... reservoir characterization upstream oil & gas inverse problem geophysics algorithm lsrtm inversion iteration training sample artificial intelligence mauricio sacchi cgl algorithm exploration geophysicist 10 least-square reverse time migration reflectivity operator reconstruction u-net...

... In the last decade, seismic wavefield processing has begun to rely more heavily on the solution of wave-equation-based inverse problems. Especially when dealing with unfavourable data acquisition conditions (e.g., poor, regular or irregular sampling of sources and/or receivers), the underlying...

... learning upstream oil & gas herman reservoir simulation geophysical data ghent university exploration geophysicist 10 inverse problem geophysics water resource research artificial intelligence applied geoscience posterior distribution experiment singha prediction inversion Bayesian...

... Uncertainty quantification provides quantitative measures on the reliability of candidate solutions of ill-posed inverse problems. Due to their sequential nature, Monte Carlo sampling methods require large numbers of sampling steps for accurate Bayesian inference and are often computationally...

... and the Aki-Richards The forward operator of petrophysical AVO inversion is of equation. The relevant inverse problem is solved under the high nonlinearity and the relevant inverse problem is ill- Bayesian framework. In particular, spatially-varying pore conditioned. In order to achieve the stable solution...

... on the previous one. The new realization is accepted or rejected Stochastic methods for seismic inversion problems for the according to a pre-defined rule, that depends on the adopted estimation of rock and fluid properties are commonly algorithm. The most popular McMC methods are the adopted in reservoir...

... Embedding the physics-based forward modeling function in training the deep network could improve the accuracy of the learning-based regression. Solving the geosteering inverse problem is a critical technique of logging while drilling (LWD). When the logging tool has an ultra-long sensitive...

... to the Hilbert space of model parameters using the adjoint operator before training mitigates non uniqueness associated with the underdetermined nature of traditional 3D geophysical inverse problems. A field inversion example using magnetic data collected in Washington -on- Brazos state historic site to image...

... and suggesting a potentially improved sta- g f =Rf , (1) bility of the newly-linearised, exact inverse problem. where g is a Green s function, f is a focusing function and INTRODUCTION R applies multidimensional convolution with the re ection re- sponse measured at the surface. In fact, the governing equation...

... We introduce a machine-learning augmented inversion framework for geophysical reservoir characterization, an ill-posed multi-parameter inverse problem. One key component is a generative network that directly models subsurface parameter distributions. The network’s augmentation can provide better...

... UQ in geophysical inverse problems. Towards practical Bayesian inversion of geobodies using geologic priors Ashutosh Tewari*, Brent Wheelock, Antonio Paiva, Arash Fathi, Myun-Seok Cheon ExxonMobil Research & Engineering Company Summary methods to characterize uncertainty in a solution are simply...

.... reservoir characterization sen parameter space machine learning upstream oil & gas inverse problem geophysics exploration geophysicist 10 optimization problem information velocity model fwi true model full waveform inversion algorithm local optimization artificial intelligence applied...

...) for solving this inverse problem is proposed. Combining the conventional gradient based inversion and machine learning scheme, SDM has the flexibility to incorporate prior information, capability of skipping local minima, and accelerated convergence. Besides, by utilizing real-time feedback obtained from...

... In inverse problems, uncertainty quantification (UQ) deals with a probabilistic description of the solution nonuniqueness and data noise sensitivity. Setting seismic imaging into a Bayesian framework allows for a principled way of studying uncertainty by solving for the model posterior...

... introduce the the- some quasi-Newton methods. Independent of the dimensional- ory of AA and then provides details on how to integrate it ity of the unknown parameters, the computational cost of im- with seismic inverse problems, including FWI and LSRTM. plementing the method can be reduced to an extremely...

... function inverse problem full waveform inversion new likelihood function New likelihood functions and level-set prior for Bayesian full-waveform inversion Matt Dunlop and Yunan Yang, Courant Institute of Mathematical Sciences, New York University SUMMARY larly in the Bayesian setting (El Moselhy...

... the network based on a global criterion. The feasibility of the proposed approach is verified by solving a magnetotelluric (MT) inverse problem. Presentation Date: Wednesday, October 14, 2020 Session Start Time: 9:20 AM Presentation Time: 10:35 AM Location: Poster Station 1 Presentation Type: Poster...

... is then demonstrated using the Bishop synthetic data set. structural geology thickness sedimentary package basement relief estimation federico golfré andreasi inverse problem geophysics reservoir characterization survey area contribution exploration geophysicist 10 upstream oil & gas gravity...

.... Presentation Date: Wednesday, October 14, 2020 Session Start Time: 8:30 AM Presentation Time: 8:55 AM Location: 360C Presentation Type: Oral health & medicine machine learning oncology reservoir characterization neural network inverse problem exploration geophysicist 10 inversion...

... Station 3 Presentation Type: Poster optimization problem wavelength source extension exploration geophysicist 10 artificial intelligence syme waveform inversion geophysics reservoir characterization global minimum annihilator modeling operator upstream oil & gas inverse problem...