• Home
  • Search
  • Rayleigh-wave dispersion data selection and model fine-tuning based on uncertainty estimation
  • https://doi.org/10.1038/s41598-025-30603-3Copy DOI Icon

Rayleigh-wave dispersion data selection and model fine-tuning based on uncertainty estimation

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Rayleigh-wave inversion is a reliable approach for obtaining subsurface shear-wave velocity structures and holds significant importance in seismic risk assessment, resource exploration, and geotechnical engineering. Numerous studies have demonstrated the great potential of deep learning (DL) in Rayleigh-wave inversion; however, existing DL methods still suffer from limited generalization, strong dependence on training data, and slow convergence. To address these issues, this study proposes a representative data selection and model optimization strategy. Specifically, we identify high-uncertainty samples based on the inconsistency of predictions from multiple pretrained models trained in parallel. An automatic differentiation-driven inversion method is then used to generate high-confidence pseudo-labels for the selected data, which are subsequently employed to fine-tune the original model. This workflow requires no borehole information and significantly improves the prediction accuracy and robustness of the model in the target area. Both synthetic and field experiments validate the effectiveness of the proposed method, demonstrating enhanced adaptability and performance in complex geological environments with relatively small additional cost.

Similar Papers
  • Research Article

Inversion of rayleigh waves dispersion using quantum-behaved PSO to characterize the embankment of mud flow Dam in Sidoarjo (LUSI)

  • Nov 01, 2020
  • IOP Conference Series: Earth and Environmental Science
  • Y Widyaningrum +2
  • Preprint Article

Verification of the accuracy of rock material determination by hammer strike sound using deep learning 

  • Mar 18, 2025
  • Daisuke Sugeta +2
  • PDF
  • Research Article
  • Citations56

Pushing the limits of solubility prediction via quality-oriented data selection.

  • Dec 17, 2020
  • iScience
  • Murat Cihan Sorkun +2
  • Research Article
  • Citations1

New models for estimating pure shear fracture toughness of confined quasi-brittle PTS specimens: Empirical and machine learning framework

  • Dec 01, 2025
  • Results in Engineering
  • Mohammad Matin Rouhani +1
  • PDF
  • Research Article
  • Citations9

DVNE-DRL: dynamic virtual network embedding algorithm based on deep reinforcement learning.

  • Nov 13, 2023
  • Scientific Reports
  • Xiancui Xiao
  • Research Article
  • Citations19

Geostatistical inference using crosshole ground-penetrating radar

  • Nov 01, 2010
  • GEOPHYSICS
  • Majken C Looms +5
  • Research Article
  • Citations31

Multi-site cross-organ calibrated deep learning (MuSClD): Automated diagnosis of non-melanoma skin cancer☆

  • Nov 24, 2022
  • Medical image analysis
  • Yufei Zhou +6
  • Conference Article

Accelerating Offshore Windfarm Site Characterization Using Deep Learning

  • Apr 29, 2024
  • H Di +3
  • Conference Article
  • Citations42

Augmentation and evaluation of training data for deep learning

  • Dec 01, 2017
  • Junhua Ding +2
  • Research Article
  • Citations3

Audio-frequency magnetotelluric data inversion method based on an adaptive binary structure constraint and its application in geothermal exploration

  • Apr 04, 2025
  • GEOPHYSICS
  • Rongzhe Zhang +4
  • PDF
  • Research Article
  • Citations5

A Method for Determining Target Areas of Hot Dry Rock Resources: A Case Study in Continental China

  • May 20, 2024
  • Energies
  • Yaqi Wang +6
  • PDF
  • Research Article
  • Citations13

Data Augmentation for Human Keypoint Estimation Deep Learning based Sign Language Translation

  • Aug 05, 2020
  • Electronics
  • Chan-Il Park +1
  • Research Article
  • Citations49

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation – Analysis of Ranking Scores and Benchmarking Results

  • Aug 26, 2022
  • Machine Learning for Biomedical Imaging
  • Raghav Mehta +91
  • Research Article
  • Citations506

Deep Learning for Geophysics: Current and Future Trends

  • Jul 15, 2021
  • Reviews of Geophysics
  • Siwei Yu +1
  • Research Article
  • Citations17

Combining Dense Seismic Arrays and Broadband Data to Image the Subsurface Velocity Structure in Geothermally Active South‐Central Utah

  • Jul 01, 2022
  • Journal of Geophysical Research: Solid Earth
  • Daniel Wells +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.