EUVIMEDEUVIMED entdecken
Crossref

Hybrid deep learning based prediction for water quality of plain watershed

Kefan Wang, Lei Liu, Xuechen Ben, Danjun Jin, Yao Zhu, Feier Wang

Environmental Research · 2024-12 · 262 · 119911

DOI: 10.1016/j.envres.2024.119911 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Research, 2024-12. Verfasst von Kefan Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Environmental & Resource Sciences, Zhejiang University, Hangzhou, 310058, China. Hauptthemen laut MEDLINE: Deep Learning, Water Quality, Rivers. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 81 Literaturangaben. Gefördert von: Zhejiang University, Science and Technology Program of Zhejiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Establishing a highly reliable and accurate water quality prediction model is critical for effective water environment management. However, enhancing the performance of these predictive models continues to pose challenges, especially in the plain watershed with complex hydraulic conditions. This study aims to evaluate the efficacy of three traditional machine learning models versus three deep learning models in predicting the water quality of plain river networks and to develop a novel hybrid deep learning model to further improve prediction accuracy. The performance of the proposed model was assessed under various input feature sets and data temporal frequencies. The findings indicated that deep learning models outperformed traditional machine learning models in handling complex time series data. Long Short-Term Memory (LSTM) models improved the R2 by approximately 29% and lowered the Root Mean Square Error (RMSE) by about 48.6% on average. The hybrid Bayes-LSTM-GRU (Gated Recurrent Unit) model significantly enhanced prediction accuracy, reducing the average RMSE by 18.1% compared to the single LSTM model. Models trained on feature-selected datasets exhibited superior performance compared to those trained on original datasets. Higher temporal frequencies of input data generally provide more useful information. However, in datasets with numerous abrupt changes, increasing the temporal interval proves beneficial. Overall, the proposed hybrid deep learning model demonstrates an efficient and cost-effective method for improving water quality prediction performance, showing significant potential for application in managing water quality in plain watershed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningWater QualityRiversEnvironmental MonitoringBayes TheoremModels, Theoretical

Stichwörter der Autor:innen

Bayesian optimizationGated recurrent unitHybrid modelLong Short-term memoryMachine learningWater quality prediction

Autor:innen und Institutionen

  • College of Environmental & Resource Sciences, Zhejiang University, Hangzhou, 310058, China.
  • Zhejiang Zone-King Environmental Sci&Tech Co. Ltd., Hangzhou, 310064, China.
  • Taizhou Ecology and Environment Bureau Wenling Branch, Wenling, Zhejiang, 317599, China.
  • College of Environmental & Resource Sciences, Zhejiang University, Hangzhou, 310058, China; Zhejiang Ecological Civilization Academy, Anji, Zhejiang, 313300, China. Electronic address: wangfeier@zju.edu.cn.

Förderung

  • Zhejiang University
  • Science and Technology Program of Zhejiang Province

Zitieren

APA

Wang, K., Liu, L., Ben, X., Jin, D., Zhu, Y., & Wang, F. (2024). Hybrid deep learning based prediction for water quality of plain watershed. Environmental Research, 262, 119911. https://doi.org/10.1016/j.envres.2024.119911

Vancouver

Wang K, Liu L, Ben X, Jin D, Zhu Y, Wang F. Hybrid deep learning based prediction for water quality of plain watershed. Environmental Research. 2024;262:119911. doi:10.1016/j.envres.2024.119911

BibTeX
@article{Wang2024,
  author = {Wang, Kefan and Liu, Lei and Ben, Xuechen and Jin, Danjun and Zhu, Yao and Wang, Feier},
  title = {Hybrid deep learning based prediction for water quality of plain watershed},
  journal = {Environmental Research},
  year = {2024},
  volume = {262},
  pages = {119911},
  doi = {10.1016/j.envres.2024.119911}
}
Kostenlos starten →