EUVIMEDEUVIMED entdecken
Crossref

Environmental geochemical and machine learning assessment of heavy metal(loid)s sources and risks in urban river–canal sediments of the Saigon system

Nguyen Xuan Tong, Phan Do Trong Nghia, Cao Phuong Thao, Truong Anh Tu, Nguyen Kim Hoa, Nguyen Duy Thanh, Luu Tang Phuc Khang

Environmental Geochemistry and Health · 2026

DOI: 10.1007/s10653-026-03181-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Geochemistry and Health, 2026. Verfasst von Nguyen Xuan Tong und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Environmental Science, Engineering and Management, Industrial University of Ho Chi Minh City, Ho Chi Minh City, 70000, Vietnam. nguyenxu…. Hauptthemen laut MEDLINE: Metals, Heavy, Geologic Sediments, Machine Learning, Rivers. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 110 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In tropical megacities undergoing rapid industrialization, comprehensive assessments of seasonal variability in heavy metal(loid)s sources and ecological risks in river-canal sediments remain limited, particularly in Southeast Asian urban systems. Urban sediments function as both secondary sinks and potential sources of heavy metal(loid)s, yet integrated evaluations linking geochemistry, source apportionment, and predictive risk modeling are still unexplored. A total of 144 sediment samples were collected during the dry and wet seasons of 2022. Here, we applied an integrated methodological framework combining geochemical characterization, sequential extraction for metal speciation, non-negative matrix factorization (NMF) for source apportionment, GIS-based risk mapping, and machine-learning prediction using Random Forest and XGBoost, with SHAP interpretation. Results demonstrated pronounced spatial and seasonal heterogeneity. Metal burdens were dominated by Fe, Cr, Cu, Zn, and As, primarily derived from crustal/soil inputs and traffic-related urban emissions. Sequential extraction indicated that Cr and Fe were largely associated with residual fractions, whereas Zn, Cu, and As were enriched in redox-sensitive phases. NMF resolved five source profiles, and risk mapping consistently identified high-risk hotspots (levels 4-5) in the Nhieu Loc-Thi Nghe canal, with additional concerns in Ben Nghe canal. Among predictive models, XGBoost exhibited superior performance, and SHAP analysis identified Cr, Fe, and As as the dominant risk drivers. Overall, this study establishes a data-driven, interpretable framework that supports evidence-based prioritization of remediation zones and strategic urban sediment management. Future work integrating metal bioavailability, ecotoxicological responses, and hydrodynamic processes would further refine risk prediction and sustainable intervention planning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Metals, HeavyGeologic SedimentsMachine LearningRiversEnvironmental MonitoringWater Pollutants, ChemicalRisk AssessmentBoosting Machine Learning AlgorithmsCitiesSeasonsPredictive Learning Models

Stichwörter der Autor:innen

ArsenicHeavy metal(loid)sMachine learningSediment contaminationUrban river systems

Substanzen

Metals, HeavyWater Pollutants, Chemical

Autor:innen und Institutionen

  • Institute of Environmental Science, Engineering and Management, Industrial University of Ho Chi Minh City, Ho Chi Minh City, 70000, Vietnam. nguyenxuantong@iuh.edu.vn.
  • Aquatic Biotechnology Laboratory, Department of Animal and Aquatic Sciences, Faculty of Agriculture, Chiang Mai University, Chiang Mai, 50200, Thailand.
  • An Giang University, Long Xuyen, An Giang, 90400, Vietnam.
  • The Center for Gene-Protein Research, Hanoi Medical University, Hanoi, 100000, Vietnam.
  • Ho Chi Minh City University of Natural Resources and Environment, Ho Chi Minh City, 70000, Vietnam.
  • Electric Power University, Hanoi, 100000, Vietnam.

Zitieren

APA

Tong, N. X., Nghia, P. D. T., Thao, C. P., Tu, T. A., Hoa, N. K., Thanh, N. D., & Khang, L. T. P. (2026). Environmental geochemical and machine learning assessment of heavy metal(loid)s sources and risks in urban river–canal sediments of the Saigon system. Environmental Geochemistry and Health. https://doi.org/10.1007/s10653-026-03181-0

Vancouver

Tong NX, Nghia PDT, Thao CP, Tu TA, Hoa NK, Thanh ND, et al. Environmental geochemical and machine learning assessment of heavy metal(loid)s sources and risks in urban river–canal sediments of the Saigon system. Environmental Geochemistry and Health. 2026. doi:10.1007/s10653-026-03181-0

BibTeX
@article{Tong2026,
  author = {Tong, Nguyen Xuan and Nghia, Phan Do Trong and Thao, Cao Phuong and Tu, Truong Anh and Hoa, Nguyen Kim and Thanh, Nguyen Duy and Khang, Luu Tang Phuc},
  title = {Environmental geochemical and machine learning assessment of heavy metal(loid)s sources and risks in urban river–canal sediments of the Saigon system},
  journal = {Environmental Geochemistry and Health},
  year = {2026},
  doi = {10.1007/s10653-026-03181-0}
}
Kostenlos starten →