Petrophysical-property estimation from seismic data using recurrent neural networks

Alfarraj, Motaz; AlRegib, Ghassan

doi:10.1190/segam2018-2995752.1

Cited by 62 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given that well-log data is limited in a given survey area, the number of training samples is limited. With such limitation, a combination of regularization techniques must be used to train a learningbased model properly and ensure it generalizes beyond the training dataset (Alfarraj and AlRegib, 2018). In addition, the data shortage limits the number of the layers (and hence parameters) that can be used in learning-based models.…”

Section: Methodsmentioning

confidence: 99%

“…Unlike feed-forward neural networks, RNNs have a hidden state variable that can be passed between sequence samples which allows them to capture long temporal dependencies in sequential data. RNNs have been utilized to solve many problems in language modeling and natural language processing (NLP) (Mikolov et al, 2010), speech and audio processing (Graves et al, 2013), video processing (Ma et al, 2017), petrophysical property estimation (Alfarraj and AlRegib, 2018), detection of natural earthquakes (Wiszniowski et al, 2014), and stacking velocity estimation (Biswas et al, 2018).…”

Section: Recurrent Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Semi-supervised Sequence Modeling for Elastic Impedance Inversion

Alfarraj,

AlRegib

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Recent applications of machine learning algorithms in the seismic domain have shown great potential in different areas such as seismic inversion and interpretation. However, such algorithms rarely enforce geophysical constraints; the lack of which might lead to undesirable results. To overcome this issue, we propose a semi-supervised sequence modeling framework based on recurrent neural networks for elastic inversion from multi-angle seismic data. Specifically, seismic traces and elastic impedance traces are modeled as time series. Then, a neural-network-based inversion model comprising convolutional and recurrent neural layers is used to invert seismic data for elastic impedance. The proposed workflow uses well-log data to guide the inversion. In addition, it utilizes seismic forward modeling to regularize the training, and to serve as a geophysical constraint for the inversion. The proposed workflow achieves an average correlation of 98% between the estimated and target elastic impedance using 10 well-logs for training on a synthetic dataset.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Recurrent Neural Networkmentioning

confidence: 99%

Semi-supervised Sequence Modeling for Elastic Impedance Inversion

Alfarraj,

AlRegib

2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Alfarraj and AlRegib proposed [32] a recurrent network architecture to perform estimation of petrophysical characteristic of the subsurface in a way that the well log data transfer into the seismic scale. This is a major contribution since it is difficult to match seismic data and well logs, given the different scales and the sparsity of well data.…”

Section: Semblance Velocity Analysismentioning

confidence: 99%

Deep Learning for Seismic Inverse Problems: Toward the Acceleration of Geophysical Analysis Workflows

Adler¹,

Araya‐Polo²,

Poggio³

2021

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

Seismic inversion is a fundamental tool in geophysical analysis, providing a window into the Earth. In particular, it enables the reconstruction of large scale subsurface earth models for hydrocarbon exploration, mining, earthquakes analysis, shallow hazard assessment and other geophysical tasks. This article provides a comprehensive and timely overview of emerging datadriven Deep Learning (DL) solutions to seismic inverse problems, including velocity, impedance, reflectivity model building and seismic bandwidth extension. The article reviews seismic wave propagation and signal acquisition principles using large scale sensor arrays in offshore and inland exploration. In addition, the relations between the seismic forward and inverse problems are established, and prominent model-based solutions including seismic tomography, Full-Waveform Inversion (FWI) and multiscale FWI are explained. A primer to DL principles is presented, including empirical risk minimization, stochastic gradient-based learning, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN) and regularization. The article then presents DL-based solutions addressing full seismic inversion as well as DL-assisted FWI solutions including Encoder-Decoder architectures, CNN-based networks and RNN-based networks with Long Short Term Memory and Gated Recurrent Units. Seismic signals features extraction methods such as semblance velocity analysis and seismic spectrograms are discussed, as well as batch vs. sequential data processing architectures. The article further presents advanced solutions based on Generative Adversarial Networks , and Physics-guided DL architectures that incorporate numerical geophysical modeling into the DL training loop, enabling unsupervised and semi-supervised learning.

show abstract

“…Talarico, Leäo, and Grana (2019) applied LSTM to model sedimentological sequences and compared the model to baseline hidden Markov model (HMM), concluding that RNNs outperform HMMs based on first-order Markov chains, while higher order Markov chains were too complex to calibrate satisfactorily. Gated recurrent unit (GRU) ( Cho et al, 2014 ) is another RNN developed based on the insights into LSTM, which was applied to predict petrophysical properties from seismic data ( Alfarraj & AlRegib, 2018 ).…”

Section: Contemporary Machine Learning In Geosciencementioning

confidence: 99%

70 years of machine learning in geoscience in review

Dramsch

2020

Advances in Geophysics

181

View full text Add to dashboard Cite

This review gives an overview of the development of machine learning in geoscience. A thorough analysis of the codevelopments of machine learning applications throughout the last 70 years relates the recent enthusiasm for machine learning to developments in geoscience. I explore the shift of kriging toward a mainstream machine learning method and the historic application of neural networks in geoscience, following the general trend of machine learning enthusiasm through the decades. Furthermore, this chapter explores the shift from mathematical fundamentals and knowledge in software development toward skills in model validation, applied statistics, and integrated subject matter expertise. The review is interspersed with code examples to complement the theoretical foundations and illustrate model validation and machine learning explainability for science. The scope of this review includes various shallow machine learning methods, e.g., decision trees, random forests, support-vector machines, and Gaussian processes, as well as, deep neural networks, including feed-forward neural networks, convolutional neural networks, recurrent neural networks, and generative adversarial networks. Regarding geoscience, the review has a bias toward geophysics but aims to strike a balance with geochemistry, geostatistics, and geology, however, excludes remote sensing, as this would exceed the scope. In general, I aim to provide context for the recent enthusiasm surrounding deep learning with respect to research, hardware, and software developments that enable successful application of shallow and deep machine learning in all disciplines of Earth science.

show abstract

Petrophysical-property estimation from seismic data using recurrent neural networks

Cited by 62 publications

References 12 publications

Semi-supervised Sequence Modeling for Elastic Impedance Inversion

Semi-supervised Sequence Modeling for Elastic Impedance Inversion

Deep Learning for Seismic Inverse Problems: Toward the Acceleration of Geophysical Analysis Workflows

70 years of machine learning in geoscience in review

Contact Info

Product

Resources

About