EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Connectivity-Aware LSTM-PSO for Water Injection Allocation in Offshore Waterflooding Reservoirs

Feng Wei, Xiaoquan Chen, Guoqiang Pang, Wei Li, Peng Chen, Shixiang Jiao

Processes · 25.06.2026 · 14 (13) · 2065

DOI: 10.3390/pr14132065 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 25.06.2026. Verfasst von Feng Wei und 5 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Water injection allocation is critical for maintaining pressure support in mature offshore waterflooding reservoirs, but its optimization is complicated by delayed injection–production responses, interwell interference, limited intervention windows, and incomplete field labels for injector–producer connectivity. This study proposes a connectivity-aware optimization framework that couples an attention-based connectivity identification network, a group-level long short-term memory (LSTM) production surrogate, and particle swarm optimization (PSO). The methodological novelty lies in using prescribed connectivity labels in a field-informed semi-synthetic benchmark to quantitatively test whether dynamic injection–production sequences and static well-pair attributes can be transformed into interpretable connectivity estimates for injection allocation decision support. The benchmark contains five injectors, ten producers, daily injection and production histories, static well-pair attributes, response lags, and normalized connectivity coefficients generated under practical injection rate, lag, water cut, and adjustment constraints. The attention model recovered the dominant injector–producer relationships with MAE = 0.0146, RMSE = 0.0240, R2 = 0.9835, cosine similarity = 0.9962, and top-three overlap = 100%. The group-level LSTM achieved MAE = 4.524 m3/d, RMSE = 5.963 m3/d, MAPE = 1.255%, and R2 = 0.964 on the chronological test set. Across 15 optimization cases, the PSO module generated feasible injection reallocations under single-well rate, total-injection balance, and +/−15% adjustment constraints. The results should be interpreted as controlled methodological validation rather than direct field deployment; further testing with anonymized field data is required.

Zitieren

APA

Wei, F., Chen, X., Pang, G., Li, W., Chen, P., & Jiao, S. (2026). Connectivity-Aware LSTM-PSO for Water Injection Allocation in Offshore Waterflooding Reservoirs. Processes, 14(13), 2065. https://doi.org/10.3390/pr14132065

Vancouver

Wei F, Chen X, Pang G, Li W, Chen P, Jiao S. Connectivity-Aware LSTM-PSO for Water Injection Allocation in Offshore Waterflooding Reservoirs. Processes. 2026;14(13):2065. doi:10.3390/pr14132065

BibTeX
@article{Wei2026,
  author = {Wei, Feng and Chen, Xiaoquan and Pang, Guoqiang and Li, Wei and Chen, Peng and Jiao, Shixiang},
  title = {Connectivity-Aware LSTM-PSO for Water Injection Allocation in Offshore Waterflooding Reservoirs},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {13},
  pages = {2065},
  doi = {10.3390/pr14132065}
}
Kostenlos starten →