Exploration
Mohammed A.Amir; Hamzah S. Amir; Mokhtar Farkash
Abstract
Permeability estimation is an essential phase in assessing the hydrocarbon potential within porous media and designing reservoir management methods. Recently, machine learning (ML) methodologies have gained prominence in the prediction of permeability. The initial stage in constructing highly reliable ...
Read More
Permeability estimation is an essential phase in assessing the hydrocarbon potential within porous media and designing reservoir management methods. Recently, machine learning (ML) methodologies have gained prominence in the prediction of permeability. The initial stage in constructing highly reliable ML models is to identify the optimum combinations of input logs, as permeability is a highly sensitive parameter; this step is essential and can influence model accuracy. While feature engineering methods provide valuable insights in selecting suitable input logs, the effectiveness of these logs or their combinations remains underexplored, particularly in the context of high-heterogeneity reservoirs. The current study intends to save time by evaluating the effectiveness of twelve distinct models, each constructed using a Multi-Layer Perceptron (MLP), based on various combinations of input logs using data from the Nubian reservoir, Sirt Basin, Libya. The methodology involved several steps, including preprocessing, splitting, optimization, and validation. The findings demonstrate that single-input logs, mainly the Gamma-ray (GR), bulk density (RHOB), and sonic logs (DT), exhibited higher correlation coefficients compared to the multiple log combinations. The GR model attained the best R² of 0.994, indicating its sensitivity in capturing non-linear relationships. On the other hand, multi-log models achieved variable accuracy, resulting in increased learning complexity. The study highlights the efficiency of selecting the optimal combination of input logs, providing practical guidance for ML-based permeability prediction in heterogeneous reservoirs.
Exploration
Sina Samadi; Peyman Afzal; Mehran Arian; Ali Solgi; Zahra Maleki; Mohammad Seraj
Abstract
An important work for fractured reservoir modeling and development of oilfields is the delineation of geomechanical attributes such as permeability. The main aim of this research work is detection of permeability zones in the Asmari reservoir of Gachsaran oilfield (SW Iran) based on mud loss data. The ...
Read More
An important work for fractured reservoir modeling and development of oilfields is the delineation of geomechanical attributes such as permeability. The main aim of this research work is detection of permeability zones in the Asmari reservoir of Gachsaran oilfield (SW Iran) based on mud loss data. The mud loss was 3D estimated by ordinary kriging method. Then, fractal number-size, concentration-volume, and concentration-distance to fault models were applied for permeability zone classification. The concentration-distance to fault fractal model shows three permeability zones, and the concentration-volume fractal modeling represents eight zones with an index multifractal behavior. Moreover, the number-size fractal analysis presented that a multifractal behavior with five societies. The correlation between the results obtained by these fractal methods reveals that the obtained zones have a proper overlap together. High value permeability zones based on the concentration-distance to fault and concentration-volume fractal models are began from 501 Barrel Per Day (BPD) mud loss, and 630 BPD obtained by the N-S modeling. Fractal modeling indicates that the permeability zones occur in the SW, NW and southern parts of the Gachsaran oilfield which can be the fractured section of the Asmari reservoir rock. Main faults from this oilfield are correlated with the permeability zones derived via fractal modeling.
A. Abdollahipour; M. Fatehi Marji; H. Soltanian; E. A. Kazemzadeh
Abstract
The permeability and coupled behavior of pore pressure and deformations play an important role in hydraulic fracturing (HF) modeling. In this work, a poroelastic displacement discontinuity method is used to study the permeability effect on the HF development in various formation permeabilities. The numerical ...
Read More
The permeability and coupled behavior of pore pressure and deformations play an important role in hydraulic fracturing (HF) modeling. In this work, a poroelastic displacement discontinuity method is used to study the permeability effect on the HF development in various formation permeabilities. The numerical method is verified by the existing analytical and experimental data. Then the propagation of a hydraulic fracture in a formation with a range of permeabilities is studied. The time required for propagation of an HF to 10 times its initial length is used to compare the propagation velocity in the formations with different permeabilities. The results obtained show that the HF propagation can be significantly delayed by a permeability less than almost 10-9 D. Also the effect of HF spacing on the propagation path is studied. It was shown that the stress shadowing effect of HFs remained for a longer spacing than in the elastic model due to the required time for fluid leak-off in the formation. Also the propagation angles are higher in the poroelastic model predictions than the elastic model. Therefore, it is proposed to use the poroelastic model when studying multi-HF propagation in order to avoid errors caused by neglecting the pore fluid effects on the HF propagation paths.
R. Gholami; A. Moradzadeh
Abstract
Reservoir permeability is a critical parameter for characterization of the hydrocarbon reservoirs. In fact, determination of permeability is a crucial task in reserve estimation, production and development. Traditional methods for permeability prediction are well log and core data analysis which are ...
Read More
Reservoir permeability is a critical parameter for characterization of the hydrocarbon reservoirs. In fact, determination of permeability is a crucial task in reserve estimation, production and development. Traditional methods for permeability prediction are well log and core data analysis which are very expensive and time-consuming. Well log data is an alternative approach for prediction of permeability because they are usually available for all of the wells. Hence, attempts have been made to utilize well log data to predict permeability. However, because of complicate and non-linear relationship of well log and core permeability data, usual statistical and artificial methods are not completely able to provide meaningful results. In this regard, recent works on artificial intelligence have led to the introduction of a robust method generally called support vector machine (SVM). The term “SVM” is divided into two subcategories: support vector classifier (SVC) and support vector regression (SVR). The aim of this paper is to use SVR for predicting the permeability of three gas wells in South Pars filed, Iran. The results show that the overall correlation coefficient (R) between predicted and measured permeability of SVR is 0.97 compared to 0.71 of a developed general regression neural network. In addition, the strength and efficiency of SVR was proved by less time-consuming and better root mean square error in training and testing dataset.
N. I. Aziz; I. Porter; F. Sereshki
Abstract
The volumetric changes in the coal matrix (Coal Shrinkage), permeability under various gas environment conditions as well as perographical properties were studied in the laboratory. The shrinkage and permeability of coal were examined with respect to changing gas type and confining pressures. The shrinkage ...
Read More
The volumetric changes in the coal matrix (Coal Shrinkage), permeability under various gas environment conditions as well as perographical properties were studied in the laboratory. The shrinkage and permeability of coal were examined with respect to changing gas type and confining pressures. The shrinkage tests were carried out in high-pressure bombs while the permeability study was conducted in a specially constructed high-pressure chamber. Methane (CH4), carbon dioxide (CO2), nitrogen, (N2) and a 50% -50% volume mixture of CO2/CH4 gas were used in the study. The tests showed that under different pressure levels gas type affected permeability and shrinkage characteristics of coal. This paper presents a case study of Tahmoor Colliery, NSW, Australia and an overall discussion on coal shrinkage, permeability and coal petrography data of Tahmoor that permits a better understanding of the gas regime in this mine. The results are important to the further understanding of the inter-relationship between gas flow, the coal matrix and permeability in ‘normal’ and ‘tight’ coal conditions (locally referred to as disturbed coal).
