EUVIMEDEUVIMED entdecken
Crossref

Bayesian-optimized transfer learning for ammonia nitrogen prediction in SBR systems: Seamless knowledge transfer from domestic to industrial-mixed wastewater

Qiu Cheng, Li Qingchuan, Huang Xingjun, Hu Junjie, Xu Jinpeng, Wu Ling, Fan Shoubo, Zhan Chunhong, Li Qianglin, Xu Lingjie, Xie Yishang

Journal of Environmental Management · 2026

DOI: 10.1016/j.jenvman.2026.128643 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Environmental Management, 2026. Verfasst von Qiu Cheng und 10 weiteren Autor:innen. Beteiligte Einrichtung: Chengdu Technological University, Chengdu, 611730, China, Sichuan Provincial Engineering Research Center of Small and Medium-sized Intelligent Wastew…. Hauptthemen laut MEDLINE: Wastewater, Nitrogen, Ammonia. Die Arbeit nennt 40 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of ammonia nitrogen (NH3-N) in industrial-mixed wastewater remains challenging due to significant domain shifts from domestic wastewater systems, including variations in influent composition, microbial community dynamics, and operational constraints. Traditional data-driven models frequently exhibit poor generalization under such conditions. To address this, we propose a Bayesian-Optimized Transfer Learning Long Short-Term Memory (BO-TL-LSTM) framework that effectively transfers knowledge from a source domain (domestic wastewater) to a target domain (industrial-mixed wastewater). The framework automates the optimization of critical hyperparameters-including the number of frozen layers, fine-tuning learning rate, batch size, and L2 regularization coefficient-through Bayesian optimization, ensuring an optimal balance between preserving transferable features and adapting to target-specific patterns. Experimental results demonstrate that BO-TL-LSTM achieves significantly improved performance with an R-squared (R2) of 0.8533, Root Mean Square Error (RMSE) of 3.37, and Mean Absolute Error (MAE) of 2.74, outperforming baseline models. Notably, the model maintains robust performance even with limited target-domain data, requiring as few as eight operational cycles for reliable prediction. This work provides a scalable and data-efficient strategy for cross-domain wastewater quality prediction, with significant implications for intelligent wastewater treatment management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WastewaterNitrogenAmmoniaBayes TheoremTransfer Machine LearningLong Short Term MemoryWaste Disposal, FluidPredictive Learning Models

Stichwörter der Autor:innen

Bayesian optimizationHyperparameter tuningIndustrial-mixed wastewaterTransfer learning

Substanzen

WastewaterNitrogenAmmonia

Autor:innen und Institutionen

  • Chengdu Technological University, Chengdu, 611730, China, Sichuan Provincial Engineering Research Center of Small and Medium-sized Intelligent Wastewater Treatment Equipment, Chengdu, 611730, China. Electronic address:…
  • Chengdu Technological University, Chengdu, 611730, China. Electronic address: dachuandd@gmail.com.
  • Chengdu SOTEC Technology Co., Ltd., Chengdu, 610000, China. Electronic address: xingjun.h@zldtec.com.
  • Chengdu SOTEC Technology Co., Ltd., Chengdu, 610000, China. Electronic address: junj.hu@zldtec.com.
  • Chengdu SOTEC Technology Co., Ltd., Chengdu, 610000, China. Electronic address: jinpeng.xu@zldtec.com.
  • Hubei Province Key Laboratory of Coal Conversion and New Carbon Materials, Wuhan University of Science and Technology, Wuhan, 430081, China. Electronic address: wuling2018@wust.edu.cn.

Zitieren

APA

Cheng, Q., Qingchuan, L., Xingjun, H., Junjie, H., Jinpeng, X., Ling, W., Shoubo, F., Chunhong, Z., Qianglin, L., Lingjie, X., & Yishang, X. (2026). Bayesian-optimized transfer learning for ammonia nitrogen prediction in SBR systems: Seamless knowledge transfer from domestic to industrial-mixed wastewater. Journal of Environmental Management. https://doi.org/10.1016/j.jenvman.2026.128643

Vancouver

Cheng Q, Qingchuan L, Xingjun H, Junjie H, Jinpeng X, Ling W, et al. Bayesian-optimized transfer learning for ammonia nitrogen prediction in SBR systems: Seamless knowledge transfer from domestic to industrial-mixed wastewater. Journal of Environmental Management. 2026. doi:10.1016/j.jenvman.2026.128643

BibTeX
@article{Cheng2026,
  author = {Cheng, Qiu and Qingchuan, Li and Xingjun, Huang and Junjie, Hu and Jinpeng, Xu and Ling, Wu and Shoubo, Fan and Chunhong, Zhan and Qianglin, Li and Lingjie, Xu and Yishang, Xie},
  title = {Bayesian-optimized transfer learning for ammonia nitrogen prediction in SBR systems: Seamless knowledge transfer from domestic to industrial-mixed wastewater},
  journal = {Journal of Environmental Management},
  year = {2026},
  doi = {10.1016/j.jenvman.2026.128643}
}
Kostenlos starten →