CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding Reservoir
Geared toward the problems of predicting the unsteadily changing single oil well production in water flooding reservoir, a machine learning model based on CNN (convolutional neural network) and LSTM (long short-term memory) is established which realizes precise predictions of monthly single-well pro...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-Wiley
2023-01-01
|
| Series: | Geofluids |
| Online Access: | http://dx.doi.org/10.1155/2023/5467956 |
| _version_ | 1797816571500953600 |
|---|---|
| author | Lei Zhang Hongen Dou Kun Zhang Ruijie Huang Xia Lin Shuhong Wu Rui Zhang Chenjun Zhang Shaojing Zheng |
| author_facet | Lei Zhang Hongen Dou Kun Zhang Ruijie Huang Xia Lin Shuhong Wu Rui Zhang Chenjun Zhang Shaojing Zheng |
| author_sort | Lei Zhang |
| collection | DOAJ |
| description | Geared toward the problems of predicting the unsteadily changing single oil well production in water flooding reservoir, a machine learning model based on CNN (convolutional neural network) and LSTM (long short-term memory) is established which realizes precise predictions of monthly single-well production. This study is considering more than 60 dynamic and static factors that affect the changes of oil well production, introduce water injection parameters into data set, select 11 main control factors, and then, build a CNN-LSTM model optimized by Bayesian optimization. The effectiveness of the proposed model is verified in a realistic reservoir. The experiment results show that the prediction accuracy of the proposed model is over 90%, which suggests a penitential application in an extensive range of applications. Production forecasting by the developed model is simple, efficient, and accurate, which can provide a guidance for the dynamic analysis of a water flooding reservoir, and work as a good reference of the development and production of other types of reservoirs. |
| first_indexed | 2024-03-13T08:39:40Z |
| format | Article |
| id | doaj.art-0604efa5d4a74d47b67257f432a45f47 |
| institution | Directory Open Access Journal |
| issn | 1468-8123 |
| language | English |
| last_indexed | 2024-03-13T08:39:40Z |
| publishDate | 2023-01-01 |
| publisher | Hindawi-Wiley |
| record_format | Article |
| series | Geofluids |
| spelling | doaj.art-0604efa5d4a74d47b67257f432a45f472023-05-30T12:28:37ZengHindawi-WileyGeofluids1468-81232023-01-01202310.1155/2023/5467956CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding ReservoirLei Zhang0Hongen Dou1Kun Zhang2Ruijie Huang3Xia Lin4Shuhong Wu5Rui Zhang6Chenjun Zhang7Shaojing Zheng8Research Institute of Petroleum Exploration and DevelopmentResearch Institute of Petroleum Exploration and DevelopmentThe Twelfth Oil Production PlantResearch Institute of Petroleum Exploration and DevelopmentResearch Institute of Petroleum Exploration and DevelopmentResearch Institute of Petroleum Exploration and DevelopmentChangqing Engineering Design Co.Research Institute of Petroleum Exploration and DevelopmentResearch Institute of Petroleum Exploration and DevelopmentGeared toward the problems of predicting the unsteadily changing single oil well production in water flooding reservoir, a machine learning model based on CNN (convolutional neural network) and LSTM (long short-term memory) is established which realizes precise predictions of monthly single-well production. This study is considering more than 60 dynamic and static factors that affect the changes of oil well production, introduce water injection parameters into data set, select 11 main control factors, and then, build a CNN-LSTM model optimized by Bayesian optimization. The effectiveness of the proposed model is verified in a realistic reservoir. The experiment results show that the prediction accuracy of the proposed model is over 90%, which suggests a penitential application in an extensive range of applications. Production forecasting by the developed model is simple, efficient, and accurate, which can provide a guidance for the dynamic analysis of a water flooding reservoir, and work as a good reference of the development and production of other types of reservoirs.http://dx.doi.org/10.1155/2023/5467956 |
| spellingShingle | Lei Zhang Hongen Dou Kun Zhang Ruijie Huang Xia Lin Shuhong Wu Rui Zhang Chenjun Zhang Shaojing Zheng CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding Reservoir Geofluids |
| title | CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding Reservoir |
| title_full | CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding Reservoir |
| title_fullStr | CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding Reservoir |
| title_full_unstemmed | CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding Reservoir |
| title_short | CNN-LSTM Model Optimized by Bayesian Optimization for Predicting Single-Well Production in Water Flooding Reservoir |
| title_sort | cnn lstm model optimized by bayesian optimization for predicting single well production in water flooding reservoir |
| url | http://dx.doi.org/10.1155/2023/5467956 |
| work_keys_str_mv | AT leizhang cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir AT hongendou cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir AT kunzhang cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir AT ruijiehuang cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir AT xialin cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir AT shuhongwu cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir AT ruizhang cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir AT chenjunzhang cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir AT shaojingzheng cnnlstmmodeloptimizedbybayesianoptimizationforpredictingsinglewellproductioninwaterfloodingreservoir |