Oil Production Rate Forecasting by SA-LSTM Model in Tight Reservoirs
The accurate forecasting of oil field production rate is a crucial indicator for each oil field’s successful development, but due to the complicated reservoir conditions and unknown underground environment, the high accuracy of production rate forecasting is a popular challenge. To find a low time c...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
GeoScienceWorld
2024-01-01
|
Series: | Lithosphere |
Online Access: | https://pubs.geoscienceworld.org/gsa/lithosphere/article-pdf/doi/10.2113/2024/lithosphere_2023_197/6175400/lithosphere_2023_197.pdf |
_version_ | 1797341384934424576 |
---|---|
author | Denghui He Yaguang Qu Guanglong Sheng Bin Wang Xu Yan Zhen Tao Meng Lei |
author_facet | Denghui He Yaguang Qu Guanglong Sheng Bin Wang Xu Yan Zhen Tao Meng Lei |
author_sort | Denghui He |
collection | DOAJ |
description | The accurate forecasting of oil field production rate is a crucial indicator for each oil field’s successful development, but due to the complicated reservoir conditions and unknown underground environment, the high accuracy of production rate forecasting is a popular challenge. To find a low time consumption and high accuracy method for forecasting production rate, the current paper proposes a hybrid model, Simulated Annealing Long Short-Term Memory network (SA-LSTM), based on the daily oil production rate of tight reservoirs with the in situ data of injection and production rates in fractures. Furthermore, forecasting results are compared with the numerical simulation model output. The LSTM can effectively learn time-sequence problems, while SA can optimize the hyperparameters (learning rate, batch size, and decay rate) in LSTM to achieve higher accuracy. By conducting the optimized hyperparameters into the LSTM model, the daily oil production rate can be forecasted well. After training and predicting on existing production data, three different methods were used to forecast daily oil production for the next 300 days. The results were then validated using numerical simulations to compare the forecasting of LSTM and SA-LSTM. The results show that SA-LSTM can more efficiently and accurately predict daily oil production. The fitting accuracies of the three methods are as follows: numerical reservoir simulation (96.2%), LSTM (98.1%), and SA-LSTM (98.7%). The effectiveness of SA-LSTM in production rate is particularly outstanding. Using the same SA-LSTM model, we input the daily oil production data of twenty oil wells in the same block and make production prediction, and the effect is remarkable. |
first_indexed | 2024-03-08T10:17:15Z |
format | Article |
id | doaj.art-f2cc33f2998a4713bcfacdd8fc4d2aeb |
institution | Directory Open Access Journal |
issn | 1941-8264 1947-4253 |
language | English |
last_indexed | 2024-03-08T10:17:15Z |
publishDate | 2024-01-01 |
publisher | GeoScienceWorld |
record_format | Article |
series | Lithosphere |
spelling | doaj.art-f2cc33f2998a4713bcfacdd8fc4d2aeb2024-01-28T14:51:43ZengGeoScienceWorldLithosphere1941-82641947-42532024-01-012024110.2113/2024/lithosphere_2023_197Oil Production Rate Forecasting by SA-LSTM Model in Tight ReservoirsDenghui He0https://orcid.org/0000-0002-9641-793XYaguang Qu1https://orcid.org/0000-0002-9641-793XGuanglong Sheng2Bin Wang3Xu Yan4Zhen Tao5Meng Lei6Key Laboratory of Drilling and Production Engineering for Oil and Gas, Wuhan, 430100, ChinaKey Laboratory of Drilling and Production Engineering for Oil and Gas, Wuhan, 430100, ChinaKey Laboratory of Drilling and Production Engineering for Oil and Gas, Wuhan, 430100, ChinaExploration and Development Research Institute of Changqing Oilfield Company, National Engineering Laboratory for Exploration and Development of Low Permeability Oil and Gas Fields, Xian, 710000, ChinaKey Laboratory of Drilling and Production Engineering for Oil and Gas, Wuhan, 430100, ChinaResearch Institute of Petroleum Exploration & Development, PetroChina, Beijing, ChinaKey Laboratory of Drilling and Production Engineering for Oil and Gas, Wuhan, 430100, ChinaThe accurate forecasting of oil field production rate is a crucial indicator for each oil field’s successful development, but due to the complicated reservoir conditions and unknown underground environment, the high accuracy of production rate forecasting is a popular challenge. To find a low time consumption and high accuracy method for forecasting production rate, the current paper proposes a hybrid model, Simulated Annealing Long Short-Term Memory network (SA-LSTM), based on the daily oil production rate of tight reservoirs with the in situ data of injection and production rates in fractures. Furthermore, forecasting results are compared with the numerical simulation model output. The LSTM can effectively learn time-sequence problems, while SA can optimize the hyperparameters (learning rate, batch size, and decay rate) in LSTM to achieve higher accuracy. By conducting the optimized hyperparameters into the LSTM model, the daily oil production rate can be forecasted well. After training and predicting on existing production data, three different methods were used to forecast daily oil production for the next 300 days. The results were then validated using numerical simulations to compare the forecasting of LSTM and SA-LSTM. The results show that SA-LSTM can more efficiently and accurately predict daily oil production. The fitting accuracies of the three methods are as follows: numerical reservoir simulation (96.2%), LSTM (98.1%), and SA-LSTM (98.7%). The effectiveness of SA-LSTM in production rate is particularly outstanding. Using the same SA-LSTM model, we input the daily oil production data of twenty oil wells in the same block and make production prediction, and the effect is remarkable.https://pubs.geoscienceworld.org/gsa/lithosphere/article-pdf/doi/10.2113/2024/lithosphere_2023_197/6175400/lithosphere_2023_197.pdf |
spellingShingle | Denghui He Yaguang Qu Guanglong Sheng Bin Wang Xu Yan Zhen Tao Meng Lei Oil Production Rate Forecasting by SA-LSTM Model in Tight Reservoirs Lithosphere |
title | Oil Production Rate Forecasting by SA-LSTM Model in Tight Reservoirs |
title_full | Oil Production Rate Forecasting by SA-LSTM Model in Tight Reservoirs |
title_fullStr | Oil Production Rate Forecasting by SA-LSTM Model in Tight Reservoirs |
title_full_unstemmed | Oil Production Rate Forecasting by SA-LSTM Model in Tight Reservoirs |
title_short | Oil Production Rate Forecasting by SA-LSTM Model in Tight Reservoirs |
title_sort | oil production rate forecasting by sa lstm model in tight reservoirs |
url | https://pubs.geoscienceworld.org/gsa/lithosphere/article-pdf/doi/10.2113/2024/lithosphere_2023_197/6175400/lithosphere_2023_197.pdf |
work_keys_str_mv | AT denghuihe oilproductionrateforecastingbysalstmmodelintightreservoirs AT yaguangqu oilproductionrateforecastingbysalstmmodelintightreservoirs AT guanglongsheng oilproductionrateforecastingbysalstmmodelintightreservoirs AT binwang oilproductionrateforecastingbysalstmmodelintightreservoirs AT xuyan oilproductionrateforecastingbysalstmmodelintightreservoirs AT zhentao oilproductionrateforecastingbysalstmmodelintightreservoirs AT menglei oilproductionrateforecastingbysalstmmodelintightreservoirs |