Application of the BiLSTM-Attention Fusion Model in 
Permeability Prediction

Yue Yang; Yin Xu; Shixuan Su; Hengyu Liu; Ke Lai

doi:10.70711/itr.v2i4.7696

Application of the BiLSTM-Attention Fusion Model in Permeability Prediction

Yue Yang, Yin Xu, Shixuan Su, Hengyu Liu, Ke Lai

Abstract

Permeability is a key parameter in reservoir physical property evaluation, traditional permeability testing heavily relies on core
experiments and empirical formulas, yet it suffers from high costs and limited coverage. In recent years, deep learning methods have demonstrated significant advantages in reservoir parameter prediction, especially suitable for handling complex geological data with strong nonlinearity and features. To address these challenges, this paper proposes a hybrid model combining Bidirectional Long Short-Term Memory
network (BiLSTM) and Attention mechanism (BiLSTM-Attention). Moreover, the model integrates the Optuna hyperparameter automatic
optimization algorithm, enabling optimal structural search while ensuring training efficiency. Compared with traditional prediction methods
such as Multilayer Perceptron (MLP), the proposed model shows remarkable advantages across all evaluation metrics.

Keywords

Permeability prediction; BiLSTM; Attention mechanism; Deep learning; Optuna; Well logging data

Full Text:

PDF

Included Database

References

[1] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 17351780. https://doi.org/10.1162/

neco.1997.9.8.1735

[2] Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673

2681. https://doi.org/10.1109/78.650093

[3] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[C]// Proceedings of the International Conference on Learning Representations (ICLR). 2015.

[4] Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint

arXiv:1409.0473.

[5] Luong, M., Pham, H., & Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. Proceedings of the

2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), 14121421.

[6] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]// Advances in Neural Information Processing Systems (NeurIPS).

2017: 59986008.

[7] Akiba T, Sano S, Yanase T, et al. Optuna: A next-generation hyperparameter optimization framework[C]// Proceedings of the 25th ACM

SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019: 26232631.

[8] Zhang J, Zhao M, Wang Q, et al. Deep learning-based reservoir property prediction using well logs: A case study from an unconventional reservoir[J]. Journal of Petroleum Science and Engineering, 2020, 189: 106920.

DOI: http://dx.doi.org/10.70711/itr.v2i4.7696

Refbacks

There are currently no refbacks.