... algorithm, the of the posterior distribution of the variables of interest. In posterior distribution is estimated from a set of realizations seismic reservoir characterization studies, McMC methods that are sequentially simulated and accepted or rejected to can be used to estimate the posterior distribution...

... simulation applied geoscience application algorithm geophysics uncertainty quantification latent space siahkoohi seismic data pre-processing artificial intelligence machine learning upstream oil & gas posterior distribution neural network sequence interpolation optimization problem...

... of a correlation matrix, constructed with a decaying correlation at true model (dashed) for shear-wave velocity with single fundamen- larger distances. The noise calculation was initially carried out through tal mode (The posterior distribution of interfaces is shown in left bot- construction of a covariance...

... will be based on unique solver. The Bayesian framework works well in AVO solving the following equation: inversion, which merges multi-formation together to generate posterior distributions of P-wave velocity, S-wave velocity dobs = + (1) and density. In the Bayesian inference, prior distribution, serving...

... layered-medium models derived from vertical profiles of velocity at single locations in the 3D model. A consistent Bayesian update is established to integrate the aforementioned distance with FWI. Through an appropriate scoring system, we show that, on average, TL distances produce posterior distributions...

... 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...

... infeasible for large-scale inverse problems, such as seismic imaging. Our main contribution is a data-driven variational inference approach where we train a normalizing flow (NF), a type of invertible neural net, capable of cheaply sampling the posterior distribution given previously unseen seismic data from...

... for interpreters to better evaluate multimineral results. reservoir characterization reservoir simulation posterior distribution well logging petrophysical endpoint endpoint exploration geophysicist 10 machine learning artificial intelligence applied geoscience dolomite constituent fraction...

... of the five receiver lines posterior distribution has a peak at 88.8 , which is very close are plotted. In the forward modeling, P-wave travel times are to this value. Posterior distributions for the three velocities calculated based on the ray-shooting algorithm for a three- that characterize the HTI...

...”. Feasible models are restricted to the output of a convolutional neural network with a fixed input, while weights and biases are Gaussian random variables. Given a deep prior model, the network parameters are sampled from the posterior distribution via a Markov chain Monte Carlo method, from which...

..., when assessing the quality of approximate MCMC samples for characterizing the posterior distribution, most diagnostics fail to account for these biases. In this work, we introduce the kernel Stein discrepancy (KSD) as a diagnostic tool to determine the convergence of MCMC samples for Bayesian seismic...

...) and Frédéric NGUYEN* (ULiège) Summary Then, we will apply BEL1D to synthetic datasets and show that we converge towards an accurate posterior distribution. BEL1D (Bayesian Evidential Learning 1D imaging) has This will be performed by comparing our results with a state- recently been introduced as a viable...

... training data proceedings exploration geophysicist 10 dataset probability posterior distribution aleatoric uncertainty international conference artificial intelligence deep learning uncertainty estimation epistemic uncertainty seg international exposition automatic channel detection nam pham...

... Session Start Time: 1:50 PM Presentation Time: 2:40 PM Location: 351F Presentation Type: Oral neural network dropout artificial intelligence posterior distribution machine learning deep learning epistemic uncertainty prediction classification result cnn model exploration geophysicist 10...

... characterization bayesian inference machine learning neural network posterior distribution upstream oil & gas full-waveform inversion inverse problem artificial intelligence kullback-leibler divergence geophysics seg international exposition architecture application welling invertible network...

... learning reservoir simulation bayesian inference model parametrization multimodal distribution model parameter facies artificial intelligence transdimensional ava inversion inverse problem reservoir characterization upstream oil & gas posterior distribution iteration inversion geophysics...

... posterior distribution upstream oil & gas algorithm seg international exposition neural network constraint seed well accuracy artificial intelligence machine learning probability annual meeting realization well log bayesian inference cnn Brazell , S. , A. Bayeh , I...

... meeting bayesian inference machine learning metivier tl distance velocity model massachusetts institute artificial intelligence full waveform inversion reservoir characterization geophysics misspecification misfit function full-waveform inversion brossier posterior distribution...

... equation markov chain monte carlo neural network machine learning algorithm acoustic wave equation likelihood function two-stage mcmc algorithm velocity field posterior distribution velocity model nnmcmc equation minkoff inversion upstream oil & gas artificial intelligence operator...

... the direct relation between seismic data and reservoir properties to efficiently estimate reservoir properties, as well as generate samples from the posterior distribution. We discuss methods of learning highly informative summary statistics from seismic data, which help minimizing computational costs...