..., a geological model construction method based on logging data and geological stratigraphic constraints is proposed to simulate VSP data using geological models with different logging responses, and a rich, complete, and physically meaningful training dataset is constructed based on the synthetic VSP data...

... sedimentary geology prediction geological subdiscipline zubair formation training dataset interpretation american association cored well information genetic element algorithm exploration geophysicist workflow confusion matrix dataset artificial intelligence economic geology applied geoscience...

... to understand their influences on the final prediction of pressure and saturation changes. In the Gulf of Mexico (GOM) case study, we utilized a synthetic seismic as the training dataset, generated from a history-matched simulation model and a calibrated rock physics model. The synthetic seismic provided direct...

... geoscience human intervention reservoir characterization extended abstract dnn exploration geophysicist 10 jérémie messud leakage artificial intelligence signal fidelity training dataset application supervised learning amplitude dataset dnn model algorithm seismic processing cgg summary...

... applied geoscience machine learning deep learning shot gather training data swell noise removal noise removal swell noise clean data noise training dataset exploration geophysicist 10 deep neural network summary dataset innovative strategy feature map seismic swell noise removal...

... functions to prevent deep learning from severe over tting. However, this regularization cannot completely solve the over tting issue caused by a biased training dataset. True model Observed data Velocity distribution of each feature Migration model Model Original segmentation migration image Assign random...

... upstream oil & gas specific relationship geophysics deep learning joint inversion method standard inversion workflow separately inverted model resistivity neural network inversion workflow artificial intelligence joint inversion applied geoscience training dataset exploration geophysicist...

.... For generating ML model with high performance, the features of target seismic data must be reflected in the training data when the training dataset is numerically generated. The characteristic of reflectivity series, one of the important features of target data, was extracted from well log data in previous...

... to a classical coherency-based optimization technique while preserving a reasonable quality of results. machine learning deep learning prestack seismic data workflow neural network regularization grid artificial intelligence applied geoscience training dataset exploration geophysicist 10 direct...

... Supervised learning-based seismic data processing has difficulty transferring synthetic data learning to real data applications. We report a distribution analysis method to build training datasets for the target field data, without modifying the network, and only a small volume of data is needed...

... ranges for the training dataset and testing dataset. Both synthetic and real data examples demonstrated the effectiveness and robustness of the method. Presentation Date: Tuesday, October 13, 2020 Session Start Time: 8:30 AM Presentation Time: 10:35 AM Location: 351F Presentation Type: Oral...

... are multiscale, rotation and translation invariant, which can better distinguish seismic facies. Inspired by that, we propose a rotation invariant CNN with scattering coefficients as the input (ScaCNN). It can improve the generalization ability of CNN, especially when the training dataset is limited. Meanwhile...

.... Additionally, we study the generalization ability of the proposed neural network over different physical models. For elastic test data, collecting the training dataset by elastic simulation shows better extrapolation accuracy than acoustic simulation, i.e., a smaller generalization gap. Presentation Date...

... demonstrate the efficiency of the proposed approach and highlight the adaptiveness of the physics augmented deep learning workflow. machine learning deep learning training dataset reservoir characterization upstream oil & gas expanded abstract unblended data velocity model artificial...

... numerous 3D training data pairs including synthetic seismic images and the corresponding label images of the paleokarst features. With this workflow, we are able to simulate realistic and diverse geologic structure patterns and paleokarst features in the training datasets from which the CNN can effectively...

... to the systematic generation of training dataset using t-SNE analysis, we can extract faint diffractions and diffraction tails overlapped by strong reflection events. In addition, we clearly demonstrated the effect of training dataset on the DL performance. Since the extracted diffractions by our method preserve...

... to separate P/S waves. This method employs a multi-task neural network that extracts P- and S-potential simultaneously from multi-component VSP data. Targeting at a specific testing dataset, we derive an efficient building strategy to construct training datasets. Synthetic data experiment shows NN trained...

... computer vision geological structure artificial intelligence upstream oil & gas training dataset seg international exposition dataset exploration geophysicist 10 estimation relative geologic time estimation geophysics interpretation fomel seismic volume 3D relative geologic time...

... spectrum t-sne analysis machine learning seismic field data trace interval architecture csg neural network crg upstream oil & gas training data training dataset artificial intelligence seg international exposition optimal annual meeting convolutional u-net field data interpolation...

..., significantly reducing the network complexity and the network training cost. The Progressive Transfer Learning technique enables us to initiate the deep learning network with only one training dataset. Unlike other deep learning approaches in this category, our training dataset is not fixed. Instead...