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.
M. R. Shahverdiloo; Sh. Zare
Abstract
Hydraulic fracturing (HF) and hydraulic testing of pre-existing fractures (HTPF) are efficient hydraulic methods in order to determine the in-situ stress of rock mass. Generally, the minimum (Sh) and maximum (SH) horizontal principal stresses are measured by hydraulic methods; ...
Read More
Hydraulic fracturing (HF) and hydraulic testing of pre-existing fractures (HTPF) are efficient hydraulic methods in order to determine the in-situ stress of rock mass. Generally, the minimum (Sh) and maximum (SH) horizontal principal stresses are measured by hydraulic methods; the vertical stress (SV) is calculated by the weight of the overburden layers. In this work, 37 HF and HTPF tests are conducted in a meta-sandstone, which has about 10% inter-layer phyllite. The artesian circumstance, considerable gap between the drilling and hydraulic tests in the long borehole, no underground access tunnel to rock cavern at the early stages of projects, and a simplified hypothesis theory of HF are the main challenges and limitations of the HF/HTPF measurements. Due to the instability in the long borehole, the drill rig type and borehole length are revised; also TV logger is added to the process of selection of the test’s deep. The HF/HTPF data is sequentially analyzed by the classic and inversion methods in order to achieve an optimum number of hydraulic tests. Besides, The SH magnitude in the inversion method is lower than the classic method; the relevant geological data and the faulting plan analysis lead to validate the SH and Sh magnitudes and the azimuths obtained by the classic method. The measured SH and Sh magnitudes are 7-17 MPa and 4-11 MPa, respectively; the calculated vertical stress magnitude is 6-14 MPa at the test locations. Indeed, the stress state is (SH > SV > Sh), and SH azimuth range is 56-93 degrees.
