XGBoost regression for robust acoustic impedance prediction in the absence of density and sonic logs
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study introduces a machine learning workflow to predict acoustic impedance (Z) using common well logs, bypassing the need for density or sonic data. The new method enhances seismic inversion accuracy in challenging geological settings.
Area Of Science
- Geophysics
- Machine Learning
- Petrophysics
Background
- Acoustic impedance (Z) is crucial for subsurface characterization and seismic inversion.
- Conventional Z derivation requires density and P-wave velocity logs, often unavailable due to operational or technical constraints.
- Existing empirical methods have limitations in heterogeneous formations with high shale content or secondary porosity.
Purpose Of The Study
- To develop a robust machine learning workflow for predicting acoustic impedance (Z) directly from commonly available well logs.
- To overcome the limitations of conventional methods and empirical formulas in complex geological settings.
- To provide a scalable and cost-effective solution for improving seismic inversion accuracy.
Main Methods
- Utilized a multi-well dataset including gamma-ray (GR), neutron porosity (NPHI), and deep resistivity (R<sub>D</sub>).
- Employed Pearson correlation to identify GR, NPHI, and log-transformed resistivity (R<sub>Dlog</sub>) as optimal predictors.
- Implemented an XGBoost regressor with Isolation Forest for outlier removal and cross-validated grid search for hyperparameter optimization.
Main Results
- The XGBoost model achieved high performance with R² values of 0.916 (training) and 0.808 (testing).
- Independent validation on a blind well demonstrated strong generalization (R² = 0.869).
- Predicted Z logs exhibited stratigraphic fidelity and suppressed artifacts, outperforming traditional methods in complex lithologies.
Conclusions
- The machine learning workflow effectively predicts acoustic impedance (Z) from readily available well logs, eliminating the need for sonic or density data.
- This approach overcomes limitations of empirical methods, accommodating higher shale volumes and mitigating errors from secondary porosity or gas effects.
- The developed method offers a scalable, cost-effective solution for enhanced seismic inversion in data-scarce or geologically complex environments.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
Regression analysis is a statistical tool that describes a mathematical relationship between a dependent variable and one or more independent variables.
In regression analysis, a regression equation is determined based on the line of best fit– a line that best fits the data points plotted in a graph. This line is also called the regression line. The algebraic equation for the regression line is called the regression equation. It is represented as:
In the equation, is the dependent...
A goodness-of-fit test is conducted to determine whether the observed frequency values are statistically similar to the frequencies expected for the dataset. Suppose the expected frequencies for a dataset are equal such as when predicting the frequency of any number appearing when casting a die. In that case, the expected frequency is the ratio of the total number of observations (n) to the number of categories (k).
Hence, the expected frequency of any number appearing when casting a die...
In the realm of AC circuits, passive circuit elements like resistors, inductors, and capacitors take on a different character when characterized by phasor voltage and current. Their behavior is expressed through impedance, a vital concept in AC circuit analysis.
Impedance is a measure of resistance to sinusoidal current flow in an AC circuit. Unlike their behavior in DC circuits, where inductors appear as short circuits and capacitors as open circuits, the behavior of these components in AC...
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...