Advances in Engineering Advances in Engineering features breaking research judged by Advances in Engineering advisory team to be of key importance in the Engineering field. Papers are selected from over 10,000 published each week from most peer reviewed journals.
(in the Sulige gas field of central Ordos Basin, western China)
Significance
The Sulige gas field in central Ordos Basin is the largest gas field in China. The first exploratory well produced natural gas from a tight sandstone reservoir, namely the P1h8 reservoir. In the early phase of the project, 2D seismic lines were acquired to determine the gas potential. However, since 2010, 3D seismic surveys have been acquired in the Sulige gas field to better characterize reservoir heterogeneity and to optimize the placement of the expensive horizontal well. At present, horizontal wells yield more gas when compared to their vertical counterparts. Nonetheless, the number of horizontal wells is much smaller than that of vertical wells. To further enhance gas production, more horizontal wells ought to be drilled. Moreover, since massive sands at the braid bars are the potential targets for horizontal wells, it is important to better map and predict the distribution of economically viable tight sandstones throughout the field. In light of this, many high-quality 3D seismic approaches have been presented. For instance, previous reports have explored approaches such as the short time Fourier transform, continuous wavelet transform, and matching pursuit decomposition. Regardless, more is needed to delineate the subsurface depositional facies and reservoir thicknesses.
Considering the linear or nonlinear correlation between seismic spectral attribute (SSAs) and sand thickness in the Sulige gas field, one can postulate that a combination of both multiple linear regression (MLR) and radial basis function neural network (RBFNN) could yield a better optimal regression model. Bearing this in mind, researchers from the National Engineering Laboratory for Offshore Oil Exploration in China: Professor Zhiguo Wang and Professor Jinghuai Gao, in collaboration with Professor Dengliang Gao at the West Virginia University in the United States and Dr. Xiaolan Lei, and Professor Daxing Wang at the CNPC Changqing Oilfield Company (China) exploited the advantages of the combined MLR and RBFNN by applying a machine learning-based spectral attribute analysis to assist 3D seismic interpretation in tight gas reservoirs in the Sulige field, Ordos Basin, western China. Their work is currently published in the research journal, Marine and Petroleum Geology.
In their workflow, they first implemented the seismic spectral decomposition by using the continuous wavelet transform with the generalized Morse wavelets. Second, they extracted SSAs of the target reservoir of interest following which they performed multi-dimensional data analysis using the principal component analysis, thus significantly reducing the computational time and storage space for SSAs analysis and visualization. In addition, through the use of red-green-blue (RGB) blending technique, the team proceeded to make a high-resolution subsurface depositional facies map from the reduced three principal components from the original multi-dimensional SSAs.
The research team reported that validation analysis of the 9 blind test wells revealed that the increased heterogeneity association with seismic facies changed and the lack of training wells could lead to false thickness predictions. Moreover, based on a geological model of the P1h8 reservoir, the correlation between spectral attributes and thickness of sands were found.
In summary, the study used mediocre-quality 3D seismic data, upon which they successfully applied a spectral attribute analysis workflow by using the continuous wavelet transform with generalized Morse wavelets and artificial neural network to improve the delineation of sandstones in the Lower Permian Xiashihezi Formation, Ordos Basin, China. Remarkably, the results obtained illustrated significant variation in reservoir thickness across the field, which can be useful for evaluating reservoir heterogeneity and connectivity. In a statement to Advances in Engineering, the authors highlighted that their machine-aided multi-dimensional SSAs analysis could be useful for play screening in the reconnaissance phase, prospect generation and maturation in the exploration phase, and well placement in the development phase.
Reference
Zhiguo Wang, Dengliang Gao, Xiaolan Lei, Daxing Wang, Jinghuai Gao. Machine learning-based seismic spectral attribute analysis to delineate a tight-sand reservoir in the Sulige gas field of central Ordos Basin, western China. Marine and Petroleum Geology, volume 113 (2020) 104136.
