Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry
Accurate carbon dioxide (CO2) phase prediction at the bottomhole of injection wells is essential for ensuring safe and efficient CO2 storage and enhanced gas recovery (EGR). Phase misclassification can cause operational inefficiencies, equipment failure, and compromised storage integrity, posing sig...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Applied Computing and Geosciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590197425000369 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849689209844006912 |
|---|---|
| author | Sungil Kim Tea-Woo Kim Yongjun Hong Hoonyoung Jeong |
| author_facet | Sungil Kim Tea-Woo Kim Yongjun Hong Hoonyoung Jeong |
| author_sort | Sungil Kim |
| collection | DOAJ |
| description | Accurate carbon dioxide (CO2) phase prediction at the bottomhole of injection wells is essential for ensuring safe and efficient CO2 storage and enhanced gas recovery (EGR). Phase misclassification can cause operational inefficiencies, equipment failure, and compromised storage integrity, posing significant risks to CO2 injection projects. While previous studies have contributed to CO2 phase prediction, they have overlooked well geometry effects, which can impact reliability in real-world applications. This study addresses these challenges by introducing a deep learning framework based on the adaptive factorization network (AFN), which enhances CO2 phase prediction accuracy by leveraging feature interactions. The AFN model was trained on ∼43,000 wells across seven major North American shale gas basins, covering a wide range of well geometries and injection conditions. CO2 phases were classified into supercritical and dense categories, reflecting prevailing flow conditions. To enhance practical applicability, we incorporated real-field wellbore data, ensuring alignment with actual injection environments. The standard AFN model achieved an F1-score of 0.94, with data augmentation further improving performance by reducing false predictions by 50 % and increasing the F1-score to 0.97. Rigorous validation demonstrated the model's robustness for optimizing wellhead temperature to achieve the desired CO2 phase transition. By explicitly considering well geometry effects and real-field conditions, this study advances data-driven CO2 injection modeling, providing a scalable, high-accuracy framework for evaluating CO2 storage and EGR feasibility. |
| format | Article |
| id | doaj-art-cf1cfcdc821744a8a0014b1ee5418c97 |
| institution | DOAJ |
| issn | 2590-1974 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Applied Computing and Geosciences |
| spelling | doaj-art-cf1cfcdc821744a8a0014b1ee5418c972025-08-20T03:21:43ZengElsevierApplied Computing and Geosciences2590-19742025-06-012610025410.1016/j.acags.2025.100254Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometrySungil Kim0Tea-Woo Kim1Yongjun Hong2Hoonyoung Jeong3Petroleum Energy Research Center, Marine Geology and Energy Division, Korea Institute of Geoscience and Mineral Resources, 124, Gwahak-ro, Yuseong-gu, Daejeon, 34132, Republic of KoreaCO2 Geological Storage Research Center, Climate Change Response Division, Korea Institute of Geoscience and Mineral Resources, 124, Gwahak-ro, Yuseong-gu, Daejeon, 34132, Republic of Korea; Corresponding author.GM Factory, 59, Dodeokgongwon-ro, Gwangmyeong-si, Gyeonggi-do, 14253, Republic of KoreaDepartment of Energy Systems Engineering, Seoul National University, Seoul, 08826, Republic of KoreaAccurate carbon dioxide (CO2) phase prediction at the bottomhole of injection wells is essential for ensuring safe and efficient CO2 storage and enhanced gas recovery (EGR). Phase misclassification can cause operational inefficiencies, equipment failure, and compromised storage integrity, posing significant risks to CO2 injection projects. While previous studies have contributed to CO2 phase prediction, they have overlooked well geometry effects, which can impact reliability in real-world applications. This study addresses these challenges by introducing a deep learning framework based on the adaptive factorization network (AFN), which enhances CO2 phase prediction accuracy by leveraging feature interactions. The AFN model was trained on ∼43,000 wells across seven major North American shale gas basins, covering a wide range of well geometries and injection conditions. CO2 phases were classified into supercritical and dense categories, reflecting prevailing flow conditions. To enhance practical applicability, we incorporated real-field wellbore data, ensuring alignment with actual injection environments. The standard AFN model achieved an F1-score of 0.94, with data augmentation further improving performance by reducing false predictions by 50 % and increasing the F1-score to 0.97. Rigorous validation demonstrated the model's robustness for optimizing wellhead temperature to achieve the desired CO2 phase transition. By explicitly considering well geometry effects and real-field conditions, this study advances data-driven CO2 injection modeling, providing a scalable, high-accuracy framework for evaluating CO2 storage and EGR feasibility.http://www.sciencedirect.com/science/article/pii/S2590197425000369Carbon dioxide phaseCarbon dioxide injection temperatureCarbon capture and storageEnhanced gas recoveryFlow simulationAdaptive factorization network |
| spellingShingle | Sungil Kim Tea-Woo Kim Yongjun Hong Hoonyoung Jeong Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry Applied Computing and Geosciences Carbon dioxide phase Carbon dioxide injection temperature Carbon capture and storage Enhanced gas recovery Flow simulation Adaptive factorization network |
| title | Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry |
| title_full | Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry |
| title_fullStr | Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry |
| title_full_unstemmed | Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry |
| title_short | Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry |
| title_sort | prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry |
| topic | Carbon dioxide phase Carbon dioxide injection temperature Carbon capture and storage Enhanced gas recovery Flow simulation Adaptive factorization network |
| url | http://www.sciencedirect.com/science/article/pii/S2590197425000369 |
| work_keys_str_mv | AT sungilkim predictionofcarbondioxidephaseatbottomholebyadaptivefactorizationnetworkconsideringwellgeometry AT teawookim predictionofcarbondioxidephaseatbottomholebyadaptivefactorizationnetworkconsideringwellgeometry AT yongjunhong predictionofcarbondioxidephaseatbottomholebyadaptivefactorizationnetworkconsideringwellgeometry AT hoonyoungjeong predictionofcarbondioxidephaseatbottomholebyadaptivefactorizationnetworkconsideringwellgeometry |