Gas reservoir segmentation in 2D onshore seismics using LSTM-AutoEncoder

Andrade, Felipe; Santos, Lívia Fajin de Mello dos; Gattass, Marcelo; Quevedo, Roberto; Michelon, Diogo; Siedschlag, Carlos; Ribeiro, Roberto

doi:10.1190/segam2021-3584077.1

Cited by 4 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later on, [Santos et al 2020] proposed the use of transfer learning techniques to expand existing classifier and apply it to different type of seismic surveys into Parnaíba Basin. Moreover, in order to check that methodology based on seismic trace, other networks based on different architectures were developed using an improved encoder-decoder LSTM [Andrade et al 2021] and a Transformer neural network [Dias et al 2021]. All those networks have been implemented in ALINE, a computational tool for the assessment of gas accumulations [Santos et al 2021].…”

Section: Introductionmentioning

confidence: 99%

PSO-based ViT-Seismic: A Vision Transformer Approach for Gas Detection in Seismic Images

Dias

Cruz

Diniz³

et al. 2022

Anais Da X Escola Regional De Computação Do Ceará, Maranhão E Piauí (ERCEMAPI 2022)

View full text Add to dashboard Cite

Seismic reflection is one of the geophysical methods most used in the oil and gas (O&G) industry for hydrocarbon prospecting. In particular, for some Brazilian onshore fields, such a method has been used for estimating the location and volume of gas accumulations. However, the analysis and interpretation of seismic data is time-consuming due to the large amount of information and the noisy nature of the acquisitions. In order to help geoscientists in those tasks, computational tools based on machine learning have been proposed considering Direct Hydrocarbon Indicators (DHIs). In this study, we present a methodology for detection of gas accumulations based on vision Transformer neural network (ViT) and Particle Swarm Optimization (PSO) scheme. In the best scenario, the proposed method achieved a sensitivity of 75.14%, a specificity of 96.14% and an accuracy of 95.60%. We present some tests performed on Parnaíba Basin which demonstrate that the proposed method is promising for gas exploration.

show abstract

Section: Introductionmentioning

confidence: 99%

PSO-based ViT-Seismic: A Vision Transformer Approach for Gas Detection in Seismic Images

Dias

Cruz

Diniz³

et al. 2022

Anais Da X Escola Regional De Computação Do Ceará, Maranhão E Piauí (ERCEMAPI 2022)

View full text Add to dashboard Cite

show abstract

“…Specifically, methods based on Deep learning models, DL, have been used for the analysis of seismic images in order to obtain interpretations that help in the exploration of hydrocarbon deposits, these methods are applied to different environments that have specifics and particular features. Within these models are those developed for the indication of natural gas reservoirs in 2D seismic images (Alfarhan et al, 2020b,a;Andrade et al, 2021;Fernando Santos et al, 2020;Pan et al, 2021a;Wang et al, 2018).…”

Section: List Of Abbreviationsmentioning

confidence: 99%

“…In this step we use the method proposed by Andrade et al (2021) for gas reservoir indication. This method consists of two steps.…”

Section: Encoder-decodermentioning

confidence: 99%

“…Additionally, a connection layer called Time Distributed is used that resizes the final encoder data to have the output layer size. For more details see Andrade et al (2021).…”

Section: Encoder-decodermentioning

confidence: 99%

“…Two different DL networks will demonstrate this property. The first model used was proposed by Andrade et al (2021) based on an LSTM network. A GRU (Section 2.3.2) replaces the neural network in the second model.…”

Section: Deep Learning Model Trainingmentioning

confidence: 99%

See 2 more Smart Citations

Generalization of the Deep Learning Model for Natural Gas Indication in 2d Seismic Image Based on the Training Dataset and the Operational Hyper Parameters Recommendation

FERNANDO MARIN SEPULVEDA

View full text Add to dashboard Cite

I especially thank my advisors whose example, guidance and constant support have made me a better professional and human. Likewise, I thank my colleagues, both from Rio de Janeiro and São Luís, since their constant help has allowed me to advance. Finally, I thank my dear family, who at all times in my life have supported me and encouraged me to overcome any obstacle.To all of you my most sincere thanks.

show abstract

Generating extremely low-dimensional representation of subsurface earth models using vector quantization and deep Autoencoder

Falola,

Churilova,

Liu

et al. 2024

Petroleum Research

View full text Add to dashboard Cite

Gas reservoir segmentation in 2D onshore seismics using LSTM-AutoEncoder

Cited by 4 publications

References 6 publications

PSO-based ViT-Seismic: A Vision Transformer Approach for Gas Detection in Seismic Images

PSO-based ViT-Seismic: A Vision Transformer Approach for Gas Detection in Seismic Images

Generalization of the Deep Learning Model for Natural Gas Indication in 2d Seismic Image Based on the Training Dataset and the Operational Hyper Parameters Recommendation

Generating extremely low-dimensional representation of subsurface earth models using vector quantization and deep Autoencoder

Contact Info

Product

Resources

About