.... 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...

... Recently, deep neural networks have been widely used for seismic inversion due to the availability of computational resources. However, having the capability to perform complex non-linear mapping it requires large amount of labeled data (well-log data) which in general is rarely available...

... The detection of cyclic depositional patterns is a key element of quantitative stratigraphy. It is often based on well log data, which can be challenging due to the presence of superimposed cycles and non-geological artifacts. We propose an approach to assist the detection of sedimentary...

... porosity and permeability at the same time using multitask learning neural networks. We also introduced a new workflow to resolve the imbalance issue existing in well log data which can enable us to estimate the porosity and permeability efficiently and accurately. We also demonstrated the effectiveness...

... Presentation Time: 4:20 PM Location: 360C Presentation Type: Oral upstream oil & gas well 32900 reservoir characterization cherry prospect well logging porosity log analysis correlating porosity water saturation well log data prospect cherry ratio method saturation seg international...

... classification, there is a problem that the data available for training are very limited. When using training data acquired under such limited conditions, such as well log data, there can be a severe imbalance in the number of training samples for the facies because the amount of data acquired in the hydrocarbon...

..., September 17, 2019 Session Start Time: 8:30 AM Presentation Start Time: 10:35 AM Location: 217A Presentation Type: Oral impedance upstream oil & gas resolution reservoir characterization realization seismic inversion well log data inversion reservoir property seismic data vertical...

... Location: 214D Presentation Type: Oral prediction estimation information seismoelectric conversion well log data well logging log analysis upstream oil & gas well-log data inverse problem boundary vertical seismic profile inversion seismoelectric inverse problem seg international...

...Crossgradient anisotropic 3D CSEM inversion integrated with seismic and well log data to reduce uncertainty Max A. Meju1*, Randall L. Mackie2, Federico Miorelli2 and Shahir A. Saleh1 1Petronas Carigali, Kuala Lumpur 2CGG Multi-Physics Imaging, Milan Summary Marine controlled-source electromagnetic...

... Start Time: 1:50:00 PM Location: Poster Station 13 Presentation Type: Poster artificial intelligence csem data well log data optimization problem inversion conductivity genetic algorithm synthetic data mallick evolutionary algorithm stoffa machine learning upstream oil & gas...

... ABSTRACT Statistical analysis of geophysical well log data and geochemical data were used to train neural networks to provide automated well site drill cutting analysis to provide increased data for use in reservoir characterization. The aim of this project is the optimization of petrophysical...

... volume even when the amount of well log data is small and not sufficient for the supervised learning algorithms. Presentation Date: Tuesday, October 16, 2018 Start Time: 9:20:00 AM Location: Poster Station 1 Presentation Type: Poster workflow facies crossplot machine learning semi...

..., October 18, 2018 Start Time: 8:30:00 AM Location: 202A (Anaheim Convention Center) Presentation Type: Oral well log data anisotropic soft porosity model seg international exposition shale log analysis upstream oil & gas reservoir characterization olivier kirstetter anisotropy...

... to impose the spatial continuity of the inverted parameters. The low frequency model is built from well log data, and included iteratively to the prior model through a process of frequency matching. The misfit between modelled and observed data is controlled by an energy “spectral attribute” to ensure...

... instantaneous amplitude and instantaneous frequency for assessing whether the BSR is related to gas hydrates. The level of BSR confirmed is in good agreement with well log data. Density derived porosity log is used to derive the bulk and shear moduli of GHBS, which along with the bulk density is used to model...

... ABSTRACT Heterogeneities are generally existed in real earth medium, and play an important role in the study of oil and gas reservoir, metallic ore deposit, and hydrology. To recover different-scale heterogeneities from seismic data, well log data and geology becomes a major challenge...

... ABSTRACT We present a workflow that integrates self-organized mapping classification results with rock physics based on well log data. The facies are extracted from reflection seismic data and rock physical models are obtained from well logs to calculate density, and P- and S-wave velocities...

.... We demonstrate how the model we propose for the upscaling can be applied to a well log data to correct the effective param- eters processing if presence of tilt is confirmed by additional measurements (for example, borehole imaging). INTRODUCTION Backus (1962) showed that a stack of homogeneous...

... of these methods is shown for well log data from the Gulf of Mexico. The results are compared to the SAM and Backus Averaging Method BAM . In conclusion, we find that the derived SHM has direct correlation to the BAM, and the power mean hierarchy holds true in all upscaling windows. The methods introduced...

... approach heavy oil shear moduli effective bulk upstream oil & gas reservoir characterization well log data composite gassmann shear modulus stress heterogeneity solid substitution geometry pore compliance Solid Substitution through Strain Concentration Tensors Sabrina Aliyeva* and Gary...