Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs
Cyclic steam stimulation (CSS) is one efficient technology for enhancing heavy-oil recovery. However, after multiple cycles, steam channeling severely limits the thermal recovery because high-temperature steam preferentially breaks through to the producers. To solve the issues of steam breakthrough,...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | Geofluids |
| Online Access: | http://dx.doi.org/10.1155/2023/6593464 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850158534721798144 |
|---|---|
| author | Yu Li Huiqing Liu Peng Jiao Qing Wang Dong Liu Liangyu Ma Zhipeng Wang Hao Peng |
| author_facet | Yu Li Huiqing Liu Peng Jiao Qing Wang Dong Liu Liangyu Ma Zhipeng Wang Hao Peng |
| author_sort | Yu Li |
| collection | DOAJ |
| description | Cyclic steam stimulation (CSS) is one efficient technology for enhancing heavy-oil recovery. However, after multiple cycles, steam channeling severely limits the thermal recovery because high-temperature steam preferentially breaks through to the producers. To solve the issues of steam breakthrough, it is essentially important and necessary to recognize steam channeling. In this work, a machine-learning-assisted identification model, based on a random-forest ensemble algorithm, is developed to predict the occurrence of steam channeling during steam huff-and-puff processes. The set of feature attributes is constructed based on the permeability ratio, steam quality, and steam-injection speed, which provides the reference for the construction of the training-sample set, steam-channeling reconstruction set, and prediction set. Based on the realistic data, the Pearson correlation coefficient is implemented to confirm the linear correlation among different characteristics; thus, the dimension reduction of the characteristic parameters is achieved. The random oversampling method is adopted to treat the unbalanced training-sample set. Our results show that this model can accurately describe the current state of steam channeling and predict steam propagation in the following cycles. |
| format | Article |
| id | doaj-art-6783fc6e661942f89c6d27f445aeb217 |
| institution | OA Journals |
| issn | 1468-8123 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Geofluids |
| spelling | doaj-art-6783fc6e661942f89c6d27f445aeb2172025-08-20T02:23:49ZengWileyGeofluids1468-81232023-01-01202310.1155/2023/6593464Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil ReservoirsYu Li0Huiqing Liu1Peng Jiao2Qing Wang3Dong Liu4Liangyu Ma5Zhipeng Wang6Hao Peng7State Key Laboratory of Petroleum Resources and ProspectingState Key Laboratory of Petroleum Resources and ProspectingState Key Laboratory of Petroleum Resources and ProspectingState Key Laboratory of Petroleum Resources and ProspectingChina National Offshore Oil Corporation (China)China National Offshore Oil Corporation (China)State Key Laboratory of Petroleum Resources and ProspectingGuangzhou Institute of Energy ConversionCyclic steam stimulation (CSS) is one efficient technology for enhancing heavy-oil recovery. However, after multiple cycles, steam channeling severely limits the thermal recovery because high-temperature steam preferentially breaks through to the producers. To solve the issues of steam breakthrough, it is essentially important and necessary to recognize steam channeling. In this work, a machine-learning-assisted identification model, based on a random-forest ensemble algorithm, is developed to predict the occurrence of steam channeling during steam huff-and-puff processes. The set of feature attributes is constructed based on the permeability ratio, steam quality, and steam-injection speed, which provides the reference for the construction of the training-sample set, steam-channeling reconstruction set, and prediction set. Based on the realistic data, the Pearson correlation coefficient is implemented to confirm the linear correlation among different characteristics; thus, the dimension reduction of the characteristic parameters is achieved. The random oversampling method is adopted to treat the unbalanced training-sample set. Our results show that this model can accurately describe the current state of steam channeling and predict steam propagation in the following cycles.http://dx.doi.org/10.1155/2023/6593464 |
| spellingShingle | Yu Li Huiqing Liu Peng Jiao Qing Wang Dong Liu Liangyu Ma Zhipeng Wang Hao Peng Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs Geofluids |
| title | Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs |
| title_full | Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs |
| title_fullStr | Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs |
| title_full_unstemmed | Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs |
| title_short | Machine-Learning-Assisted Identification of Steam Channeling after Cyclic Steam Stimulation in Heavy-Oil Reservoirs |
| title_sort | machine learning assisted identification of steam channeling after cyclic steam stimulation in heavy oil reservoirs |
| url | http://dx.doi.org/10.1155/2023/6593464 |
| work_keys_str_mv | AT yuli machinelearningassistedidentificationofsteamchannelingaftercyclicsteamstimulationinheavyoilreservoirs AT huiqingliu machinelearningassistedidentificationofsteamchannelingaftercyclicsteamstimulationinheavyoilreservoirs AT pengjiao machinelearningassistedidentificationofsteamchannelingaftercyclicsteamstimulationinheavyoilreservoirs AT qingwang machinelearningassistedidentificationofsteamchannelingaftercyclicsteamstimulationinheavyoilreservoirs AT dongliu machinelearningassistedidentificationofsteamchannelingaftercyclicsteamstimulationinheavyoilreservoirs AT liangyuma machinelearningassistedidentificationofsteamchannelingaftercyclicsteamstimulationinheavyoilreservoirs AT zhipengwang machinelearningassistedidentificationofsteamchannelingaftercyclicsteamstimulationinheavyoilreservoirs AT haopeng machinelearningassistedidentificationofsteamchannelingaftercyclicsteamstimulationinheavyoilreservoirs |