Synthetic seismic data for training deep learning networks

Merrifield, Tom P.; Griffith, Donald P.; Zamanian, S. Ahmad; Gesbert, Stéphane; Sen, Suvrajeet; Guzman, Jorge De La Torre; Potter, R. David; Kuehl, Henning

doi:10.1190/int-2021-0193.1

Cited by 3 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has been used for seismic signal processing (Baardman & Hegge, 2021; Vinard et al., 2022; Yu et al., 2019; Wang et al., 2020), imaging and inversion (Aleardi & Salusti, 2021; Roethe & Tarantola, 1991; Ruiz et al., 2021; Sun et al., 2020; Wang et al., 2021; Zhang & Alkhalifah, 2019; Zhang & Gao, 2021) and seismic data interpretation (Durall et al., 2021; Duan et al., 2019; Grana et al., 2020; Li et al., 2020; Merrifield et al., 2022; Tschannen et al., 2020; Vizeu et al., 2022; Wu et al., 2020). Existing studies have shown that training datasets play an important role in deep learning.…”

Section: Introductionmentioning

confidence: 99%

Generating complete synthetic datasets for high‐resolution amplitude‐versus‐offset attributes deep learning inversion

Nie

Wang

Han

et al. 2023

Geophysical Prospecting

View full text Add to dashboard Cite

Deep learning has been used in seismic exploration to solve seismic inversion problems, however it requires sufficient and diverse training samples and labels to obtain satisfactory results. Insufficient training labels are a common problem since labels usually come from well‐logging data, which are limited and sparsely distributed. This can result in a trained network with poor generalizability. A novel complete synthetic dataset‐driven method utilizing convolutional neural network is presented for seismic amplitude‐versus‐offset attributes P and G inversion. Gaussian simulation sampling with physical constraints is used to generate a complete elastic parameter dataset by traversing the entire elastic parameter model space. By randomly combining elastic parameters from the full elastic parameters model space, sufficient synthetic pre‐stack amplitude‐versus‐offset gathers and attribute datasets are generated for training the convolutional neural network. Compared with the limited real data‐driven convolutional neural network, the complete synthetic dataset‐driven convolutional neural network has better generalizability. Broadband training labels improve the accuracy and resolution of the complete synthetic dataset‐driven convolutional neural network's inversion results beyond that of the conventional least‐square data‐fitting method. The complete synthetic dataset‐driven convolutional neural network is robust for processing noise‐contaminated seismic data, but if the frequency band of the labels for training the network is too wide and the signal‐to‐noise ratio of pre‐stack amplitude‐versus‐offset gathers is too low, the quality of the inversion results will reduce. The Marmousi II model and field data examples show that the novel complete synthetic dataset‐driven convolutional neural network can extract higher‐resolution amplitude‐versus‐offset attributes P and G.

show abstract

Section: Introductionmentioning

confidence: 99%

Generating complete synthetic datasets for high‐resolution amplitude‐versus‐offset attributes deep learning inversion

Nie

Wang

Han

et al. 2023

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

Addressing Uncertainty on Machine Learning Models for Long-Period Fiber Grating Signal Conditioning Using Monte Carlo Method

Barino,

Santos

2024

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Using a synthetic data trained convolutional neural network for predicting subresolution thin layers from seismic data

Mosegaard

Feng

et al. 2023

Interpretation

View full text Add to dashboard Cite

Numerous studies have demonstrated the capability of supervised deep learning techniques for predicting geologic features of interest from seismic sections, including features that are difficult to identify using traditional interpretation methods. However, the successful application of these techniques in practice has been limited by the difficulty of obtaining a large training data set where the seismic data and corresponding ground truth labels are well-defined. Manually creating large amounts of labels requires a heavy workload, and the uncertainty of the interpretation and labeling process decreases the model’s ability for making accurate predictions. Using the chalk-flint sequence scenario onshore Denmark as an example, we have developed a novel workflow for predicting subresolution thin layers from seismic sections. It entails generating large quantities of synthetic training data with high-quality labels using stochastic geologic modeling, training a convolutional neural network based on the synthetic data set, and applying it to real seismic data. This is, to our knowledge, the first example of using deep learning to predict subresolution thin layers from seismic data based on geostatistically generated training images. It is shown that a neural network trained on synthetic data can predict a realistic number of subresolution flint layers from the real seismic data that have been collected from the Stevns region in Denmark, which has value for the understanding of the overall geologic characteristics of succession and engineering applications such as construction site evaluation.

show abstract

Synthetic seismic data for training deep learning networks

Cited by 3 publications

References 10 publications

Generating complete synthetic datasets for high‐resolution amplitude‐versus‐offset attributes deep learning inversion

Generating complete synthetic datasets for high‐resolution amplitude‐versus‐offset attributes deep learning inversion

Addressing Uncertainty on Machine Learning Models for Long-Period Fiber Grating Signal Conditioning Using Monte Carlo Method

Using a synthetic data trained convolutional neural network for predicting subresolution thin layers from seismic data

Contact Info

Product

Resources

About