A lithological sequence classification method with well log via SVM-assisted bi-directional GRU-CRF neural network

Liu, Zhege; Cao, Junxing; You, Jiachun; Chen, Shuna; Lu, Yujia; Zhou, Peng

doi:10.1016/j.petrol.2021.108913

Cited by 17 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently data-driven deep learning methods are widely used in geophysics for first-to-wave pickup (Liao et al, 2020;Qu et al, 2021), seismic data denoising (Wang and Chen, 2019;Liu et al, 2020;Liu et al, 2022), and seismic facies recognition (Tschannen et al, 2020;Liu et al, 2021). Due to the advantage of automatically characterizing complex multivariate non-linear relationships, DNN is also used for acquiring reservoir gas-bearing properties.…”

Section: Introductionmentioning

confidence: 99%

Gas-bearing prediction of deep reservoir based on DNN embeddings

Cao

Liu

et al. 2023

Front. Earth Sci.

Self Cite

View full text Add to dashboard Cite

The extraction of gas-bearing information from the deeply underground reservoir is extremely difficult due to the weak seismic response and complicated gas distribution characteristics. To predict gas-bearing reservoirs efficiently, we developed a deep neural network (DNN) embedding-based gas-bearing prediction scheme. First, the cepstrum coefficient that is sensitive to hydrocarbons is computed using the raw seismic data. A DNN model inspired by the x-vector in speech recognition is designed, comprising the long short-term memory (LSTM) networks and two fully connected (FC) networks, stacked from the bottom to the top layer. Then, the cepstrum features are fed into the DNN for training and testing, and DNN embedding is extracted from the top layers after optimized network parameters are determined. Finally, the gas-bearing probability of the reservoir is predicted by calculating the cosine distance between pairs of DNN embeddings. When applied to synthetic seismic data, the proposed method offers greater than 90% accuracy at SNR > 3 dB. Besides, the predicted result applied in deep carbonate reservoirs in China’s Sichuan Basin is in basic agreement with the actual situation, demonstrating the certain feasibility of the proposed scheme.

show abstract

Section: Introductionmentioning

confidence: 99%

Gas-bearing prediction of deep reservoir based on DNN embeddings

Cao

Liu

et al. 2023

Front. Earth Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Coal pay zones were predicted using a variety of machine learning algorithms (LR, SVM, ANN, RF, and XGBoost) and data manipulation methods (NROS and SMOTE) [21]. Bi-directional gated recurrent units and a conditional random field layer (Bi-GRU-CRF) are the models used in the lithological sequence classification technique that was proposed using the neural networks and hidden Markov models (ANN-HMM) hybrid framework [10]. In contrast to the ANN, SVM, AdaBoost, and RF classifiers, the performance of the gradient boosting decision tree (GBDT) classifier was demonstrated and confirmed [22].…”

Section: Page|78mentioning

confidence: 99%

Characterization of Lithfacies Properties of Carbonate Reservoir rocks using Machine Learning Techniques

hamada,

M. Al-khudafi,

A. Al-Sharifi

et al. 2024

Journal of Petroleum and Mining Engineering

View full text Add to dashboard Cite

This study aims to assess the effectiveness of several decision tree machine techniques for identifying formation lithology of complex carbonate reservoir rocks in Gamal oil field. A total of 20966 log data points from four wells were used to create the study's data. Lithology is determined using seven log parameters. The seven log parameters are the density log, neutron log, sonic log, gamma ray log, deep lateral log, shallow lateral log, and resistivity log. Different decision tree-based algorithms for classification approaches were applied. Several typical machine learning models, namely the, Random Forest. Random trees, J48, reduced-error pruning decision trees, logistic model trees, Hoeffding Tree were assessed using well logging data for formation lithology prediction. The obtained results show that the random forest model, out of the proposed decision tree models, performed best at lithology identification, with precession, recall, and F-score values of 0.913, 0.914, and 0.913, respectively. Random trees came next. with average precision, recall, and F1-score of 0.837, 0.84, and 0.837, respectively, the J48 model came in third place. The Hoeffding Tree classification model, however, showed the worst performance. We conclude that boosting strategies enhance the performance of tree-based models. Evaluation of prediction capability of models is also carried out using different datasets.

