Inception–Attention–BiLSTM Hybrid Network: A Novel Approach for Shear Wave Velocity Prediction Utilizing Well Logging

Shear wave velocity prediction is critical for applications in petrophysics, reservoir characterization, and unconventional energy resource development. While empirical formulas and theoretical rock physics models offer solutions, they are often limited by geological complexity, high cost, and compu...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiayi Li, Yaoting Lin, Zhixian Gui, Peng Wang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2345
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850052991745261568
author Jiayi Li
Yaoting Lin
Zhixian Gui
Peng Wang
author_facet Jiayi Li
Yaoting Lin
Zhixian Gui
Peng Wang
author_sort Jiayi Li
collection DOAJ
description Shear wave velocity prediction is critical for applications in petrophysics, reservoir characterization, and unconventional energy resource development. While empirical formulas and theoretical rock physics models offer solutions, they are often limited by geological complexity, high cost, and computational inefficiency. After the emergence of deep learning methods, a series of new approaches have been provided to tackle these problems. In this study, a novel Inception–attention–BiLSTM hybrid network is proposed to enhance shear wave prediction accuracy and stability by integrating the strengths of three components: Inception for multi-scale feature extraction, attention mechanisms for dynamically highlighting key temporal features, and BiLSTM for capturing long-term dependencies in logging data. The test dataset of this network comes from the Jurassic Badaowan Formation in the Junggar Basin, achieving superior performance compared to standalone Inception and BiLSTM networks. The proposed hybrid network demonstrated MAE and R<sup>2</sup> values of 0.211 and 0.994, respectively, outperforming Inception (MAE 0.671, R<sup>2</sup> 0.981) and BiLSTM (MAE 0.215, R<sup>2</sup> 0.991). These results underscore its robustness in handling complex logging data, providing a more accurate and generalizable framework for Vs prediction while addressing limitations of traditional methods. This work highlights the potential of hybrid deep learning architectures in advancing logging data analysis and reservoir characterization.
format Article
id doaj-art-aedfbf7593814220a2280420bd959b4d
institution DOAJ
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-aedfbf7593814220a2280420bd959b4d2025-08-20T02:52:41ZengMDPI AGApplied Sciences2076-34172025-02-01155234510.3390/app15052345Inception–Attention–BiLSTM Hybrid Network: A Novel Approach for Shear Wave Velocity Prediction Utilizing Well LoggingJiayi Li0Yaoting Lin1Zhixian Gui2Peng Wang3Key Laboratory of Exploration Technologies for Oil and Gas Resources of Ministry of Education, Yangtze University, Wuhan 430100, ChinaSchool of Computer Science and Engineering, Guangdong Ocean University at Yangjiang, Yangjiang 529500, ChinaKey Laboratory of Exploration Technologies for Oil and Gas Resources of Ministry of Education, Yangtze University, Wuhan 430100, ChinaKey Laboratory of Exploration Technologies for Oil and Gas Resources of Ministry of Education, Yangtze University, Wuhan 430100, ChinaShear wave velocity prediction is critical for applications in petrophysics, reservoir characterization, and unconventional energy resource development. While empirical formulas and theoretical rock physics models offer solutions, they are often limited by geological complexity, high cost, and computational inefficiency. After the emergence of deep learning methods, a series of new approaches have been provided to tackle these problems. In this study, a novel Inception–attention–BiLSTM hybrid network is proposed to enhance shear wave prediction accuracy and stability by integrating the strengths of three components: Inception for multi-scale feature extraction, attention mechanisms for dynamically highlighting key temporal features, and BiLSTM for capturing long-term dependencies in logging data. The test dataset of this network comes from the Jurassic Badaowan Formation in the Junggar Basin, achieving superior performance compared to standalone Inception and BiLSTM networks. The proposed hybrid network demonstrated MAE and R<sup>2</sup> values of 0.211 and 0.994, respectively, outperforming Inception (MAE 0.671, R<sup>2</sup> 0.981) and BiLSTM (MAE 0.215, R<sup>2</sup> 0.991). These results underscore its robustness in handling complex logging data, providing a more accurate and generalizable framework for Vs prediction while addressing limitations of traditional methods. This work highlights the potential of hybrid deep learning architectures in advancing logging data analysis and reservoir characterization.https://www.mdpi.com/2076-3417/15/5/2345InceptionBiLSTMattention mechanismshear wave velocity predictionhybrid network
spellingShingle Jiayi Li
Yaoting Lin
Zhixian Gui
Peng Wang
Inception–Attention–BiLSTM Hybrid Network: A Novel Approach for Shear Wave Velocity Prediction Utilizing Well Logging
Applied Sciences
Inception
BiLSTM
attention mechanism
shear wave velocity prediction
hybrid network
title Inception–Attention–BiLSTM Hybrid Network: A Novel Approach for Shear Wave Velocity Prediction Utilizing Well Logging
title_full Inception–Attention–BiLSTM Hybrid Network: A Novel Approach for Shear Wave Velocity Prediction Utilizing Well Logging
title_fullStr Inception–Attention–BiLSTM Hybrid Network: A Novel Approach for Shear Wave Velocity Prediction Utilizing Well Logging
title_full_unstemmed Inception–Attention–BiLSTM Hybrid Network: A Novel Approach for Shear Wave Velocity Prediction Utilizing Well Logging
title_short Inception–Attention–BiLSTM Hybrid Network: A Novel Approach for Shear Wave Velocity Prediction Utilizing Well Logging
title_sort inception attention bilstm hybrid network a novel approach for shear wave velocity prediction utilizing well logging
topic Inception
BiLSTM
attention mechanism
shear wave velocity prediction
hybrid network
url https://www.mdpi.com/2076-3417/15/5/2345
work_keys_str_mv AT jiayili inceptionattentionbilstmhybridnetworkanovelapproachforshearwavevelocitypredictionutilizingwelllogging
AT yaotinglin inceptionattentionbilstmhybridnetworkanovelapproachforshearwavevelocitypredictionutilizingwelllogging
AT zhixiangui inceptionattentionbilstmhybridnetworkanovelapproachforshearwavevelocitypredictionutilizingwelllogging
AT pengwang inceptionattentionbilstmhybridnetworkanovelapproachforshearwavevelocitypredictionutilizingwelllogging