1887

Abstract

Summary

TOC, one of the crucial reservoir properties, is significant for the reservoir evaluation. Therefore, it’s necessary to acquire high-precision TOC by the low-cost and effective technology. Because logging parameters and TOC have a complicated nonlinear mapping connection and time series features, we propose a LSTM-Attention (Long Short-Term Memory Combined with Attention Mechanism) method for predicting TOC, and use the real logging data of an exploration area in Qinshui Basin to test the performance of this model. This method makes full use of the advantages of LSTM in processing serialized structural data. To automatically extract the crucial information from LSTM structure, the attention mechanism is introduced. The research results suggest that compared with SVR, GBDT and LSTM models, LSTM-Attention model has lower prediction error and broad application prospects in TOC prediction.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202372047
2023-09-12
2025-11-12

  • From This Site

    /content/papers/10.3997/2214-4609.202372047
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Bakhorji, A., Mustafa, H. and Aramco, S. [2012] Rock physics modeling and analysis of elastic signatures for intermediate to low porosity sandstones.SEG Technical Program Expanded Abstracts 2012, 1–5.
     [Google Scholar]
  2. Berhich, A., Belouadha, F.Z. and Kabbaj, M.I. [2023] An attention-based LSTM network for large earthquake prediction.Soil Dynamics and Earthquake Engineering, 165.
     [Google Scholar]
  3. Hao, X., Du, H. and Reynolds, M. [2019] Location-velocity attention for pedestrian trajectory prediction.IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE.
     [Google Scholar]
  4. Silva, A.A., Neto, I., Misságia, R.M., Ceia, M.A., Carrasquilla, A.G. and Archilha, N.L. [2015] Artificial neural networks to support petrographic classification of carbonate-siliciclastic rocks using well logs and textural information.Journal of Applied Geophysics, 117, 118–125.
     [Google Scholar]
  5. Wang, G.C., Carr, T.R. and Ju, Y.W. [2014] Identifying organic-rich Marcellus shale lithofacies by support vector machine classifier in the Appalachian basin.Computers & Geosciences, 64, 52–60.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202372047
Loading
TOC Prediction Using LSTM-Attention Method: a Case Study in Qinshui Basin
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.202372047
/content/papers/10.3997/2214-4609.202372047
/content/papers/10.3997/2214-4609.202372047
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