Heterogeneous Seismic Waves Pattern Recognition in Oil Exploration with Spectrum Imaging

project
Dec 2021

This paper presents a classification model for seismic data using Mel-spectrum analysis and pre-trained ResNet34 with transfer learning, achieving an accuracy of 98.32%. It introduces a more efficient approach for seismic wave pattern recognition in oil exploration compared to traditional Fourier transformation methods.

  • The paper discusses the challenges in managing and processing seismic wave data in oil exploration. It introduces a novel approach using Mel-spectrum analysis and deep learning (ResNet34) for the classification of seismic data. The study demonstrates significant improvements over traditional Fourier transformation methods, both in terms of accuracy and efficiency.
    • Seismic Waves Processing
    • Quality Control
    • Pattern Classification
    • Neural Network
    • Bulk Data Management
    Paper