Not enough data to create a plot.
Try a different view from the menu above.
machine learning
The numerical solution of wave equations plays a crucial role in computational geophysics problems, which forms the foundation of inverse problems and directly impact the high-precision imaging results of earth models. However, common numerical methods often lead to signifcant computational and storage requirements. Due to the heavy reliance on forward modeling methods in inversion techniques, particularly full waveform inversion, enhancing the computational efficiency and reducing storage demands of traditional numerical methods becomes a key issue in computational geophysics. In this paper, we present the deep Lax-Wendroff correction method (DeepLWC), a deep learning-based numerical format for solving two#xD; dimensional (2D) hyperbolic wave equations. DeepLWC combines the advantages of the traditional numerical schemes with a deep neural network. We provide a detailed comparison of this method with representative traditional Lax-Wendroff correction (LWC) method. Our numerical results indicate that the DeepLWC signifcantly improves calculation speed (by more than ten times) and reduces storage space by over 10000 times compared to traditional numerical methods. In contrast to the more popular Physics Informed Neural Network (PINN) method, DeepLWC maximizes the advantages of traditional mathematical methods in solving PDEs and employs a new sampling approach, leading to improved accuracy and faster computations. It is particularly worth pointing that, DeepLWC introduces a novel research paradigm for numerical equation-solving, which can be combined with various traditional numerical methods, enabling acceleration and reduction in storage requirements of conventional approaches.
During geophysical exploration, inpainting defective logging images caused by mismatches between logging tools and borehole sizes can affect fracture and hole identification, petrographic analysis and stratigraphic studies. However, existing methods do not describe stratigraphic continuity enough. Also, they ignore the completeness of characterization in terms of fractures, gravel structures, and fine-grained textures in the logging images. To address these issues, we propose a deep learning method for inpainting stratigraphic features. First, to enhance the continuity of image inpainting, we build a generative adversarial network (GAN) and train it on numerous natural images to extract relevant features that guide the recovery of continuity characteristics. Second, to ensure complete structural and textural features are found in geological formations, we introduce a feature-extraction-fusion module with a co-occurrence mechanism consisting of channel attention(CA) and self-attention(SA). CA improves texture effects by adaptively adjusting control parameters based on highly correlated prior features from electrical logging images. SA captures long-range contextual associations across pre-inpainted gaps to improve completeness in fractures and gravels structure representation. The proposed method has been tested on various borehole images demonstrating its reliability and robustness.
- Geology > Geological Subdiscipline > Stratigraphy (0.74)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock (0.46)
- Geophysics > Seismic Surveying > Borehole Seismic Surveying (1.00)
- Geophysics > Borehole Geophysics (1.00)
- Reservoir Description and Dynamics > Reservoir Characterization > Exploration, development, structural geology (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Open hole/cased hole log analysis (1.00)
- Production and Well Operations > Well & Reservoir Surveillance and Monitoring > Borehole imaging and wellbore seismic (1.00)
- (2 more...)
Adeshina Badejo is a petroleum engineering PhD student at Texas A&M University under the Texas A&M at Qatar Strategic Research Initiatives Program. He has a strong interest in reducing the environmental impact of the continued use of fossil fuels. His research focuses on flow assurance challenges of the CO2 value chain from the extraction point to the subsurface injectivity point with the integration of machine learning. Badejo has been actively involved with SPE since 2016 as a volunteer. He led the Heriot-Watt University PetroBowl team to the regional qualifiers in Zagreb, Croatia, and received the 2023 SPE Aberdeen Section Student Bursary Award. He also served as the 2018โ2019 SPE Programs Chairperson during his undergraduate studies and co-initiated the inaugural edition of The Industry Discourse, a student-led energy conference. He holds a masterโs degree in subsurface energy systems from Heriot-Watt University, Edinburgh and a bachelorโs degree in petroleum and gas engineering from the University of Lagos, Nigeria.
- North America > United States > Texas (0.56)
- Europe > Croatia > Zagreb County > Zagreb (0.30)
- Africa > Nigeria > Lagos State > Lagos (0.30)
- Energy > Oil & Gas > Upstream (1.00)
- Education > Educational Setting > Higher Education (0.92)
Investigating the causes of permeability anisotropy in heterogeneous conglomeratic sandstone using multiscale digital rock
Chi, Peng (China University of Petroleum (East China), China University of Petroleum (East China)) | Sun, Jianmeng (China University of Petroleum (East China), China University of Petroleum (East China)) | Yan, Weichao (Ocean University of China, Ocean University of China) | Luo, Xin (China University of Petroleum (East China), China University of Petroleum (East China)) | Ping, Feng (Southern University of Science and Technology)
Heterogeneous conglomeratic sandstone exhibits anisotropic physical properties, rendering a comprehensive analysis of its physical processes challenging with experimental measurements. Digital rock technology provides a visual and intuitive analysis of the microphysical processes in rocks, thereby aiding in scientific inquiry. Nevertheless, the multiscale characteristics of conglomeratic sandstone cannot be fully captured by a single-scale digital rock, thus limiting its ability to characterize the pore structure. Our work introduces a proposed workflow that employs multiscale digital rock fusion to investigate permeability anisotropy in heterogeneous rock. We utilize a cycle-consistent generative adversarial network (CycleGAN) to fuse CT scans data of different resolutions, creating a large-scale, high-precision digital rock that comprehensively represents the conglomeratic sandstone pore structure. Subsequently, the digital rock is partitioned into multiple blocks, and the permeability of each block is simulated using a pore network. Finally, the total permeability of the sample is calculated by conducting an upscaling numerical simulation using the Darcy-Stokes equation. This process facilitates the analysis of the pore structure in conglomeratic sandstone and provides a step-by-step solution for permeability. From a multiscale perspective, this approach reveals that the anisotropy of permeability in conglomeratic sandstone stems from the layered distribution of grain sizes and differences in grain arrangement across different directions.
