A novel workflow based on physics-informed machine learning to determine the permeability profile of fractured coal seams using downhole geophysical logs

Published on Sep 1, 2021in Marine and Petroleum Geology4.348
· DOI :10.1016/J.MARPETGEO.2021.105171
Abstract null null Permeability is arguably the most important parameter in gas pre-drainage and production practices in coal mining and coal seam gas industries. In fractured coal seams, permeability can significantly vary both laterally and vertically. Knowing the vertical variation of permeability in relatively thick coal seams is important in optimizing inseam pre-drainage design in underground coal mining and improving reservoir management and completion design efficiency in the coal seam gas industry. Existing empirical/statistical coal permeability models often yield poor results in estimating permeability profiles where there is significant variation in the characteristics of coal fracture systems. This study presents a novel workflow for evaluating the permeability profile of naturally fractured thick coal seams using downhole geophysical logging data. The workflow combines physics-based simulation, laboratory experiments, and a data-driven machine learning approach for estimating the permeability profile. As part of this workflow, several coal specimens from the study coal seam are first tested under different stresses to measure their permeability, density, and ultrasonic responses. Numerical simulation of the Navier-Stokes fluid flow and elastic wave propagation was then performed on a range of constructed coal block geometries with various fracture densities. In the next step, a physics-informed, neural network-based model (PINN) was trained using the data obtained from both laboratory experiments and numerical simulation. The model inputs included density, as well as compressional and shear wave velocities of the coal seam and its output is the trend of permeability variation across the coal seam interval. In-situ permeability measurement at a certain depth (e.g., from well pressure testing) was then used to convert the permeability trend to the entire permeability profile of the coal seam along its interval. The performance of the proposed workflow was finally evaluated using a suite of downhole geophysical logging data from a borehole intersecting two coal seams in an eastern Australian basin. This study demonstrates that the proposed workflow is relatively simple to implement and yet accurate for evaluating the permeability profile of a coal seam across its interval.
#1Muhammad Ali (China University of Geosciences (Wuhan))H-Index: 5
#2Ren Jiang (PetroChina)H-Index: 2
Last. Jar Ullah (China University of Geosciences (Wuhan))H-Index: 2
view all 7 authors...
Abstract This study proposes a novel approach to predict missing shear sonic log responses more precisely and accurately using similarity patterns of various wells with similar geophysical properties, which is important in decision making and planning of hydrocarbon exploration. Deep Neural Network (DNN) along with the similarity metrics such as Jaccard and Overlap similarities are employed to examine the relationship between the wells. Further, dimensionality reduction techniques including Mult...
#1Adelina Lv (UNSW: University of New South Wales)H-Index: 4
#2Mohammad Ali Aghighi (UNSW: University of New South Wales)H-Index: 9
Last. Hamid Roshan (UNSW: University of New South Wales)H-Index: 24
view all 4 authors...
The effective stress coefficient (ESC) is a key parameter in the linear poroelastic effective stress formulation. In fluid-bearing porous media, the effective stress is the difference between total stress and a fraction of the pore fluid pressure controlled by the ESC. The ESC is either measured in the laboratory or estimated by empirical models using field data. Among different techniques, sonic velocity measurements are widely used to estimate the ESC. The structure of coal, however, has some ...
#1Mohammad Ali Aghighi (UNSW: University of New South Wales)H-Index: 9
#2Adelina Lv (UNSW: University of New South Wales)H-Index: 4
Last. Hamid Roshan (UNSW: University of New South Wales)H-Index: 24
view all 3 authors...
Abstract Modelling gas flow in sorptive porous materials (e.g. coal) offers significant challenges compared to that of non-sorptive porous media (e.g. conventional hydrocarbon reservoirs). Sorption processes in the matrix, gas flow in the fractures (cleats) and induced strains in the bulk of coal interact in a coupled manner, affecting the sorption, mechanical and hydraulic characteristics of the media. Despite extensive research on constitutive models that take into account the coupling process...
#1Yumao Pang (SDUST: Shandong University of Science and Technology)H-Index: 2
#3Xingwei GuoH-Index: 8
Abstract The South Yellow Sea Basin (SYSB) is an area for oil and gas exploration in eastern China. The previous geological studies were mainly about the Mesozoic–Cenozoic strata, but no commercial hydrocarbon resource has been discovered up to now. This study focuses on the Silurian–Lower Triassic source-reservoir relationships and hydrocarbon charging history in the Central Uplift of the SYSB using the first scientific drilling well (CSDP-2). The well is drilled through the Paleozoic–Mesozoic ...
#1A. D. MorozovH-Index: 2
#2D. PopkovH-Index: 2
Last. G. V. PaderinH-Index: 3
view all 9 authors...
Summary Increasing amount of hydraulic fracturing (HF) jobs in the recent two decades brought in a significant amount of measured data available for development of predictive models via machine learning (ML). In multistage fractured completions, post-fracturing production reveals evidence that different stages produce very non-uniformly, and up to 30% may not be producing at all due to a combination of geomechanics and fracturing design factors. Therefore, there is a significant room for fractur...
#1Cyrus Salehi (UQ: University of Queensland)H-Index: 1
#2Ruizhi Zhong (UQ: University of Queensland)H-Index: 11
Last. Raymond L. Johnson (UQ: University of Queensland)H-Index: 15
view all 6 authors...
Bulk permeability of coal is a critical parameter in coalbed methane (CBM) or coal seam gas (CSG) well completion designs and field development planning. The estimation of permeability can be made by well testing either during drilling or production; however, well tests are costly, time sensitive and resource-intensive. Therefore, field-wide estimates are often dependent on production data history-matching, which has a high degree of uncertainty.In this paper, we present a new attempt to apply m...
#1Mathieu DucrosH-Index: 6
#2Fadi H. Nader (French Institute of Petroleum)H-Index: 16
Abstract The Levant Basin of the East-Mediterranean region contains a biogenic petroleum system and possibly an underlying thermogenic system. The application of a new map-based uncertainty and sensitivity analysis that integrates a large set of geological parameters demonstrates that a connection between an Upper Cretaceous thermogenic petroleum system and the shallower Oligo-Miocene reservoirs is highly possible in the southern part of the basin (offshore Israel and southern Lebanon) where hyd...
#1Hao LiH-Index: 1
#1Kaibo Zhou (HUST: Huazhong University of Science and Technology)H-Index: 6
#2Yangxiang Hu (HUST: Huazhong University of Science and Technology)H-Index: 2
Last. Tao ChenH-Index: 1
view all 7 authors...
Permeability estimation plays an important role in reservoir evaluation, hydrocarbon development, etc. Traditional methods have problems of time consuming and high cost. At present, the application of machine learning methods are more and more extensive, however, some machine learning models developed for permeability have fewer samples, requiring prior knowledge, and some parameters need to be calculated indirectly. To this end, based on a certain scale of permeability dataset, a hybrid method ...
#1Zhiguo Wang (Xi'an Jiaotong University)H-Index: 8
Abstract We propose a machine learning-based seismic spectral attribute (SSA) analysis to delineate the thickness of a tight-sand reservoir in the Sulige gas field of central Ordos Basin, western China. In our workflow, we first implement the seismic spectral decomposition by using the continuous wavelet transform (CWT) with the generalized Morse wavelets (GMWs). The best parameters of generalized Morse wavelets (GMWs) are obtained by using a geological model of the tight reservoir. Second, we e...
Cited By1
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.