1-20 of 2924
Keywords: algorithm
Close
Sort by
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3908599
... operator in a 3D coordinate system. The operator is introduced into the objective function with the Hadamard operator and avoids rearranging the seismic traces. Then, a fast optimization algorithm is developed to minimize the objective function. Acoustic impedance inversion on Overthrust model and field...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3905277
... inversion exploration geophysicist probability geological subdiscipline characterization facies porosity international applied geoscience algorithm figure Improved carbonate reservoir characterization using formation density derived from pre-stack simultaneous inversion: a case study in West...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3907951
... analysis geology artificial intelligence machine learning geologist asia government well logging algorithm machine learning method coefficient american association classification inversion prediction applied geoscience reservoir characterization tubular pore reservoir evaluation...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3904696
... Uncertainty quantification (UQ) is crucial for seismic full waveform inversion (FWI), which is a highly ill-posed inverse problem. In the framework of Bayesian inference, we propose to use an adaptive Markov chain Monte Carlo (MCMC) sampling algorithm to quantify the uncertainties of FWI...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3907458
... develop a stochastic inversion algorithm to characterize hydraulic fracture dimensions and quantify the associated uncertainties using cross-well distributed fiber-optic strain measurements. Strain modeling is accomplished by employing a 3D displacement discontinuity method based geomechanical model...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3904704
... the logging curves to perform SGS. Then the simulation results are used as the initial model, and the Monte Carlo-Markov Chain (MCMC) algorithm is used to randomly perturb and optimize it. Under the Bayesian framework, the seismic data are used as the constraints of the objective function in the inversion...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3907517
... government algorithm sacchi international society geophysics seismic exploration ieee transaction energy 10 trajectory Multicomponent seismic data vector reconstruction via quaternionic matrix factorization Yonghai Fu, China University of Geosciences(Beijing), Jianjun Gao, China University...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3907527
... inversion accuracy wang chengxiang energy 10 tao chunfeng modeling impedance inversion society algorithm Label-defect tolerance ability of deep learning inversion networks and its applications Yang Ping*1 Xu Hunqun2 Liu Di1 Tao Chunfeng1 Wang Chengxiang1 Yue Changqing1 1 BGP, CNPC; 2. College...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-W03-01
... property have been tackled with this technology. Our industry has large datasets that are especially suitable for data-driven methods. However, ML algorithms have been labeled as a “black box” as the actual process is not evident to the end user. Furthermore, the uncertainty of the results is always...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-W12-01
... A Python-Excel ML Toolkit was developed which enables grassroots digital transformation by implementing ML tools in Excel’s familiar environment without users needing to code in Python. This was done by linking multivariate machine learning (ML) algorithms coded in Python to the Excel...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3913547
... the subsurface geometry by identifying formation rocks and geostructure, training formation materials properties with patterns. The formation pore pressure and in-situ stresses, dominated by the burial history of compaction, are learned using hybrid algorithms. This digital model is capable of continuous...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3916072
... constraint exploration geophysicist geophysics calculation summary algorithm Semi-supervised learning with knowledge embedding for horizon volumes calculation Rui Guo*, He Lin, Maoshan Chen, Chunfeng Tao, Yingnan Gao, Ruochong Wen. BGP, CNPC. Summary Different from purely data-driven supervised deep...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3916315
... The success of deep learning algorithms is contingent on sufficient, accurate training data to learn accurate mathematical representations of data points and mirror the interpretation process. Unfortunately, scarce training sets are common in seismic interpretation and the algorithm performance...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3917287
... that users can work interactively with whole groups that span the entire survey, rather than with individual picks. This allows the user to stay in control of the outcome, while delegating much of the tedious labor to the UML algorithm. artificial intelligence projection processor geologist...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3917108
... Microseismic monitoring entails denoising of continuous long-duration time series, followed by event picking. Typically, both processes require different set of algorithms and analysis. We propose a machine learning approach that simultaneously denoises seismic records and picks phase attributes...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3909092
... geoscience society correction upstream oil & gas reservoir characterization exploration geophysicist energy 10 inversion annual international conference algorithm tomography le stunff pp-ps tomography registration displacement exhibition S-wave velocity model building using PP-PS...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3909950
... uncertainties to γ, ϵ, δ , and associated uncertainties. The developed uncertainty algorithm yields an estimation on the lower and upper bounds of γ, ϵ, δ , that bracket the true answers. The synthetic tests indicate that γ can be resolved when mud slowness is correctly determined. There is minor...
Proceedings Papers

Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, August 27–September 1, 2023
Paper Number: SEG-2023-3909329
..., hindered the widespread adoption of acceptance-rejection algorithms, such as those from the family of Monte-Carlo Markov Chain methods. We present a flexible approach to probabilistic sampling that leverages the ability of denoising neural networks to provide direct access to the gradient of the log...

Product(s) added to cart

Close Modal