EUVIMEDEUVIMED entdecken
Crossref

Machine Learning-Driven Dynamic Measurement of Environmental Indicators in Multiple Scenes and Multiple Disturbances

Yu-Qi Wang, Han-Bo Zhou, Xiao-Qin Luo, Shang-Wen Deng, Hao-Ran Xu, Yun-Peng Song, Jia-Ji Chen, Wan-Xin Yin, Hao-Yi Cheng iD, Ai-Jie Wang, Hong-Cheng Wang iD

Environmental Science & Technology · 05.08.2025 · 59 (30) · 15877-15889

DOI: 10.1021/acs.est.5c06126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Science & Technology, online erschienen am 24.07.2025. Verfasst von Yu-Qi Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Urban-Rural Water Resource and Environment, School of Eco-Environment, Harbin Institute of Technology, Shenzhen 518055, China. Hauptthemen laut MEDLINE: Machine Learning, Environmental Monitoring. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 84 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Shenzhen Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Digital city water management systems require extensive data sensing for various environmental indicators, yet measurement accuracy often falls short under diverse extreme conditions. This study proposes a chemical oxygen demand (COD) measurement method based on ultraviolet-visible spectrum analysis and machine learning (ML), taking into account the removal of interferences, including temperature, pH, turbidity, common anions and cations, as well as COD composition and different water environments. The data collected from the river and wastewater were processed through principal component analysis, and random forest (RF) performed the best among the multiclass models with a mean absolute percentage error (MAPE) of only 6.73% for total COD (TCOD), dissolved COD (SCOD), and particulate COD (PCOD). RF has excellent transferability with an average MAPE of 8.17% for TCOD, PCOD, and COD in another real wastewater and river. Interpretability analysis elucidates the mechanism of PCA downscaling on the model. Techno-economic assessment revealed that this method incurs only 60.9% of the costs of laboratory monitoring and 49.3% of the costs of conventional automatic monitoring stations. Life cycle assessment showed that the introduction of ML can reduce environmental impacts by 31.32%. The study concludes with a discussion of the dynamic feasibility of this approach in future urban water systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningEnvironmental MonitoringWastewaterRiversBiological Oxygen Demand Analysis

Stichwörter der Autor:innen

life cycle assessmentmachine learningmodel interpretabilitymodel transferonline water monitoringpolymorphic CODtechno-economic assessmentultraviolet−visible spectrum

Substanzen

Wastewater

Autor:innen und Institutionen

  • State Key Laboratory of Urban-Rural Water Resource and Environment, School of Eco-Environment, Harbin Institute of Technology, Shenzhen 518055, China.
  • College of the Environment, Liaoning University, Shenyang 110036, China.

ORCID-Profile: Hao-Yi Cheng, Hong-Cheng Wang

Förderung

  • National Key Research and Development Program of China
  • Shenzhen Science and Technology Program

Zitieren

APA

Wang, Y. Q., Zhou, H. B., Luo, X. Q., Deng, S. W., Xu, H. R., Song, Y. P., Chen, J. J., Yin, W. X., Cheng, H. Y., Wang, A. J., & Wang, H. C. (2025). Machine Learning-Driven Dynamic Measurement of Environmental Indicators in Multiple Scenes and Multiple Disturbances. Environmental Science & Technology, 59(30), 15877-15889. https://doi.org/10.1021/acs.est.5c06126

Vancouver

Wang YQ, Zhou HB, Luo XQ, Deng SW, Xu HR, Song YP, et al. Machine Learning-Driven Dynamic Measurement of Environmental Indicators in Multiple Scenes and Multiple Disturbances. Environmental Science & Technology. 2025;59(30):15877-15889. doi:10.1021/acs.est.5c06126

BibTeX
@article{Wang2025,
  author = {Wang, Yu-Qi and Zhou, Han-Bo and Luo, Xiao-Qin and Deng, Shang-Wen and Xu, Hao-Ran and Song, Yun-Peng and Chen, Jia-Ji and Yin, Wan-Xin and Cheng, Hao-Yi and Wang, Ai-Jie and Wang, Hong-Cheng},
  title = {Machine Learning-Driven Dynamic Measurement of Environmental Indicators in Multiple Scenes and Multiple Disturbances},
  journal = {Environmental Science & Technology},
  year = {2025},
  volume = {59},
  number = {30},
  pages = {15877--15889},
  doi = {10.1021/acs.est.5c06126}
}
Kostenlos starten →