Machine-learning based prediction of phase velocities and phase angles from group velocities and group angles in an anisotropic elastic medium- a feasibility study

Mallick, Subhashis; Rath, Prayas; Ming-liang, Liu; Darhower, Scott A.; Ha, Chau Duc Minh; Moraes, Anthony Manuel; Rangel, R. C.; Ayani, Mohit

doi:10.1190/segam2019-3214496.1

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to the data‐hungry deep learning based approach, ensemble learning might have an advantage in dealing with relatively small data sets (Cracknell & Reading, 2013; Hall & Hall, 2017). In fact, ensemble learning algorithms have prevailed these days owing to their high prediction accuracy and strong generalization ability (Ao et al., 2018; Gupta et al., 2019; Hall & Hall, 2017; Kim et al., 2018; Mallick et al., 2019; Tang et al., 2021; L. Zhang & Zhan, 2017; Z. Zhang et al., 2018; Zhou et al., 2020). The essence of ensemble learning is to integrate a number of weak learners into a strong learner, thus reducing the variance or bias.…”

Section: Introductionmentioning

confidence: 99%

Porosity Prediction With Uncertainty Quantification From Multiple Seismic Attributes Using Random Forest

Zou

Zhao

et al. 2021

JGR Solid Earth

View full text Add to dashboard Cite

Porosity is one of the most critical parameters for subsurface characterization, and is of vital interest to understand fluid flow properties (Bernabé, 1995;Carman, 1956), elastic and mechanics behaviors of rocks (McBeck et al., 2019), and pore pressure evolution and prediction (Obradors-Prats et al., 2017). Therefore, predicting porosity from seismic data has significant influences in geo-energy (oil, gas, geothermal, etc.) reservoir characterization and development (

show abstract

Section: Introductionmentioning

confidence: 99%

Porosity Prediction With Uncertainty Quantification From Multiple Seismic Attributes Using Random Forest

Zou

Zhao

et al. 2021

JGR Solid Earth

View full text Add to dashboard Cite

show abstract

“…However, very few ML models were developed to study the elastic anisotropy of rocks (e.g. You et al, 2019;Mallick et al, 2019). Especially, it lacks the use of the extreme gradient boosting (XGB) method for such objective.…”

Section: Introductionmentioning

confidence: 99%

Study the elastic properties and the anisotropy of rocks using different machine learning methods

Nguyen‐Sy

et al. 2020

Geophysical Prospecting

View full text Add to dashboard Cite

This paper aims to demonstrate that the elastic stiffnesses and the anisotropic parameters of rocks can be accurately predicted from geophysical features such as the porosity, the density, the compression stress, the pore pressure and the burial depth using relevant machine learning methods. It also suggests that the extreme gradient boosting method is the best method for this purpose. It is more accurate, extremely faster to train and more robust than the artificial neural networks and the support vector machine methods. Very high R‐squared scores was obtained for the predicted elastic stiffnesses of a relevant dataset that is available in the literature. This dataset contains different types of rocks, and the values of the features are in large ranges. An optimal set of parameters was obtained by considering an appropriate sensitivity analysis. The optimized model is very easy to implement in Python for practical applications.

show abstract

Fluid and lithofacies prediction based on integration of well-log data and seismic inversion: A machine-learning approach

et al. 2021

View full text Add to dashboard Cite

Seismic prediction of fluid and lithofacies distributions is of great interest to reservoir characterization, geological model building, and flow unit delineation. Inferring fluids and lithofacies from seismic data under the framework of machine learning is commonly subject to issues of limited features, imbalanced data sets, and spatial constraints. As a consequence, an XGBoost based workflow, which takes feature engineering, data balancing, and spatial constraints into account, is proposed to predict the fluid and lithofacies distribution by integrating well-log and seismic data. The constructed feature set based on simple mathematical operations and domain knowledge outperforms the benchmark group consisting of conventional elastic attributes of P-impedance and Vp/Vs ratio. A radial basis function characterizing the weights of training samples according to the distances from the available wells to the target region is developed to impose spatial constraints on the model training process, significantly improving the prediction accuracy and reliability of gas sandstone. The strategy combining the synthetic minority oversampling technique (SMOTE) and spatial constraints further increases the F1 score of gas sandstone and also benefits the overall prediction performance of all the facies. The application of the combined strategy on prestack seismic inversion results generates a more geologically reasonable spatial distribution of fluids, thus verifying the robustness and effectiveness of the proposed workflow.

show abstract

Machine-learning based prediction of phase velocities and phase angles from group velocities and group angles in an anisotropic elastic medium- a feasibility study

Cited by 3 publications

References 17 publications

Porosity Prediction With Uncertainty Quantification From Multiple Seismic Attributes Using Random Forest

Porosity Prediction With Uncertainty Quantification From Multiple Seismic Attributes Using Random Forest

Study the elastic properties and the anisotropy of rocks using different machine learning methods

Fluid and lithofacies prediction based on integration of well-log data and seismic inversion: A machine-learning approach

Contact Info

Product

Resources

About