Application of BiLSTM in Lithology Identification of Beach-Bar Sand Reservoir
The tight beach-bar sand reservoir in the study area has rich petroleum reserves and high exploration and development potential. However, it is characterized by deep burial, thin single-layer thickness, ultra-low permeability, complex pore structure, and extremely low natural productivity of the sin...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Well Logging Technology
2023-06-01
|
| Series: | Cejing jishu |
| Subjects: | |
| Online Access: | https://www.cnpcwlt.com/#/digest?ArticleID=5493 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849328137101377536 |
|---|---|
| author | CHEN Ganghua ZHANG Yuxia WANG Jun ZHANG Huafeng WANG Youwen |
| author_facet | CHEN Ganghua ZHANG Yuxia WANG Jun ZHANG Huafeng WANG Youwen |
| author_sort | CHEN Ganghua |
| collection | DOAJ |
| description | The tight beach-bar sand reservoir in the study area has rich petroleum reserves and high exploration and development potential. However, it is characterized by deep burial, thin single-layer thickness, ultra-low permeability, complex pore structure, and extremely low natural productivity of the single well and it is difficult to classify the reservoir and identify the lithology. Based on the characteristic of time sequence logging data, a bi-directional long short-term memory neural network (BiLSTM) lithology identification model is constructed. The Random Forest method is used to conduct feature selection for conventional logging parameters and other parameters. The selected parameters are used as input variables to train the BiLSTM model. The model is applied to validate the well data of the test set, and the results showed that the accuracy of the model is 0.86, achieving good application results. This proves that BiLSTM model is suitable for the lithology identification of the beach-bar sand reservoir. |
| format | Article |
| id | doaj-art-bb2d16f4ab2f4be5a396c12c9017f74c |
| institution | Kabale University |
| issn | 1004-1338 |
| language | zho |
| publishDate | 2023-06-01 |
| publisher | Editorial Office of Well Logging Technology |
| record_format | Article |
| series | Cejing jishu |
| spelling | doaj-art-bb2d16f4ab2f4be5a396c12c9017f74c2025-08-20T03:47:40ZzhoEditorial Office of Well Logging TechnologyCejing jishu1004-13382023-06-0147331932510.16489/j.issn.1004-1338.2023.03.0101004-1338(2023)03-0319-07Application of BiLSTM in Lithology Identification of Beach-Bar Sand ReservoirCHEN Ganghua0ZHANG Yuxia1WANG Jun2ZHANG Huafeng3WANG Youwen4School of Geosciences, China University of Petroleum, Qingdao, Shandong 266580, ChinaSchool of Geosciences, China University of Petroleum, Qingdao, Shandong 266580, ChinaShengli Oil Field Exploration and Development Research Institute, Dongying, Shandong 257015, ChinaSchool of Geosciences, China University of Petroleum, Qingdao, Shandong 266580, ChinaShengli Oil Field Exploration and Development Research Institute, Dongying, Shandong 257015, ChinaThe tight beach-bar sand reservoir in the study area has rich petroleum reserves and high exploration and development potential. However, it is characterized by deep burial, thin single-layer thickness, ultra-low permeability, complex pore structure, and extremely low natural productivity of the single well and it is difficult to classify the reservoir and identify the lithology. Based on the characteristic of time sequence logging data, a bi-directional long short-term memory neural network (BiLSTM) lithology identification model is constructed. The Random Forest method is used to conduct feature selection for conventional logging parameters and other parameters. The selected parameters are used as input variables to train the BiLSTM model. The model is applied to validate the well data of the test set, and the results showed that the accuracy of the model is 0.86, achieving good application results. This proves that BiLSTM model is suitable for the lithology identification of the beach-bar sand reservoir.https://www.cnpcwlt.com/#/digest?ArticleID=5493log interpretationdeep learningbi-directional long short-term memory neural network (bilstm)lithology identificationbeach-bar sand reservoir |
| spellingShingle | CHEN Ganghua ZHANG Yuxia WANG Jun ZHANG Huafeng WANG Youwen Application of BiLSTM in Lithology Identification of Beach-Bar Sand Reservoir Cejing jishu log interpretation deep learning bi-directional long short-term memory neural network (bilstm) lithology identification beach-bar sand reservoir |
| title | Application of BiLSTM in Lithology Identification of Beach-Bar Sand Reservoir |
| title_full | Application of BiLSTM in Lithology Identification of Beach-Bar Sand Reservoir |
| title_fullStr | Application of BiLSTM in Lithology Identification of Beach-Bar Sand Reservoir |
| title_full_unstemmed | Application of BiLSTM in Lithology Identification of Beach-Bar Sand Reservoir |
| title_short | Application of BiLSTM in Lithology Identification of Beach-Bar Sand Reservoir |
| title_sort | application of bilstm in lithology identification of beach bar sand reservoir |
| topic | log interpretation deep learning bi-directional long short-term memory neural network (bilstm) lithology identification beach-bar sand reservoir |
| url | https://www.cnpcwlt.com/#/digest?ArticleID=5493 |
| work_keys_str_mv | AT chenganghua applicationofbilstminlithologyidentificationofbeachbarsandreservoir AT zhangyuxia applicationofbilstminlithologyidentificationofbeachbarsandreservoir AT wangjun applicationofbilstminlithologyidentificationofbeachbarsandreservoir AT zhanghuafeng applicationofbilstminlithologyidentificationofbeachbarsandreservoir AT wangyouwen applicationofbilstminlithologyidentificationofbeachbarsandreservoir |