Acoustic impedance inversion via voting stacked regression (VStaR) algorithms

Abstract In this study, we focused on improving acoustic impedance (AI) in seismic exploration. AI is a crucial parameter estimated by multiplying the density of a material by the velocity of an acoustic wave passing through it. A low AI in sandstones and carbonates often indicates high porosity, wh...

Full description

Saved in:
Bibliographic Details
Main Authors: Lutfi Mulyadi Surachman, Sanlin I. Kaka, Abdullatif Al-Shuhail
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-06332-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334358603726848
author Lutfi Mulyadi Surachman
Sanlin I. Kaka
Abdullatif Al-Shuhail
author_facet Lutfi Mulyadi Surachman
Sanlin I. Kaka
Abdullatif Al-Shuhail
author_sort Lutfi Mulyadi Surachman
collection DOAJ
description Abstract In this study, we focused on improving acoustic impedance (AI) in seismic exploration. AI is a crucial parameter estimated by multiplying the density of a material by the velocity of an acoustic wave passing through it. A low AI in sandstones and carbonates often indicates high porosity, which enhances hydrocarbon accumulation. Accurate AI estimation is thus critical for reliable hydrocarbon exploration. To refine the AI estimation, we used stacking and voting regression algorithms, with depth, two-way travel time (TWTT), and nine seismic attributes as inputs. All models were implemented using scikit-learn . The VStaR model achieved superior predictive performance ( $$\hbox {R}^{2}$$ = 0.9973) and yielded a more accurate fitting parameter (a = 0.1584) in the acoustic impedance–porosity transformation compared to the VSR ( $$\hbox {R}^{2}$$ = 0.9775, a = 0.1583). The VSR approach made the voting of a top-performing base model with two less predictive base models, as used in the existing literature. Relative to the true and BLIMP-derived impedance, the fitting accuracy followed the order of true > VStaR > VSR > BLIMP. While VStaR required longer computation time ( $$\approx$$ 400 s), it reduced RMSE by 14.74% compared to the top-performing base model. VStaR outperformed all evaluated models based on MSE, RMSE, and $$\hbox {R}^{2}$$ metrics. The novelty of the VStaR method based on hyperparameters lies in its superior performance in obtaining a more precise prediction of acoustic impedance compared to the VSR and conventional BLIMP method, potentially improving the effectiveness of hydrocarbon exploration in Illam carbonate dataset.
format Article
id doaj-art-ea82a6edc6ae43c5818eba285383a8f3
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ea82a6edc6ae43c5818eba285383a8f32025-08-20T03:45:35ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-06332-yAcoustic impedance inversion via voting stacked regression (VStaR) algorithmsLutfi Mulyadi Surachman0Sanlin I. Kaka1Abdullatif Al-Shuhail2Geoscience Department, College of Petroleum Engineering and Geoscience, King Fahd University of Petroleum and MineralsGeoscience Department, College of Petroleum Engineering and Geoscience, King Fahd University of Petroleum and MineralsGeoscience Department, College of Petroleum Engineering and Geoscience, King Fahd University of Petroleum and MineralsAbstract In this study, we focused on improving acoustic impedance (AI) in seismic exploration. AI is a crucial parameter estimated by multiplying the density of a material by the velocity of an acoustic wave passing through it. A low AI in sandstones and carbonates often indicates high porosity, which enhances hydrocarbon accumulation. Accurate AI estimation is thus critical for reliable hydrocarbon exploration. To refine the AI estimation, we used stacking and voting regression algorithms, with depth, two-way travel time (TWTT), and nine seismic attributes as inputs. All models were implemented using scikit-learn . The VStaR model achieved superior predictive performance ( $$\hbox {R}^{2}$$ = 0.9973) and yielded a more accurate fitting parameter (a = 0.1584) in the acoustic impedance–porosity transformation compared to the VSR ( $$\hbox {R}^{2}$$ = 0.9775, a = 0.1583). The VSR approach made the voting of a top-performing base model with two less predictive base models, as used in the existing literature. Relative to the true and BLIMP-derived impedance, the fitting accuracy followed the order of true > VStaR > VSR > BLIMP. While VStaR required longer computation time ( $$\approx$$ 400 s), it reduced RMSE by 14.74% compared to the top-performing base model. VStaR outperformed all evaluated models based on MSE, RMSE, and $$\hbox {R}^{2}$$ metrics. The novelty of the VStaR method based on hyperparameters lies in its superior performance in obtaining a more precise prediction of acoustic impedance compared to the VSR and conventional BLIMP method, potentially improving the effectiveness of hydrocarbon exploration in Illam carbonate dataset.https://doi.org/10.1038/s41598-025-06332-ySeismic attributesAcoustic impedanceHydrocarbon explorationBase ModelsFinal estimators3-fold cross-validation
spellingShingle Lutfi Mulyadi Surachman
Sanlin I. Kaka
Abdullatif Al-Shuhail
Acoustic impedance inversion via voting stacked regression (VStaR) algorithms
Scientific Reports
Seismic attributes
Acoustic impedance
Hydrocarbon exploration
Base Models
Final estimators
3-fold cross-validation
title Acoustic impedance inversion via voting stacked regression (VStaR) algorithms
title_full Acoustic impedance inversion via voting stacked regression (VStaR) algorithms
title_fullStr Acoustic impedance inversion via voting stacked regression (VStaR) algorithms
title_full_unstemmed Acoustic impedance inversion via voting stacked regression (VStaR) algorithms
title_short Acoustic impedance inversion via voting stacked regression (VStaR) algorithms
title_sort acoustic impedance inversion via voting stacked regression vstar algorithms
topic Seismic attributes
Acoustic impedance
Hydrocarbon exploration
Base Models
Final estimators
3-fold cross-validation
url https://doi.org/10.1038/s41598-025-06332-y
work_keys_str_mv AT lutfimulyadisurachman acousticimpedanceinversionviavotingstackedregressionvstaralgorithms
AT sanlinikaka acousticimpedanceinversionviavotingstackedregressionvstaralgorithms
AT abdullatifalshuhail acousticimpedanceinversionviavotingstackedregressionvstaralgorithms