Garuda - Garba Rujukan Digital

Hydraulic Conductivity Modeling of Fractured Rock at Grasberg Surface Mine, Papua-Indonesia Cahyadi, Tedy Agung; Widodo, Lilik Eko; Syihab, Zuher; Notosiswoyo, Sudarto; Widijanto, Eman
Journal of Engineering and Technological Sciences Vol 49, No 1 (2017)
Publisher : ITB Journal Publisher, LPPM ITB

Packer tests and slug tests were conducted at 49 points at the Grasberg surface mine, Indonesia to obtain hydraulic conductivity data. The HC-system approach, which relies on rock quality designation, lithology permeability index, depth index, and gouge content designation, was applied. Geotechnical drill holes in 441 locations, consisting of 4,850 points of information, were used to determine the K values using the equation K = 2x10-6x HC0.5571. The K values, which were within the range of 10-8 and 10-5 m/s, were distributed into five alternative 3D distributions using Ordinary Kriging (OK) and Artificial Neural Network (ANN). The result of the ANN modeling showed that some of the K values, with log K varying from -10.51 m/s to -3.09 m/s, were outside the range of the observed K values. The OK modeling results of K values, with log K varying from -8.12 m/s to -5.75 m/s, were within the range of the observed K values. The ANN modeled K values were slightly more varied than the OK modeled values. The result of an alternative OK modeling was chosen to represent the existing data population of flow media because it fits well to the geological conditions.

Hydraulic Conductivity Modeling of Fractured Rock at Grasberg Surface Mine, Papua-Indonesia Tedy Agung Cahyadi; Lilik Eko Widodo; Zuher Syihab; Sudarto Notosiswoyo; Eman Widijanto
Journal of Engineering and Technological Sciences Vol. 49 No. 1 (2017)
Publisher : Institute for Research and Community Services, Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/j.eng.technol.sci.2017.49.1.3

Packer tests and slug tests were conducted at 49 points at the Grasberg surface mine, Indonesia to obtain hydraulic conductivity data. The HC-system approach, which relies on rock quality designation, lithology permeability index, depth index, and gouge content designation, was applied. Geotechnical drill holes in 441 locations, consisting of 4,850 points of information, were used to determine the K values using the equation K = 2x10-6x HC0.5571. The K values, which were within the range of 10-8 and 10-5 m/s, were distributed into five alternative 3D distributions using Ordinary Kriging (OK) and Artificial Neural Network (ANN). The result of the ANN modeling showed that some of the K values, with log K varying from -10.51 m/s to -3.09 m/s, were outside the range of the observed K values. The OK modeling results of K values, with log K varying from -8.12 m/s to -5.75 m/s, were within the range of the observed K values. The ANN modeled K values were slightly more varied than the OK modeled values. The result of an alternative OK modeling was chosen to represent the existing data population of flow media because it fits well to the geological conditions.

Backpropagation neural networks for solving gas flow equations in porous media Adrianto, Adrianto; Syihab, Zuher; Sutopo, Sutopo; Marhaendrajana, Taufan
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 5: October 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i5.pp3744-3756

This study proposes a backpropagation neural network (BPNN) as an alternative solver for nonlinear equations in gas flow simulation through porous media. Conventional solvers like the Newton-Raphson (N-R) method are accurate but may become inefficient for large-scale or heterogeneous systems. We develop a feedforward BPNN architecture with adaptive learning rates to solve discretized residual equations from the one-dimensional gas flow model. The methodology includes finite difference discretization and mapping the nonlinear algebraic system into a four-layer neural network. The BPNN solver is validated against the Newton method across various grid sizes and heterogeneous permeability-porosity distributions. Results show that BPNN achieves high accuracy, with maximum absolute errors (MAE) of only 0.241 psi in the homogeneous model and 0.0418 psi in the heterogeneous model. While the BPNN requires more iterations and longer computation time, especially for finer grids, it exhibits the ability to learn pressure patterns and improve efficiency over time. This approach demonstrates that BPNN can serve as a viable nonlinear solver in reservoir simulation, offering flexibility in handling nonlinearities while maintaining accuracy.

