... the temporal stacking of predicted geological units. Our hybrid learning strategy trains the network in a supervised manner on a few labelled lines and in an unsupervised manner on the entire dataset. We showed, on a real seismic dataset, that our approach significantly improves the prediction’s accuracy...

... and time-consuming analysis are limited to application of digital rock technology. Therefore, an intelligent digital rock physics analysis workflow including image processing, modelling, and parameters prediction can improve the construction efficiency of fine porosity-permeability relationship and rock...

... 10 prediction american association applied geoscience society openfwi dataset international velocitygan highest ssim generalization equation Generalization capability of data-driven deep learning models for seismic full waveform inversion: an example using the OpenFWI dataset Ayrat...

... One of the main objectives of seismic inversion in reservoir characterization is to predict lithofluid facies, such as gas sand, brine sand, and shale. For seismic inversion methods that explicitly generate elastic properties (Vp, Vs, and density), a critical next step is to use these properties...

... that joint modeling has a better performance in elastic parameter prediction. Based on the analysis of rock electrical conductivity, the changes of rock lithology and physical properties can be judged to a certain extent. structural geology phyllosilicate upstream oil & gas rock type asia...

... This study introduces an efficient machine learning workflow for quickly predicting microearthquake (MEQ) locations within Enhanced Geothermal Systems (EGS), focusing on the Newberry EGS site. We leverage on a high-resolution field 3D P-velocity model to simulate physics-informed synthetic MEQ...

... to eliminate internal multiples based on the Marchenko equation, originated from a basis of the inverse scattering theory. We review and describe challenges and processing steps required to perform effective internal multiple attenuation on thin-layered media using the Marchenko-based prediction method...

... of Marchenko-based internal multiple removal strategies. One focuses on internal multiple prediction (IMP) based on Marchenko redatuming and seismic interferometry (SI). The second method emphasizes primary reflection retrieval (PRR) by capturing primary reflections without adaptive subtraction. It is derived...

... permeability porosity hydraulic tortuosity diameter classification permeability prediction relation american association discriminator society sedimentary rock clastic rock tortuosity prediction modeling exploration geophysicist rocklog consultancy summary applied geoscience international...

... accuracy. Besides, in order to make full use of different fracture prediction results ranging from post-stack seismic, VVAz (Velocity Versus Azimuth) and AVAz, the neural net fracture prediction is carried out to realize multi-scale fracture prediction, which is useful for further well deployment...

... geologist alregib geology reservoir characterization classifier applied geoscience counterfactual counterfactual uncertainty international application united states government machine learning dataset interpretation prediction workflow prospect american association explanation exploration...

... 2D, gridded magnetic data and detect steel pipelines. Using a U-Net architecture, the network is able to make pixel-wise predictions of the presence or absence of a pipeline at any location on the input grid. united states government upstream oil & gas geologist deep learning pipeline...

... geomechanics modeling methods. The comparison results demonstrated the applicability and reliability of the proposed digital approach, with learning accuracy of over 99% for the geomechanical parameters and geostructure, the wellbore stability predictions of several horizontal wells were also proved accurate...

... government international american association upstream oil & gas resolution exploration geophysicist expanded abstract geology seismic resolution migration cgg figure demultiple energy 10 prediction courtesy society acquisition Improving seismic resolution by reprocessing multiple...

... sandstone reservoir layers embedded in contrasting lithologies and allows for improved predictability in new well locations. Seismic amplitude interpretation is run in parallel with other processes to reduce subsurface risk, including seismic pre-stack inversion, spectral decomposition, and waveform...

... As we all know, accuracy of depth prediction determines the quality of oilfield development effectiveness to a large extent, especially for thin sand within offshore reservoir, where development wells are mainly horizontal and extremely sensitive to depth. However, traditional methods predict...

..., and the uncertainty is larger. geologist artificial intelligence machine learning upstream oil & gas well logging geological subdiscipline geology log analysis prediction exploration geophysicist ml algorithm american association energy 10 applied geoscience summary estimation reservoir...

... In complex geological environments, noise from the overburden often impacts the primary reflection signals from the reservoir. If the noise systematically interferes with the signal, then such data can lead to erroneous predictions. We consider a 3D real-data example from a clastic setting where...

... This study employs Convolutional Neural Networks (CNNs) to predict low-wavenumber seismic velocity models to serve as starting models for Full Waveform Inversion (FWI), utilizing the Gulf of Mexico’s Tiber field data, characterized by its expansive allochthonous salt body. The CNNs were trained...

... classifier geological subdiscipline dataset reservoir characterization bayesian discriminative classification upstream oil & gas rock type reservoir geomechanics classification prediction exploration geophysicist inversion workflow applied geoscience energy 10 geologic knowledge...