- Europe > Norway > North Sea > Central North Sea > Utsira High > PL 338 > Block 16/1 > Edvard Grieg Field > ร sgard Formation (0.99)
- Europe > Norway > North Sea > Central North Sea > Utsira High > PL 338 > Block 16/1 > Edvard Grieg Field > Skagerrak Formation (0.99)
- Europe > Norway > North Sea > Central North Sea > Utsira High > PL 338 > Block 16/1 > Edvard Grieg Field > Hegre Formation (0.99)
- (3 more...)
Xinming Wu joined the USTC (University of Science and Technology of China) as a professor in 2019, where he started the Computational Interpretation Group (CIG). Xinming received an engineering degree (2009) in geophysics from Central South University, an M.Sc. From 2016 to 2019, he was a postdoctoral fellow working with Sergey Fomel at Bureau of Economic Geology, The University of Texas at Austin. Xinming received the J. Clarence Karcher Award from the Society of Exploration Geophysics (SEG) in 2020 and was selected to be the 2020 SEG Honorary Lecturer, South and East Asia. He also received the Shanghai excellent master thesis award in 2013 (Generating 3D seismic Wheeler volumes: methods and applications).[1].
- North America > United States > Texas > Travis County > Austin (0.25)
- Asia > China > Shanghai > Shanghai (0.25)
- Geophysics > Seismic Surveying > Seismic Processing (0.56)
- Geophysics > Seismic Surveying > Seismic Interpretation (0.37)
Tim presents a framework for autonomous, real-time electrical imaging. He also shares two case studies of the framework in action and potential areas of development for this work. This forward-looking conversation utilizes machine learning and the latest electrical geophysical instrumentation to highlight what the future can be for hydrogeophysics.
- Information Technology > Communications > Mobile (0.40)
- Information Technology > Artificial Intelligence > Machine Learning (0.38)
Arnab Dhara discusses his paper, "Physics-guided deep autoencoder to overcome the need for a starting model in full-waveform inversion," in the June issue of The Leading Edge. Arnab proposes employing deep learning as a regularization in full-waveform inversion. He explains why physics-based solutions with machine learning are challenging to develop, how he made it possible to train the network without known answers, and why he tested his approach with the Marmousi and SEAM models. Arnab also shares why this research took over 20 years to build on the initial idea and how he used full-waveform inversion without a starting model. This is a cutting-edge conversation that may represent the future of FWI.
Laura Bandura advises on strategy and performance improvement opportunities across the value chain within the Chevron Gulf of Mexico Business Unit. Laura has had a diverse career in her nine years at Chevron pioneering applications of machine learning to seismic imaging and interpretation, and cross-functional digital portfolio management. Prior to Chevron, Laura was a physicist at Argonne National Lab and the Facility for Rare Isotope Beams (FRIB) at Michigan State University, specializing in charged particle beam dynamics with applications to nuclear physics. She co-designed the fragment separator at FRIB, which is used to isolate and discover new isotopes. Laura has published research articles and patented inventions across a variety of fields, including geophysics, machine learning, nuclear science, and charged particle beam dynamics.
Sergey Fomel is Wallace E. Pratt Professor of Geophysics at The University of Texas at Austin and the Director of the Texas Consortium for Computational Seismology (TCCS). At UT Austin, he is affiliated with the Bureau of Economic Geology, the Department of Geological Sciences, and the Oden Institute for Computational Engineering and Sciences. Sergey received a PhD in Geophysics from Stanford University in 2001. Previously, he worked at the Institute of Geophysics in Russia (currently Trofimuk Institute of Petroleum Geology and Geophysics), Schlumberger Geco-Prakla, and the Lawrence Berkeley National Laboratory. For his contributions to exploration geophysics, he has been recognized with a number of professional awards, including the J. Clarence Karcher Award from SEG in 2001, Best SEG Poster Presentation Awards in 2007 and 2011, and the Conrad Schlumberger Award from EAGE in 2011.
- Asia (0.51)
- North America > United States > Texas > Travis County > Austin (0.26)
- Geophysics > Seismic Surveying > Seismic Processing (0.73)
- Geophysics > Seismic Surveying > Seismic Modeling > Velocity Modeling (0.31)
Fabien Allo highlights his award-winning article, "Characterization of a carbonate geothermal reservoir using rock-physics-guided deep neural networks." Fabien shares the potential of deep neural networks (DNNs) in integrating seismic data for reservoir characterization. He explains why DNNs have yet to be widely utilized in the energy industry and why utilizing a training set was key to this study. Fabien also details why they did not include any original wells in the final training set and the advantages of neural networks over seismic inversion. This episode is an exciting opportunity to hear directly from an award-winning author on some of today's most cutting-edge geophysics tools.