higher prediction accuracy by combining machine learning algorithms with NMR logging based pore structure characterization, which can provide a guideline for sweet spot identification within the tight formation. This not only optimizes resource extraction but also aligns with the global shift towards clean and renewable energy sources, promoting sustainability and reducing the carbon footprint associated with conventional energy production. In summary, the fusion of machine learning and NMR logging based reservoir evaluation plays a crucial role in advancing both energy efficiency and the transition to cleaner energy sources.

Determining rock resistivity for saturation estimation in reservoirs is challenging due to the complex nature of pores in the rock. This paper aims to establish a computational relationship between formation factors ( F ) and permeability ( K ) by combining theoretical and experimental data. Firstly, the relationship between the permeability of the curved capillary model and formation factors, as well as the relationship between the permeability of the complex curved capillary model and formation factors, are deduced. Theoretical analysis proved that the formation factors ( F ) have a power relationship with permeability ( K ) and porosity ( φ ), and confirms the existence of additional resistivity ( R _x ). To validate the theoretical study, we conducted a model analysis using open experimental data from 35 sandstone cores with different porosities and permeabilities from the tight gas sandstone in the Western US basins, which measured resistivity data in saline at 20, 40 and 80 Kppm, respectively. We confirmed the existences of additional resistivity ( R _x ) by fitting the relationship between the rock resistivity of saturated formation water ( R ₀ ) and the formation water resistivity ( R _w ). We then fitted the formation resistivity change factor ( F _d ) with permeability ( K ), the formation resistivity change factor ( F _d ) with porosity ( φ ), the additional resistivity ( R _x ) with permeability ( K ), and the additional resistivity ( R _x ) with porosity ( φ ). Both the changeable formation resistivity change factor ( F _d ) and additional resistivity ( R _x ) showed a strong linear relationship with permeability ( K ) in logarithmic coordinates. We also verified the existence of a suitable equation using available experimental data by changing the formation parameters and permeability. The study shows that the fitting equations may be utilized to determine the changeable formation resistivity change factor ( F _d ), additional resistivity ( R _x ) and the rock resistivity of saturated formation water ( R ₀ ) with varying permeability. The predicted rock resistivity of saturated formation water ( R ₀ ) strongly correlates with that measured in the laboratory, providing better precision for future reservoir evaluations using saturation estimations.