Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networks
Well log prediction while drilling estimates the rock properties ahead of drilling bits. A reliable well log prediction is able to assist reservoir engineers in updating the geological models and adjusting the drilling strategy if necessary. This is of great significance in reducing the drilling ris...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/feart.2023.1153619/full |
| _version_ | 1827906089767665664 |
|---|---|
| author | Heng Wang Heng Wang Yungui Xu Yungui Xu Shuhang Tang Shuhang Tang Lei Wu Weiping Cao Weiping Cao Xuri Huang Xuri Huang |
| author_facet | Heng Wang Heng Wang Yungui Xu Yungui Xu Shuhang Tang Shuhang Tang Lei Wu Weiping Cao Weiping Cao Xuri Huang Xuri Huang |
| author_sort | Heng Wang |
| collection | DOAJ |
| description | Well log prediction while drilling estimates the rock properties ahead of drilling bits. A reliable well log prediction is able to assist reservoir engineers in updating the geological models and adjusting the drilling strategy if necessary. This is of great significance in reducing the drilling risk and saving costs. Conventional interactive integration of geophysical data and geological understanding is the primary approach to realize well log prediction while drilling. In this paper, we propose a new artificial intelligence approach to make the well log prediction while drilling by integrating seismic impedance with three neural networks: LSTM, Bidirectional LSTM (Bi-LSTM), and Double Chain LSTM (DC-LSTM). The DC-LSTM is a new LSTM network proposed in this study while the other two are existing ones. These three networks are thoroughly adapted, compared, and tested to fit the artificial intelligent prediction process. The prediction approach can integrate not only seismic information of the sedimentary formation around the drilling bit but also the rock property changing trend through the upper and lower formations. The Bi-LSTM and the DC-LSTM networks achieve higher prediction accuracy than the LSTM network. Additionally, the DC-LSTM approach significantly promotes prediction efficiency by reducing the number of training parameters and saving computational time without compromising prediction accuracy. The field data application of the three networks, LSTM, Bi-LSTM, and DC-LSTM, demonstrates that prediction accuracy based on the Bi-LSTM and DC-LSTM is higher than that of the LSTM, and DC-LSTM has the highest efficiency overall. |
| first_indexed | 2024-03-13T00:51:43Z |
| format | Article |
| id | doaj.art-dd6ccd8014014a728123cef9717f3ad8 |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-03-13T00:51:43Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-dd6ccd8014014a728123cef9717f3ad82023-07-07T14:01:36ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632023-07-011110.3389/feart.2023.11536191153619Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networksHeng Wang0Heng Wang1Yungui Xu2Yungui Xu3Shuhang Tang4Shuhang Tang5Lei Wu6Weiping Cao7Weiping Cao8Xuri Huang9Xuri Huang10State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, ChinaSchool of Geosciences and Technology, Southwest Petroleum University, Chengdu, ChinaState Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, ChinaSchool of Geosciences and Technology, Southwest Petroleum University, Chengdu, ChinaState Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, ChinaSchool of Geosciences and Technology, Southwest Petroleum University, Chengdu, ChinaShale Gas Project Management Department of CNPC Chuanqing Drilling Engineering Co., Ltd., Chengdu, ChinaState Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, ChinaSchool of Geosciences and Technology, Southwest Petroleum University, Chengdu, ChinaState Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, ChinaSchool of Geosciences and Technology, Southwest Petroleum University, Chengdu, ChinaWell log prediction while drilling estimates the rock properties ahead of drilling bits. A reliable well log prediction is able to assist reservoir engineers in updating the geological models and adjusting the drilling strategy if necessary. This is of great significance in reducing the drilling risk and saving costs. Conventional interactive integration of geophysical data and geological understanding is the primary approach to realize well log prediction while drilling. In this paper, we propose a new artificial intelligence approach to make the well log prediction while drilling by integrating seismic impedance with three neural networks: LSTM, Bidirectional LSTM (Bi-LSTM), and Double Chain LSTM (DC-LSTM). The DC-LSTM is a new LSTM network proposed in this study while the other two are existing ones. These three networks are thoroughly adapted, compared, and tested to fit the artificial intelligent prediction process. The prediction approach can integrate not only seismic information of the sedimentary formation around the drilling bit but also the rock property changing trend through the upper and lower formations. The Bi-LSTM and the DC-LSTM networks achieve higher prediction accuracy than the LSTM network. Additionally, the DC-LSTM approach significantly promotes prediction efficiency by reducing the number of training parameters and saving computational time without compromising prediction accuracy. The field data application of the three networks, LSTM, Bi-LSTM, and DC-LSTM, demonstrates that prediction accuracy based on the Bi-LSTM and DC-LSTM is higher than that of the LSTM, and DC-LSTM has the highest efficiency overall.https://www.frontiersin.org/articles/10.3389/feart.2023.1153619/fullmachine learninglong short-term memorywell log predictiondrilling bitseismic impedanceneural networks |
| spellingShingle | Heng Wang Heng Wang Yungui Xu Yungui Xu Shuhang Tang Shuhang Tang Lei Wu Weiping Cao Weiping Cao Xuri Huang Xuri Huang Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networks Frontiers in Earth Science machine learning long short-term memory well log prediction drilling bit seismic impedance neural networks |
| title | Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networks |
| title_full | Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networks |
| title_fullStr | Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networks |
| title_full_unstemmed | Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networks |
| title_short | Well log prediction while drilling using seismic impedance with an improved LSTM artificial neural networks |
| title_sort | well log prediction while drilling using seismic impedance with an improved lstm artificial neural networks |
| topic | machine learning long short-term memory well log prediction drilling bit seismic impedance neural networks |
| url | https://www.frontiersin.org/articles/10.3389/feart.2023.1153619/full |
| work_keys_str_mv | AT hengwang welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT hengwang welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT yunguixu welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT yunguixu welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT shuhangtang welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT shuhangtang welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT leiwu welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT weipingcao welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT weipingcao welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT xurihuang welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks AT xurihuang welllogpredictionwhiledrillingusingseismicimpedancewithanimprovedlstmartificialneuralnetworks |