Prediction of Reservoir Quality from Log-Core and Seismic Inversion Analysis with an Artificial Neural Network: A Case Study from the Sawan Gas Field, Pakistan

Abstract

This paper presents a novel approach that aims to predict better reservoir quality regions from seismic inversion and spatial distribution of key reservoir properties from well logs. The reliable estimation of lithology and reservoir parameters at sparsely located wells in the Sawan gas field is still a considerable challenge. This is due to three main reasons: (a) the extreme heterogeneity in the depositional environments, (b) sand-shale intercalations, and (c) repetition of textural changes from fine to coarse sandstone and very coarse sandstone in the reservoir units. In this particular study, machine learning (ML) inversion algorithm was selected to predict the spatial variations of acoustic impedance (AI), porosity, and saturation. While trained in a supervised mode, the support vector machine (SVM) inversion algorithm performed effectively in identifying and mapping individual reservoir properties to delineate and quantify fluid-rich zones. Meanwhile, the Sequential Gaussian Simulation (SGS) and Gaussian Indicator Simulation (GIS) algorithms were employed to determine the spatial variability of lithofacies and porosity from well logs and core analyses data. The calibration of the detailed spatial variations from post-stack seismic inversion using SVM and wireline logs data indicated an appropriate agreement, i.e., variations in AI is related to the variations in reservoir facies and parameters. From the current study, it was concluded that in a highly heterogeneous reservoir, the integration of SVM and GIS algorithms is a reliable approach to achieve the best estimation of the spatial distribution of detailed reservoir characteristics. The results obtained in this study would also be helpful to minimize the uncertainty in drilling, production, and injection in the Sawan gas field of Pakistan as well as other reservoirs worldwide with similar geological settings.

Simulating the strategies of oil field development for enhanced oil recovery

“…In addition the measures of reperforation, well conversion, sidetrack drilling, infill production drilling, the recommended strategy suggested an initial injection-production ratio of 2.0 that followed by a reduced ratio of 1.0 and a 60% gas recycling at X-8. The authors would like to suggest the application of machine learning [19,20] and two other people's paper about fluid saturation+machine learning (that you can find online) for better understanding integrating all the aforementioned measures and taking into consideration the sensitivity analysis results. Table 13 lists the simulated results of the whole field from the recommended plan, while tab.…”

Evaluating the Effect of New Gas Solubility and Bubble Point Pressure Models on PVT Parameters and Optimizing Injected Gas Rate in Gas-Lift Dual Gradient Drilling

“…Besides, there are still many unknown aspects of applying the new interdisciplinary investigation techniques in assessing the gas solubility, bubble point pressure, bottom hole pressure or temperature, gas injection rate, etc., throughout dual gradient drilling or other deepwater drilling tasks. These techniques include fractal geometry theory [52][53][54][55], digital rock technology [56][57][58], one-dimensional [59][60][61][62] and two-dimensional nuclear magnetic resonance [63,64], numerical methods [65][66][67], artificial intelligence [68][69][70][71][72] especially the deep learning technique [73][74][75], which could be used individually or in a joint manner during well planning, design, engineering, operations, and technology application, etc. This wide range of topics is suggested as the potential areas of future research.…”

Controls on Reservoir Heterogeneity of a Shallow-Marine Reservoir in Sawan Gas Field, SE Pakistan: Implications for Reservoir Quality Prediction Using Acoustic Impedance Inversion

“…The proper and dependable estimation of low-impedance gas-bearing zones, estimation of reservoir parameters, and reservoir thickness calculation at sparse well locations in the Sawan gas field (SGF) is still a substantial task [26], and vast hydrocarbon potential remained unexplored [27]. In addition, numerous wells drilled thereabouts are declared dry or have been abandoned [28].…”

“…[33] applied the post-stack inversion methods to explain the resource potential of gas reservoirs in the south of Pakistan and nearby Indian subcontinent. Recent studies by [26,34] have utilized the acoustic impedance (AI) to estimate the various petrophysical parameters. However, the comprehensive study on the reservoir thickness (sand-ratio), discrimination of reservoir facies and their heterogeneities through qualitative and quantitative measurements and the factors that control the reservoir heterogeneity using the 3D seismic is still missing.…”