Application of depth learning in prediction of glutenite reservoir
Sedimentary facies of gravel reservoir has the characteristics of multiple sources and short flow. Sand body thickness changes rapidly in plane and space. Model-based multi-attribute regression seismic reservoir prediction method often results in unreasonable inter-well prediction results because of...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2022-01-01
|
| Series: | E3S Web of Conferences |
| Subjects: | |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2022/25/e3sconf_gesd2022_02011.pdf |
| _version_ | 1811219159943479296 |
|---|---|
| author | Dong Meng |
| author_facet | Dong Meng |
| author_sort | Dong Meng |
| collection | DOAJ |
| description | Sedimentary facies of gravel reservoir has the characteristics of multiple sources and short flow. Sand body thickness changes rapidly in plane and space. Model-based multi-attribute regression seismic reservoir prediction method often results in unreasonable inter-well prediction results because of insufficient generalization ability of the model. For this reason, a deep learning reservoir prediction method based on fault blocks is proposed. Within a fault block range (regardless of wells outside the fault block), the seismic attributes extracted from the sliding time window of the isochronous sedimentary surface are used as input, and the sandstone thickness data of the target layer of the well point are used as expected output to train the depth neural network model of the multi-layer perceptor. Then, the trained model is used to predict the sandstone thickness distribution in the well distribution area. The application of actual data in A oilfield shows that the predictive coincidence rate of sandstone thickness in known wells is more than 95%, and the drilling occurrence rate of sandstone in horizontal section after completion of a posterior horizontal well is more than 80%. This method has high prediction accuracy and good generalization ability. |
| first_indexed | 2024-04-12T07:20:29Z |
| format | Article |
| id | doaj.art-73c807c644184e64a530a516cdf756f4 |
| institution | Directory Open Access Journal |
| issn | 2267-1242 |
| language | English |
| last_indexed | 2024-04-12T07:20:29Z |
| publishDate | 2022-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj.art-73c807c644184e64a530a516cdf756f42022-12-22T03:42:20ZengEDP SciencesE3S Web of Conferences2267-12422022-01-013580201110.1051/e3sconf/202235802011e3sconf_gesd2022_02011Application of depth learning in prediction of glutenite reservoirDong Meng0Research Institute of Petroleum Exploration and Development of Daqing Oilfield Company LimitedSedimentary facies of gravel reservoir has the characteristics of multiple sources and short flow. Sand body thickness changes rapidly in plane and space. Model-based multi-attribute regression seismic reservoir prediction method often results in unreasonable inter-well prediction results because of insufficient generalization ability of the model. For this reason, a deep learning reservoir prediction method based on fault blocks is proposed. Within a fault block range (regardless of wells outside the fault block), the seismic attributes extracted from the sliding time window of the isochronous sedimentary surface are used as input, and the sandstone thickness data of the target layer of the well point are used as expected output to train the depth neural network model of the multi-layer perceptor. Then, the trained model is used to predict the sandstone thickness distribution in the well distribution area. The application of actual data in A oilfield shows that the predictive coincidence rate of sandstone thickness in known wells is more than 95%, and the drilling occurrence rate of sandstone in horizontal section after completion of a posterior horizontal well is more than 80%. This method has high prediction accuracy and good generalization ability.https://www.e3s-conferences.org/articles/e3sconf/pdf/2022/25/e3sconf_gesd2022_02011.pdfglutenite reservoirreservoir predictiondepth learningmulti-layer perceptron |
| spellingShingle | Dong Meng Application of depth learning in prediction of glutenite reservoir E3S Web of Conferences glutenite reservoir reservoir prediction depth learning multi-layer perceptron |
| title | Application of depth learning in prediction of glutenite reservoir |
| title_full | Application of depth learning in prediction of glutenite reservoir |
| title_fullStr | Application of depth learning in prediction of glutenite reservoir |
| title_full_unstemmed | Application of depth learning in prediction of glutenite reservoir |
| title_short | Application of depth learning in prediction of glutenite reservoir |
| title_sort | application of depth learning in prediction of glutenite reservoir |
| topic | glutenite reservoir reservoir prediction depth learning multi-layer perceptron |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2022/25/e3sconf_gesd2022_02011.pdf |
| work_keys_str_mv | AT dongmeng applicationofdepthlearninginpredictionofglutenitereservoir |