... techniques, from elastic inversion outputs. By using multiple attributes and allowing the fitting of nonlinear models to the data, machine learning techniques provide more accurate predictions of these properties, reducing uncertainties in the characterization of source rocks. The methodology proposed...

... This work explores computationally efficient evaluations to assimilate seismic data in pore pressure forecast at predrill stages. The pore pressure prediction comes from an interdisciplinary workflow that accounts for available data, geological expertise, and physical processes during the basin...

... the engineering “sweet spot” seismic prediction technology to look for the area of engineering “sweetest spot”, and then to guide the horizontal well trajectory design, secondly, we use the micro-seismic monitoring technology to evaluate the effect of hydraulic fracturing, thirdly, we integrate two technologies...

... Hydrocarbon prospect risking is a critical application in geophysics predicting well outcomes from a variety of data including geological, geophysical, and other information modalities. Traditional routines require interpreters to go through a long process to arrive at the probability of success...

... association gaiser geophysical consulting prediction james gaiser Sea oor elastic parameters estimation using a regression neural network Moacyr de Souza Bezerra*,Colorado School of mines, James Simmons, Colorado School of mines and James Gaiser, Gaiser Geophysical Consulting SUMMARY Determination...

...-surface extremely difficult, especially in geologic regimes with complex overburden such as salt or basalt formations. To overcome this problem, we propose a deep learning framework that uses a convolutional neural network (CNN) to form an ensemble of low wavenumber model predictions which can...

... efficient and accurate workflow. Here we demonstrate how to optimize and automate the validation of seismic attributes as hydrocarbon indicators while leveraging now abundantly available open-source Python resources. machine learning prediction international amplitude artificial intelligence...

... acquisition geometries and parameters. These challenges have been addressed by successfully implementing a well- defined seismic processing workflow including technologies such as 5D regularization, 3D surface and internal multiples prediction, tilted transverse isotopic (TTI) depth velocity model building...

... Are facies and stratigraphic architecture reliably predicted using machine learning (ML) techniques on sedimentary outcrop statistics? When are the predictions robust and under what conditions will they fail? At what threshold of training data do these predictions become accurate...

...-based approach to predict low-frequency components. In this paper, we demonstrate the effectiveness of the progressive transfer learning workflow by building a practical workflow and applying it to the field data. artificial intelligence machine learning upstream oil & gas seismic model...

... understanding and reduce uncertainty in geological models. Software-based structural modelling technologies are well-established and have traditionally been operated manually by domain specialists to perform structural analysis tasks. These processes, while allowing rigorous prediction of fault and horizon...

... Carbon capture and storage is a viable greenhouse gas mitigation technology. Monitoring of CO 2 should, in addition to locating the plume, provide quantitative information on CO 2 saturation. We propose a full waveform inversion (FWI) algorithm for the prediction of the spatial distribution...

.... To help identify compartmenting faults across the field, we utilized a machine learning-based approach to quickly help predict the location of the faults. We also trained a probabilistic neural network to predict areas of high net-to-gross reservoir which we correlate to wells within our study area...

... Correlation and convolution based internal multiple prediction is one of the most common methods to predict and subsequently attenuate internal multiples. Such technique is limited to the raypath of internal multiple that satisfy the “low-high-low” concept setting. In order to fulfill...

... that the model is presented with the needed information during training. The synthetic model was used to train a U-Net to predict the facies classes from the seismic cube. Then the trained model was used to infer the facies from the real seismic data. The results are compared against using the same training...

... We combine the ideas of transfer learning and semantic segmentation of seismic facies in a dataset-to-dataset transfer learning research problem with the goal of reducing the number of inputted labeled seismic slices while also improving computational cost and accuracy of predicting geological...

... be analyzed as volumes, slices, or statistical distribution. Mean SNR over the volume/subvolume can be compared directly with the predicted SNR from acquisition design, thus allowing to quantitatively close the loop, rather than blindly relying on simple theoretical predictions. For feasibility studies...

... learning exploration geophysicist diffracted wavefield reflection transfer applied geoscience international gajewski prediction energy 10 dataset american association convolutional autoencoder university Transfer learning seismic and GPR diffraction separation with a convolutional neural...

... artificial intelligence frequency extrapolation fine-tuning reservoir characterization exploration geophysicist neural network prediction architecture figure 1 picking applied geoscience dataset storseismic international application american association randy harsuko energy 10 Seismic...

... present results of litho-classification as well as reservoir property and pore pressure prediction, all derived from elastic parameters of input prestack Amplitude-Variation-with Angle (AVA) inversions from the Midland Basin, in West Texas. upstream oil & gas shale gas kerogen complex...