A Seq2Seq Model Improved by Transcendental Learning and Imaged Sequence Samples for Porosity Prediction
Since the accurate prediction of porosity is one of the critical factors for estimating oil and gas reservoirs, a novel porosity prediction method based on Imaged Sequence Samples (ISS) and a Sequence to Sequence (Seq2Seq) model fused by Transcendental Learning (TL) is proposed using well-logging da...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/11/1/39 |
_version_ | 1797625329771085824 |
---|---|
author | Lijian Zhou Lijun Wang Zhiang Zhao Yuwei Liu Xiwu Liu |
author_facet | Lijian Zhou Lijun Wang Zhiang Zhao Yuwei Liu Xiwu Liu |
author_sort | Lijian Zhou |
collection | DOAJ |
description | Since the accurate prediction of porosity is one of the critical factors for estimating oil and gas reservoirs, a novel porosity prediction method based on Imaged Sequence Samples (ISS) and a Sequence to Sequence (Seq2Seq) model fused by Transcendental Learning (TL) is proposed using well-logging data. Firstly, to investigate the correlation between logging features and porosity, the original logging features are normalized and selected by computing their correlation with porosity to obtain the point samples. Secondly, to better represent the depositional relations with depths, an ISS set is established by slidingly grouping sample points across depth, and the selected logging features are in a row. Therefore, spatial relations among the features are established along the vertical and horizontal directions. Thirdly, since the Seq2Seq model can better extract the spatio-temporal information of the input data than the Bidirectional Gate Recurrent Unit (BGRU), the Seq2Seq model is introduced for the first time to address the logging data and predict porosity. The experimental results show that it can achieve superior prediction results than state-of-the-art. However, the cumulative bias is likely to appear when using the Seq2Seq model. Motivated by teacher forcing, the idea of TL is proposed to be incorporated into the decoding process of Seq2Seq, named the TL-Seq2Seq model. The self-well and inter-well experimental results show that the proposed approach can significantly improve the accuracy of porosity prediction. |
first_indexed | 2024-03-11T09:55:02Z |
format | Article |
id | doaj.art-6df1575160634b71915f5b5e6f9b6c06 |
institution | Directory Open Access Journal |
issn | 2227-7390 |
language | English |
last_indexed | 2024-03-11T09:55:02Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Mathematics |
spelling | doaj.art-6df1575160634b71915f5b5e6f9b6c062023-11-16T15:52:34ZengMDPI AGMathematics2227-73902022-12-011113910.3390/math11010039A Seq2Seq Model Improved by Transcendental Learning and Imaged Sequence Samples for Porosity PredictionLijian Zhou0Lijun Wang1Zhiang Zhao2Yuwei Liu3Xiwu Liu4School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266525, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao 266525, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao 266525, ChinaSinoPEC Petroleum Exploration and Production Research Institute, Beijing 100083, ChinaSinoPEC Petroleum Exploration and Production Research Institute, Beijing 100083, ChinaSince the accurate prediction of porosity is one of the critical factors for estimating oil and gas reservoirs, a novel porosity prediction method based on Imaged Sequence Samples (ISS) and a Sequence to Sequence (Seq2Seq) model fused by Transcendental Learning (TL) is proposed using well-logging data. Firstly, to investigate the correlation between logging features and porosity, the original logging features are normalized and selected by computing their correlation with porosity to obtain the point samples. Secondly, to better represent the depositional relations with depths, an ISS set is established by slidingly grouping sample points across depth, and the selected logging features are in a row. Therefore, spatial relations among the features are established along the vertical and horizontal directions. Thirdly, since the Seq2Seq model can better extract the spatio-temporal information of the input data than the Bidirectional Gate Recurrent Unit (BGRU), the Seq2Seq model is introduced for the first time to address the logging data and predict porosity. The experimental results show that it can achieve superior prediction results than state-of-the-art. However, the cumulative bias is likely to appear when using the Seq2Seq model. Motivated by teacher forcing, the idea of TL is proposed to be incorporated into the decoding process of Seq2Seq, named the TL-Seq2Seq model. The self-well and inter-well experimental results show that the proposed approach can significantly improve the accuracy of porosity prediction.https://www.mdpi.com/2227-7390/11/1/39porosity predictiondeep learningtranscendental learningimaged sequence sampleslogging data |
spellingShingle | Lijian Zhou Lijun Wang Zhiang Zhao Yuwei Liu Xiwu Liu A Seq2Seq Model Improved by Transcendental Learning and Imaged Sequence Samples for Porosity Prediction Mathematics porosity prediction deep learning transcendental learning imaged sequence samples logging data |
title | A Seq2Seq Model Improved by Transcendental Learning and Imaged Sequence Samples for Porosity Prediction |
title_full | A Seq2Seq Model Improved by Transcendental Learning and Imaged Sequence Samples for Porosity Prediction |
title_fullStr | A Seq2Seq Model Improved by Transcendental Learning and Imaged Sequence Samples for Porosity Prediction |
title_full_unstemmed | A Seq2Seq Model Improved by Transcendental Learning and Imaged Sequence Samples for Porosity Prediction |
title_short | A Seq2Seq Model Improved by Transcendental Learning and Imaged Sequence Samples for Porosity Prediction |
title_sort | seq2seq model improved by transcendental learning and imaged sequence samples for porosity prediction |
topic | porosity prediction deep learning transcendental learning imaged sequence samples logging data |
url | https://www.mdpi.com/2227-7390/11/1/39 |
work_keys_str_mv | AT lijianzhou aseq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT lijunwang aseq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT zhiangzhao aseq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT yuweiliu aseq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT xiwuliu aseq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT lijianzhou seq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT lijunwang seq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT zhiangzhao seq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT yuweiliu seq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction AT xiwuliu seq2seqmodelimprovedbytranscendentallearningandimagedsequencesamplesforporosityprediction |