... practical studies, it is unfeasible to run fluid flow simulations and predict the reservoir production for hundredths of reservoir realizations due to the computational cost of dynamic fluid flow simulations. For this reason, we propose a statistical method for the selection of a subset of reservoir models...

... volumes at a time, primarily selected based on the interpreter preference. Fortunately, machine learning technology provides the opportunity to quantitatively use many frequency volumes. We analyze twelve spectral magnitude components using multivariate feature selection techniques. The chosen subsets...

... of physically meaningful properties such as impedance, and overall reduce the cost of application. The improvements include wavelet selection, smart preconditioning via NMF (non-stationary matching filter), inversion parameter selection, multi-domain analytic line search, use of an alternate migration operator...

... geophysicist mohammad mohanna omar jahdali society completion installation and operations american association selection jana alfaraj Integrated approach for de-risking an unconventional tight sand play Fahad Alkhunaini*, Mohammad Mohanna, Francis Elisabeth, Jana Alfaraj, Heba Alsoqair and Omar...

...: 11:00 AM Location: 351D Presentation Type: Oral reservoir characterization frequency selection relaxation optimization problem objective function waveform inversion artificial intelligence constraint conventional fwi wri upstream oil & gas initial model wavefield inversion...

... ABSTRACT Selecting appropriate attributes is a crucial part of the seismic facies classification workflow for reducing computational cost and reasonable model building. For supervised learning, the best attribute subset can be built by selecting input attributes that identify...

... channel complex. Three predominant groups are obtained using this classification technique a) Sand-rich deposits b) Siltstone deposits c) Mud-rich deposits. The proper selection of input seismic attributes in SOM along with the use of display options such as horizon probes proves to be a quick workflow...

...Seismic amplitude attributes selection based on 3D model Jun Liu*1, Dengfeng Yang1, Daoli Liu1 1The Research Institute of CNOOC (China) Ltd. Shenzhen, Shenzhen, P. R. China Summary Seismic amplitude attributes are widely used in seismic exploration. However, there are many seismic amplitude...

... features in total, which are used as input data to train the SVM model, have been extracted. These features include 63 1D time/spectral-domain features, and 60 2D texture features. Afterwards, we use a combination of univariate feature selection and random-forest-based recursive feature elimination...

... must be carefully pre-processed. More specifically, when synthetic and observed data have a large waveform mismatch during the initial iterations, waveforms should be carefully selected for calculating the misfit gradient in order to avoid instability. We introduce a fully automated algorithm based...

... ABSTRACT In order to directly obtain the reflectivity series from seismic data, we develop an advanced reflectivity inversion method. The choice between and norm minimization is always difficult for the conventional reflectivity inversion methods, which also require the selection...

... ABSTRACT Computing shots that marginally contribute to seismic images is a waste of resources. This is particularly acute when the desired seismic image focuses on specific sub-surface structures. Selecting the right minimal set of shots to migrate is an open question. Many strategies have...

... machine learning reservoir characterization sp anomaly spectral method anomaly data inversion selection geophysics spectral analysis horizontal cylinder artificial intelligence mtm application interpretation power spectrum High-resolution spectral analysis methods for self-potential data...

... company decision maker flexibility reliability measure saturation decision flexibility voi analysis petroleum industry machine learning decision situation seismic avo data selection information gathering scheme artificial intelligence porosity reservoir characterization Value...

... seg xj oilfield variation feasibility analysis liu zhipeng interpretation upstream oil & gas wang xiaoliu shuyun cnooc research institute water sweep annual international meeting time-lapse seismic application reservoir characterization selection seismic data seismic...

... inversion unconstrained inversion discovery apparent anisotropy anomaly skrugard selection barent sea Towed Streamer EM data from Barents Sea, Norway Anwar Bhuiyan*, Eivind Vesterås and Allan McKay, PGS Summary The measured Towed Streamer EM data from a survey in the Barents Sea, undertaken...

.... We propose a data-selection algorithm for FWI that ensures all input data is within a half-cycle difference compared with the predicted data. This data-selection process is implemented in each iteration of the inversion to generate a velocity model with higher accuracy and minimal artifacts...

... facies. Interpreters use the resulting seismic facies to predict changes in lithology, rock properties, and/or fluid content of the strata being imaged. However, interpreters are confronted with the selection of the clustering technique and the number of seismic facies that best reveal geologic trends...

... romain brossier inversion reservoir characterization plane wave brossier geophysics fwi application full waveform inversion philippe roux institut waveform inversion selection noise summation imaging hierarchical waveform inversion frequency upstream oil & gas université...

... reflector traveltime reflection event delft university reservoir characterization procedure reflector estimation selection multi-datum response haffinger amplitude verschuur imprint Multi-datum based estimation of near-surface full-waveform redatuming operators Jan-Willem Vrolijk, Peter...