show abstract

“…Mahmoud and co-workers examined the efficacy of three machine learning models, ANN, adaptive neural fuzzy inference system (ANFIS), and functional neural network (FNN), in real-time lithology prediction during drilling, with both ANFIS and FNN showing high accuracy. Liu et al, Jiang et al, and Sun et al each contributed significantly in 2021. Liu et al proposed a lithology classification algorithm based on Bi-GRU-CRF, integrating it with probabilistic output of SVM, yielding compelling results.…”

Section: Introductionmentioning

confidence: 99%

“…Mahmoud and co-workers 19 examined the efficacy of three machine learning models, ANN, adaptive neural fuzzy inference system (ANFIS), and functional neural network (FNN), in real-time lithology prediction during drilling, with both ANFIS and FNN showing high accuracy. Liu et al, 20 Jiang et al, 21 and Sun et al 22 23 identified lithology using a gradient-boosted decision tree (GBDT) algorithm in 2021, demonstrating excellent classification performance. Kumar et al 24 in 2022 applied a range of supervised machine learning techniques to interpret horizons from geophysical logs, with all models showing over 88% accuracy.…”

Section: Introductionmentioning

confidence: 99%

New Deep Learning Network (Deep Residual Shrinkage Network) Is Applied for Lithology Identification To Search for the Reservoir of CO₂ Geological Storage

Sun,

Zhang,

Zhang

2024

Energy Fuels

View full text Add to dashboard Cite

Lithology identification plays a key role in CO 2 sequestration projects, helping to improve the feasibility, safety, and effectiveness of sequestration projects; therefore, accurate prediction of lithology is critical. The mapping relationship between the logging parameters and lithology complex and the logging response is multi-solution, resulting in inaccurate results of traditional logging lithology identification methods. In this study, we propose an enhanced predictive model for lithology, termed the deep residual shrinkage network (DRSN). This network incorporates a residual network, an attention mechanism, and a soft threshold strategy. The introduction of residual blocks in residual networks addresses the gradient vanishing problem inherent in deep neural networks by allowing the learning of residuals through skip connections. The attention mechanism enhances the focus of the model on crucial input elements, thereby improving its capacity to capture key information. Soft thresholding strategies are employed to eliminate noise from the inputs, enhancing the robustness of the model. Six logging parameters (photoelectric index, density, acoustic, gamma, spontaneous potential, and neutron) are chosen as inputs, with lithology serving as the output of the model. For comparison, we introduce the widely used residual network (ResNet), a classical lightweight network (SqueezeNet), and the convolutional neural network (CNN). Testing on three wells in China's Tarim Oilfield demonstrates that the DRSN model accurately locates reservoirs and identifies lithology more precisely. In lithology prediction for the three wells, DRSN achieved accuracy rates of 90.84, 85.51, and 93.70%, respectively. This research offers a novel approach to lithology prediction in the realm of carbon dioxide geological storage.

show abstract

A lithological sequence classification method with well log via SVM-assisted bi-directional GRU-CRF neural network

Cited by 17 publications

References 14 publications

Gas-bearing prediction of deep reservoir based on DNN embeddings

Gas-bearing prediction of deep reservoir based on DNN embeddings

Characterization of Lithfacies Properties of Carbonate Reservoir rocks using Machine Learning Techniques

New Deep Learning Network (Deep Residual Shrinkage Network) Is Applied for Lithology Identification To Search for the Reservoir of CO₂ Geological Storage

Contact Info

Product

Resources

About

A lithological sequence classification method with well log via SVM-assisted bi-directional GRU-CRF neural network

Cited by 17 publications

References 14 publications

Gas-bearing prediction of deep reservoir based on DNN embeddings

Gas-bearing prediction of deep reservoir based on DNN embeddings

Characterization of Lithfacies Properties of Carbonate Reservoir rocks using Machine Learning Techniques

New Deep Learning Network (Deep Residual Shrinkage Network) Is Applied for Lithology Identification To Search for the Reservoir of CO2 Geological Storage

Contact Info

Product

Resources

About

New Deep Learning Network (Deep Residual Shrinkage Network) Is Applied for Lithology Identification To Search for the Reservoir of CO₂ Geological Storage