Guofa Li

ORCID: 0000-0003-4043-8544
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Seismic Imaging and Inversion Techniques
  • Seismic Waves and Analysis
  • Hydraulic Fracturing and Reservoir Analysis
  • Drilling and Well Engineering
  • Geophysical Methods and Applications
  • Hydrocarbon exploration and reservoir analysis
  • Advanced machining processes and optimization
  • Underwater Acoustics Research
  • Probabilistic and Robust Engineering Design
  • Advanced Measurement and Metrology Techniques
  • Sparse and Compressive Sensing Techniques
  • Image and Signal Denoising Methods
  • Manufacturing Process and Optimization
  • Fatigue and fracture mechanics
  • Ultrasonics and Acoustic Wave Propagation
  • Structural Health Monitoring Techniques
  • Microwave Imaging and Scattering Analysis
  • Reservoir Engineering and Simulation Methods
  • Optical Systems and Laser Technology
  • Geoscience and Mining Technology
  • Laser and Thermal Forming Techniques
  • Industrial Vision Systems and Defect Detection
  • Reliability and Maintenance Optimization
  • Advanced Numerical Analysis Techniques
  • NMR spectroscopy and applications

China University of Petroleum, Beijing
2016-2025

Jilin University
2011-2023

China National Petroleum Corporation (China)
2002-2021

Shandong Lianxing Energy Group (China)
2021

Jilin Medical University
2011-2021

University of Alberta
2015

Qujing Normal University
2013

Chinese Academy of Sciences
2010

Changchun Institute of Applied Chemistry
2010

China University of Mining and Technology
2004-2008

Failure mode and effects analysis (FMEA) is a widely used technique for identifying, evaluating, eliminating potential failures in production, system, process. The traditional FMEA ranks the failure modes according to risk priority numbers (RPN), which are obtained by multiplications of crisp values factors, such as occurrence (O), severity (S), detection (D). However, criticized mishandling uncertain information calculating RPN unreasonably. To overcome above deficiencies, this study...

10.1080/08982112.2019.1677913 article EN Quality Engineering 2019-11-01

Seismic wave propagation in a viscoelastic medium suffers from energy attenuation and velocity dispersion. For prestack seismic data, the earth absorption not only decreases resolution, but it also distorts amplitude variation with offset (AVO). Inverse [Formula: see text] filtering is technique commonly used to remove these effects. However, its application often instability presence of noise. Therefore, we have developed two-step scheme We decompose into two independent components, namely,...

10.1190/geo2015-0038.1 article EN Geophysics 2015-08-26

ABSTRACT Random noise attenuation is an essential step in seismic data processing for improving quality and signal‐to‐noise ratio. We adopt unsupervised machine learning approach to attenuate random via signal reconstruction strategy. This can be accomplished the following steps: Firstly, we randomly mute a part of input neural network according certain percentage, then outputs reconstructed influenced by this mute. The objective function measures distance between data. Secondly, use...

10.1111/1365-2478.13070 article EN Geophysical Prospecting 2021-01-23

Enlightened by the classical total variation (TV) model, we present a novel random noise reduction method for seismic data based on Bayesian inversion, called inversion filtering. The regards 2D 'clean' as model parameters, and is equivalent to inverting these parameters from observed data. implemented maximizing posterior distribution, which replaced product of priori distribution likelihood function. performance this mainly depends choice information. Based statistical knowledge or...

10.1088/1742-2132/9/1/007 article EN Journal of Geophysics and Engineering 2011-12-12

Sparse deconvolution methods frequently invert for subsurface reflection impulses and adopt a trace-by-trace processing pattern. However, following this approach causes unreliability of the estimated reflectivity due to nonuniqueness inverse problem, poor spatial continuity structures in reconstructed section, suppression on signals with small amplitudes. We have developed structurally constrained multichannel band-controlled (SC-MBCD) algorithm alleviate these three issues. The inverts...

10.1190/geo2017-0516.1 article EN Geophysics 2018-06-06

The resolution of seismic data determines the ability to characterize individual geological structures in a image. Sparse spike inversion (SSI) is an effective approach for improving data. However, basic assumption SSI that strong reflectivity formation sparse, which may not be reasonable fit weak thin-layer reflections. In this study, we propose deep learning-based method reconstruct high-resolution by combining information from longitudinal distribution and lateral structure features field...

10.1109/tgrs.2023.3234617 article EN IEEE Transactions on Geoscience and Remote Sensing 2023-01-01

The characterization of the spatial structures thin-layer sand bodies is foundation for detailed reservoir description and physical property estimation. This requires using geophysical inversion technique to make full use subsurface sedimentation information found in well logging seismic data comprehensive evaluation. However, traditional model-based method limited by frequency bandwidth data, resolution results cannot meet accuracy requirements characterization. In this paper, we introduce...

10.1190/geo2023-0647.1 article EN Geophysics 2025-04-30

10.1109/tgrs.2025.3566400 article EN IEEE Transactions on Geoscience and Remote Sensing 2025-01-01

Seismic absorption compensation is an important processing approach to mitigate the attenuation effects caused by intrinsic inelasticity of subsurface media and enhance seismic resolution. However, conventional approaches ignore spatial connection along traces, which makes result vulnerable high-frequency noise amplification, thus reducing signal-to-noise ratio (S/N) result. To alleviate this issue, we have developed a structurally constrained multichannel (SC-MAC) algorithm. In cost...

10.1190/geo2019-0132.1 article EN Geophysics 2019-10-16

Seismic high-resolution (HR) reconstruction is a crucial process for identifying increasingly thin layers from observed seismic data. Nowadays, machine learning (ML) has been adopted in resolution improvement; however, most of the ML-based methods directly use 1-D neural networks and ignore spatial information along traces. Thus, these cause poor stability accuracy issues improving multidimensional In this article, we propose to incorporate structural constraint into network framework...

10.1109/tgrs.2022.3157064 article EN IEEE Transactions on Geoscience and Remote Sensing 2022-01-01

With the successful application and breakthrough of deep learning technology in image segmentation, there has been continuous development field seismic facies interpretation using convolutional neural networks. These intelligent automated methods significantly reduce manual labor, particularly laborious task manually labeling facies. However, extensive demand for training data imposes limitations on their wider application. To overcome this challenge, we adopt UNet architecture as...

10.1016/j.petsci.2023.11.027 article EN cc-by-nc-nd Petroleum Science 2023-12-03
Coming Soon ...