Recurrent neural network: application in facies classification

Miao, Tian; Verma, Sumit

doi:10.1016/b978-0-12-822295-9.00013-3

Cited by 4 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In model-driven methods, time-series transforms are generally implemented to provide nonredundant insights into the underlying prior properties of seismic data [7], [8], including time-domain [1], [9]- [12], time-frequency-domain [13]- [17], and frequency-domain [1], [18]- [20]. In contrast, data-driven methods are aimed at automatically learning local patterns in seismic data without prior knowledge or assumptions, which builds upon the learning capability of the autoencoder [21]- [26], or recurrent network [27]- [29]. Thereafter, isolated learning-based SFA achieves SFA via multifarious feature clustering algorithms such as centroid-based clustering [30]- [35], [36], probabilistic model clustering [37]- [39], and spectral clustering [11], [40], [41].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder

Hua,

Qian,

Zhang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder

Hua,

Qian,

Zhang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Harvesting Earth's heat: A deep learning Odyssey for reservoir characterization and sustainable geothermal energy management

Ullah,

Li,

Förster

et al. 2024

Geoenergy Science and Engineering

View full text Add to dashboard Cite

Attention mechanism‐assisted recurrent neural network for well log lithology classification

Gao,

Tian,

Grana

et al. 2024

Geophysical Prospecting

View full text Add to dashboard Cite

Lithology classification is a fundamental aspect of reservoir classification. Due to the limited availability of core samples, computational modelling methods for lithology classification based on indirect measurements are required. The main challenge for standard clustering methods is the complex vertical dependency of sedimentological sequences as well as the spatial coupling of well logs. Machine learning methods, such as recurrent neural networks, long short‐term memory and bidirectional long short‐term memory, can account for the spatial correlation of the measured data and the predicted model. Based on these developments, we propose a novel approach using two distinct models: a self‐attention‐assisted bidirectional long short‐term memory model and a multi‐head attention‐based bidirectional long short‐term memory model. These models consider spatial continuity and adaptively adjust the weight in each step to improve the classification using the attention mechanism. The proposed method is tested on a set of real well logs with limited training data obtained from core samples. The prediction results from the proposed models and the benchmark one are compared in terms of the accuracy of lithology classification. Additionally, the weight matrices from both attention mechanisms are visualized to elucidate the correlations between depth steps and to help analyse how these mechanisms contribute to improved prediction accuracy. The study shows that the proposed multi‐head attention‐based bidirectional long short‐term memory model improves classification, especially for thin layers.

show abstract

Recurrent neural network: application in facies classification

Cited by 4 publications

References 35 publications

Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder

Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder

Harvesting Earth's heat: A deep learning Odyssey for reservoir characterization and sustainable geothermal energy management

Attention mechanism‐assisted recurrent neural network for well log lithology classification

Contact Info

Product

Resources

About