Case Study of Heterogeneity Index’s Effect on The Successful Workover Based on The Apriori Algorithm Fahrizal Maulana; Amega Yasutra; Zuher Syihab
Scientific Contributions Oil and Gas Vol 48 No 1 (2025)
Publisher : Testing Center for Oil and Gas LEMIGAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29017/scog.v48i1.1658

The Indonesian government has set a target to reduce the consumption-production gap by increasing national oil production to 1 million barrels of oil per day (BOPD) and 12 billion standard cubic feet per day (BSCFD) of gas by 2030. Amongst several approaches, the optimization of mature fields offers a significant opportunity for quick production gains. However, analyzing these fields presents challenges due to the complexity, incompleteness, and poor quality of historical data. Heterogeneity Index (HI) is one of the methods that quickly measure well performance. This method is as simple as measuring a certain well as compared to the average performance at certain time. The parameter being used might vary, but production data is the most frequent one given its availability. Despite simple and practical, skepticism on the reliability of this method is still questionable. This work revisited "XYZ" field consisting of XX wells producing more than 32 years with hundreds of workovers. We brought evidences and insights on how HI leads to the workover success from. Apriori algorithm, an Association Rule Mining (ARM) technique, is employed to uncover rules from the noisy data. The results show that workover on wells with low HI mostly leads to success. Another insight is that of scale treatment is the most influential one in determining the success. Given these findings, the flow efficiency is the issue that should be well treated and HI is representative enough to measure this one.

A Hybrid Probabilistic-Backpropagation Neural Network Solver for Nonlinear Systems in Reservoir Simulation Adrianto; Zuher Syihab; Sutopo; Taufan Marhaendrajana
Scientific Contributions Oil and Gas Vol 48 No 3 (2025)
Publisher : Testing Center for Oil and Gas LEMIGAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29017/scog.v48i3.1751

Reservoir simulation requires solving large, sparse systems of nonlinear equations, where iterative Krylov subspace solvers such as the conjugate gradient (CG), stabilized conjugate gradient (BiCG-STAB), and generalized minimal residual (GMRES) are widely applied. However, these methods often have limitations in terms of their stability and accuracy in nonlinear systems. This paper introduces a hybrid probabilistic backpropagation neural network (Prob-BPNN) solver that integrates neural-network-based initialization with probabilistic inference to improve robustness. The solver was benchmarked against CG, BiCG-STAB, and GMRES using two synthetic reservoir models with the GMRES solution at a tolerance of 10-10, serving as the reference solution. The results show that Prob-BPNN consistently achieved production profiles closely matching the reference solution, with errors of MAE ≤ 0.066, RMSE ≤ 0.071, MAPE ≤ 2.04%, and R2 ≥ 0.945. In contrast, CG and BiCG-STAB produced unstable and nonphysical results, with errors exceeding 292% and negative R2 values. In terms of computational performance, Prob- BPNN required 9.96 s in Case 1 and 45.90 s in Case 2, compared to 2.85 s and 1.53 s for GMRES, respectively. Although more computationally expensive, Prob-BPNN delivered convergence on the same residual order of magnitude (below 10-3) as GMRES while avoiding the severe instabilities observed in CG and BiCG-STAB. These findings indicate that the Prob-BPNN is preferable in applications where solver robustness and accuracy are critical, even at the expense of a higher execution time. Future research should focus on reducing computational overhead through parallelization and hybridization strategies to enhance the scalability of large-scale reservoir models.

A Fully Implicit Reservoir Simulation Using Physics Informed Neural Network Agus Wahyudi; Tutuka Ariadji; Taufan Marhaendrajana; Kuntjoro Adji Sidarto; Zuher Syihab
Scientific Contributions Oil and Gas Vol 48 No 3 (2025)
Publisher : Testing Center for Oil and Gas LEMIGAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29017/scog.v48i3.1858

The accuracy of simulation of multiphase flow in porous media is critical for reservoir management but is hindered by the nonlinear, coupled nature of governing equations and truncation errors in mesh-based numerical solvers. This study introduces a mesh-free, fully implicit Physics-Informed Neural Networks (PINN) framework for two-phase immiscible oil–water flow, where feedforward neural networks simultaneously approximate continuous pressure and saturation fields, embedding the governing PDEs, boundary, and initial conditions directly into the loss function. Three network topologies of single-row (N1), dual-row (N2), and branched-layer (NY) were tested across nine configurations which include variants of the networks. The novelty lies in the fully implicit PINN formulation of branched networks architectures with capability to reduce interference between pressure and saturation predictions. Benchmarking against the commercial simulator (Eclipse©) showed the NY achieved the best performance, with a mean squared error of less then 1.0×10-10. The N1 showed the ability to maintain stability at successive timesteps, while N2 models converged more slowly. The deep and narrow networks yielded higher accuracy but required almost double computation per iteration. Results demonstrate that even though with higher computational cost, the proposed PINN-based approach delivers high-fidelity solutions for complex reservoir problems without spatial meshing, offering a promising alternative to common numerical methods for both regular and irregular geometries.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search