Prediction of Reflection Seismic Low-Frequency Components of Acoustic Impedance Using Deep Learning
The unreliable prediction of the low-frequency components from inverted acoustic impedance causes uncertainty in quantitative seismic interpretation. To address this issue, we first calculate various seismic and geological attributes that contain low-frequency information, such as relative geologica...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Minerals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-163X/13/9/1187 |
| _version_ | 1797578673338974208 |
|---|---|
| author | Lian Jiang John P. Castagna Zhao Zhang Brian Russell |
| author_facet | Lian Jiang John P. Castagna Zhao Zhang Brian Russell |
| author_sort | Lian Jiang |
| collection | DOAJ |
| description | The unreliable prediction of the low-frequency components from inverted acoustic impedance causes uncertainty in quantitative seismic interpretation. To address this issue, we first calculate various seismic and geological attributes that contain low-frequency information, such as relative geological age, interval velocity, and integrated instantaneous amplitude. Then, we develop a method to predict the low-frequency content of seismic data using these attributes, their high-frequency components, and recurrent neural networks. Next, we test how to predict the low-frequency components using stacking velocity obtained from velocity analysis. Using all the attributes and seismic data, we propose a supervised deep learning method to predict the low-frequency components of the inverted acoustic impedance. The results obtained in both synthetic and real data cases show that the proposed method can improve the prediction accuracy of the low-frequency components of the inverted acoustic impedance, with the best improvement in a real data example of 57.7% compared with the impedance predicted using well-log interpolation. |
| first_indexed | 2024-03-10T22:26:06Z |
| format | Article |
| id | doaj.art-65efd96d4eb044a6868939e445126e06 |
| institution | Directory Open Access Journal |
| issn | 2075-163X |
| language | English |
| last_indexed | 2024-03-10T22:26:06Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Minerals |
| spelling | doaj.art-65efd96d4eb044a6868939e445126e062023-11-19T12:05:32ZengMDPI AGMinerals2075-163X2023-09-01139118710.3390/min13091187Prediction of Reflection Seismic Low-Frequency Components of Acoustic Impedance Using Deep LearningLian Jiang0John P. Castagna1Zhao Zhang2Brian Russell3Department of Earth and Atmospheric Sciences, University of Houston, Houston, TX 77204, USADepartment of Earth and Atmospheric Sciences, University of Houston, Houston, TX 77204, USAChevron, Houston, TX 77002, USAGeoSoftware, Calgary, AB T2R 0C6, CanadaThe unreliable prediction of the low-frequency components from inverted acoustic impedance causes uncertainty in quantitative seismic interpretation. To address this issue, we first calculate various seismic and geological attributes that contain low-frequency information, such as relative geological age, interval velocity, and integrated instantaneous amplitude. Then, we develop a method to predict the low-frequency content of seismic data using these attributes, their high-frequency components, and recurrent neural networks. Next, we test how to predict the low-frequency components using stacking velocity obtained from velocity analysis. Using all the attributes and seismic data, we propose a supervised deep learning method to predict the low-frequency components of the inverted acoustic impedance. The results obtained in both synthetic and real data cases show that the proposed method can improve the prediction accuracy of the low-frequency components of the inverted acoustic impedance, with the best improvement in a real data example of 57.7% compared with the impedance predicted using well-log interpolation.https://www.mdpi.com/2075-163X/13/9/1187low frequenciesacoustic impedancedeep learningGRUseismic attributesseismic inversion |
| spellingShingle | Lian Jiang John P. Castagna Zhao Zhang Brian Russell Prediction of Reflection Seismic Low-Frequency Components of Acoustic Impedance Using Deep Learning Minerals low frequencies acoustic impedance deep learning GRU seismic attributes seismic inversion |
| title | Prediction of Reflection Seismic Low-Frequency Components of Acoustic Impedance Using Deep Learning |
| title_full | Prediction of Reflection Seismic Low-Frequency Components of Acoustic Impedance Using Deep Learning |
| title_fullStr | Prediction of Reflection Seismic Low-Frequency Components of Acoustic Impedance Using Deep Learning |
| title_full_unstemmed | Prediction of Reflection Seismic Low-Frequency Components of Acoustic Impedance Using Deep Learning |
| title_short | Prediction of Reflection Seismic Low-Frequency Components of Acoustic Impedance Using Deep Learning |
| title_sort | prediction of reflection seismic low frequency components of acoustic impedance using deep learning |
| topic | low frequencies acoustic impedance deep learning GRU seismic attributes seismic inversion |
| url | https://www.mdpi.com/2075-163X/13/9/1187 |
| work_keys_str_mv | AT lianjiang predictionofreflectionseismiclowfrequencycomponentsofacousticimpedanceusingdeeplearning AT johnpcastagna predictionofreflectionseismiclowfrequencycomponentsofacousticimpedanceusingdeeplearning AT zhaozhang predictionofreflectionseismiclowfrequencycomponentsofacousticimpedanceusingdeeplearning AT brianrussell predictionofreflectionseismiclowfrequencycomponentsofacousticimpedanceusingdeeplearning |