EUVIMEDEUVIMED entdecken
Crossref

An adaptive hybrid modeling approach integrating elastic net and Kriging for activated sludge treatment

Yaohui Li, Zebin Zhang, Zhifeng Yin, Jingfang Shen, Wenwei Liu

Environmental Research · 2026-07 · 301 · 124422

DOI: 10.1016/j.envres.2026.124422 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Research, 2026-07. Verfasst von Yaohui Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Electrical Engineering, Xuchang University, Xuchang, 461000, Henan, China; School of Informatics, Huazhong Agricultural Uni…. Hauptthemen laut MEDLINE: Sewage, Models, Theoretical, Waste Disposal, Fluid. Die Arbeit nennt 30 Literaturangaben. Gefördert von: Henan Province Natural Science Foundation, Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

When solving complex nonlinear problems, constructing a Kriging model by all variables is prone to overfitting, resulting in reduced prediction accuracy. To enhance the generalization capability of the Kriging model, this study proposes a hybrid modeling method that combines elastic net (EN) with Kriging, named as KrigNet. This method first determines the optimal value of the penalty coefficient λ by optimizing the K-fold cross-validation error, and then obtains the EN regression coefficient vector corresponding to λ. Subsequently, EN regularization is employed to shrink the regression coefficients of less influential variables to zero, thereby simplifying the regression function vector of Kriging. Finally, the weights for EN and Kriging are computed by the leave-one-out cross-validation error, and a weighted average of the predictions from both models is taken to obtain the final KrigNet model. Through evaluation and comparison based on benchmark functions and a case on water quality prediction of activated sludge treatment (AST), the KrigNet demonstrates superior generalization capability and higher prediction accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SewageModels, TheoreticalWaste Disposal, Fluid

Stichwörter der Autor:innen

Activated sludge treatmentElastic net regularizationHybrid modelingKriging surrogate modelVariable selection

Substanzen

Sewage

Autor:innen und Institutionen

  • College of Mechanical and Electrical Engineering, Xuchang University, Xuchang, 461000, Henan, China; School of Informatics, Huazhong Agricultural University, Wuhan, 430070, China.
  • School of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou, 450001, Henan, China.
  • College of Mechanical and Electrical Engineering, Xuchang University, Xuchang, 461000, Henan, China. Electronic address: 11996002@xcu.edu.cn.
  • School of Informatics, Huazhong Agricultural University, Wuhan, 430070, China.
  • Guangdong Provincial Key Laboratory of Electronic Information Products Reliability Technology, Guangzhou, 511370, China. Electronic address: wenwei2009@163.com.

Förderung

  • Henan Province Natural Science Foundation
  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China

Zitieren

APA

Li, Y., Zhang, Z., Yin, Z., Shen, J., & Liu, W. (2026). An adaptive hybrid modeling approach integrating elastic net and Kriging for activated sludge treatment. Environmental Research, 301, 124422. https://doi.org/10.1016/j.envres.2026.124422

Vancouver

Li Y, Zhang Z, Yin Z, Shen J, Liu W. An adaptive hybrid modeling approach integrating elastic net and Kriging for activated sludge treatment. Environmental Research. 2026;301:124422. doi:10.1016/j.envres.2026.124422

BibTeX
@article{Li2026,
  author = {Li, Yaohui and Zhang, Zebin and Yin, Zhifeng and Shen, Jingfang and Liu, Wenwei},
  title = {An adaptive hybrid modeling approach integrating elastic net and Kriging for activated sludge treatment},
  journal = {Environmental Research},
  year = {2026},
  volume = {301},
  pages = {124422},
  doi = {10.1016/j.envres.2026.124422}
}
Kostenlos starten →