1887

Abstract

Summary

The accurate prediction of fluid saturation is of great significance for oil and gas exploration and development. However, the prediction of fluid saturation using seismic data mostly stays qualitative and semi-quantitative. How to manage the quantitative prediction of fluid saturation is always a challenge. We present a new saturation quantitative prediction method based on Relevance Vector Machine optimized by Particle Swarm Optimization (PSO-RVM). We use PSO-RVM in quantitative prediction of water saturation with comprehensive application of seismic, logging and geological data. By comparing with Relevance Vector Machine (RVM), PSO-RVM has higher correlation coefficient, lower root mean square error (RMSE) and higher prediction accuracy. At the same time, we introduce the coefficient of variation (CV) to quantify the uncertainty and estimate the reliability of this algorithm. The prediction results of field data are in good agreement with drilling and logging, which shows that this method can predict water saturation quantitatively. PSO-RVM has reference significance in field production.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202310717
2023-06-05
2026-02-07

  • From This Site

    /content/papers/10.3997/2214-4609.202310717
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Jiang, R., OuYangY., Zeng, Q., et al. [2017] Application of the Russell fluid factor in tight sandstone gas detection, Natural Gas Industry, 37, 76–81.
     [Google Scholar]
  2. Wang, D., Wang, H., Ma, J., et al. [2019] Fluids discrimination by ray-path elastic impedance inversion: A successful case from Sulige tight gas field, Applied Geophysics, 16, 218–22.
     [Google Scholar]
  3. Tian, Y., Stovas, A., Gao, J., et al. [2022] Gas Saturation Characterization of Tight Sandstone Via Avo Attributes. 83th EAGE Conference and Exhibition, 1–5.
     [Google Scholar]
  4. Tipping, M. E. [2001] The relevance vector machine. Advances in Neural Information Processing System, 12, 652–658.
     [Google Scholar]
  5. Tipping, M. E. [2003] Sparse Bayesian learning and the relevance vector machine. Journal of Machine Learning Research, 1, 211–244.
     [Google Scholar]
  6. Pilikos, G. [2020] The relevance vector machine for seismic Bayesian compressive sensing. Geophysics, 85, 279–292.
     [Google Scholar]
  7. Dai, S., Li, S., Zhu, T., et al. [2021] An attribute-guided method for reservoir parameter prediction using relevance vector machine, 82nd Annual Conference and Exhibition, 1–5.
     [Google Scholar]
  8. Li, M., Dai, S., Liu, W., et al. [2022] A Novel Permeability Prediction Method with Uncertainty Evaluation, 83th EAGE Conference and Exhibition, 1–5.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202310717
Loading
A Quantitative Saturation Prediction Method Based on PSO-RVM Algorithm
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.202310717
/content/papers/10.3997/2214-4609.202310717
/content/papers/10.3997/2214-4609.202310717
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error