Marine and Petroleum Geology, Journal Year: 2025, Volume and Issue: unknown, P. 107452 - 107452
Published: May 1, 2025
Language: Английский
Marine and Petroleum Geology, Journal Year: 2025, Volume and Issue: unknown, P. 107452 - 107452
Published: May 1, 2025
Language: Английский
Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(3)
Published: March 1, 2025
Traditional fluid identification methods usually rely on labeled data, which is both scarce and expensive in real-world applications. One significant challenge this regard the difficulty of transferring techniques across diverse geological environments. To address issue, we propose a new method that integrates siamese networks with cross-domain adaptation mechanisms (FCSCD). The primary objective FCSCD to bridge data distribution gap between different domains, thereby improving efficiency. By harnessing contrastive learning power networks, promotes transfer knowledge source target domains by measuring feature similarities these settings. Furthermore, adoption ensures differences categories are aligned, ultimately improves classification accuracy. This proves particularly effective for tasks complex reservoirs, where substantial variations regions pose challenges traditional models. Experimental results from typical well dataset Tarim Oilfield show model outperforms approaches large margin. Comparative experiments also highlight exceptional adaptability robustness managing boundary complexities addressing shifts distributions domains.
Language: Английский
Citations
1Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(2)
Published: April 2, 2025
Language: Английский
Citations
0Natural Resources Research, Journal Year: 2025, Volume and Issue: unknown
Published: April 17, 2025
Language: Английский
Citations
0Marine and Petroleum Geology, Journal Year: 2025, Volume and Issue: unknown, P. 107452 - 107452
Published: May 1, 2025
Language: Английский
Citations
0