Improved reservoir characterization of thin beds by advanced deep learning approach

• Published in: Applied computing and geosciences Vol. 23; p. 100188
• Main Authors: Manzoor, Umar, Ehsan, Muhsan, Hussain, Muyyassar, Bashir, Yasir
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.09.2024; Elsevier
• Subjects: Continuous wavelet transform; Deep learning; Deep neural network; Geological facies; High-frequency; Limited resolution; Reservoir characterization; Seismic attributes; Seismic data; Thin beds; Deep learning; Limited resolution; Deep neural network; Geological facies; Seismic attributes; Continuous wavelet transform; Reservoir characterization; Thin beds; High-frequency; Seismic data
• ISSN: 2590-1974; 2590-1974
• DOI: 10.1016/j.acags.2024.100188

Targeting reservoirs below seismic resolution presents a major challenge in reservoir characterization. High-resolution seismic data is critical for imaging the thin gas-bearing Khadro sand facies in several fields within the Lower Indus Basin (LIB). To truly characterize thin beds below tuning thickness, we showcase an optimally developed deep learning technique that can save up to 75% turn-around time while significantly reducing cost. Our workflow generates high-frequency acoustic impedance synthetics by utilizing a deep neural network (DNN) at the reservoir level vis-a-vis validating the results with existing geological facies. Simultaneously, we introduce continuous wavelet transform (CWT); wherein the three components (real, imaginary, and magnitude) are interrelated to obtain a resultant high-frequency seismic volume. A strong agreement is established at available wells to achieve a higher resolution seismic by injecting higher frequencies, which is then populated throughout the 3D cube. An excellent correlation is met with key seismic attributes extracted across the field for original and CWT-based synthetic seismic. The augmented seismic volume with enhanced frequency range substantiates the dominant frequency (Fd) and resolves thin beds, which is also validated with the help of wedge modeling of both acquired and high-frequency datasets. As a geologically valid solution, our approach effectively resolves an initially 54 m bed to ∼25 m. This deep-learning methodology is ideally suited to regions where the acquired seismic has limited resolution and lacks advanced reservoir characterization. [Display omitted] •Deep learning for thin bed characterization: Developed DL technique utilizes deep neural network to generate high-frequency acoustic impedance synthetics for characterizing thin beds below seismic resolution.•Continuous wavelet transform (CWT): CWT is introduced to obtain high-frequency seismic volume by interrelating the three components (real, imaginary, and magnitude).•Improved resolution and validation: Higher resolution seismic is achieved by injecting higher frequencies and is validated with existing geological facies. Excellent correlation is met with key seismic attributes extracted across the field.•Resolving thin beds: Augmented seismic volume with enhanced frequency range effectively resolves thin beds, substantiates the dominant frequency, and is validated with wedge modeling. The approach is ideally suited for regions with limited resolution seismic data and lacking advanced reservoir characterization.