Identifying human activities causing water pollution based on microbial community sequencing and source classifier machine learning
Environment International · 2025-01 · 195 · 109240
DOI: 10.1016/j.envint.2024.109240 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environment International, 2025-01. Verfasst von Zhangmu Jing und 6 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Science, Beijing 100012, China; State E…. Hauptthemen laut MEDLINE: Machine Learning, Water Pollution, Environmental Monitoring, Water Microbiology. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: China Scholarship Council, Chinese Research Academy of Environmental Sciences.
Abstract (Originalsprache)
Identifying and differentiating human activities is crucial for effectively preventing the threats posed by environmental pollution to aquatic ecosystems and human health. Machine learning (ML) is a powerful analytical tool for tracking human impacts on river ecosystems based on high-through datasets. This study employed an ML framework and 16S rRNA sequencing data to reveal microbial dynamics and trace human activities across China. The results revealed that the microbial assembly was mainly dominated by deterministic factors (environmental factors and interactions between species), and the metacommunity partition was significantly associated with human activities in both water and sediment (Chi-square testwP = 1.93 × 10-22; Chi-square testsP = 6.00 × 10-6). Human activities increased the vulnerability of interspecific occurrence networks and the influence of environmental factors on the OTUs similarity and phylogenetic distance. Combined of microbiological indices (MBIs), microbial relative abundance (MRA), and environmental and geographical indices (EGIs), the source classifier machine learning (SCML) algorithm was used to categorize five human activities (i.e., low human-impact, agricultural inputs, domestic inputs, industrial inputs, and dam construction). The SCML optimal configuration is (MBIs + MRA + EGIs) exhibited strong performance with TestW R2 of 0.882 and TestS R2 of 0.924. This study provides valuable insights for improving ecosystem management, supporting sustainable water resource management and advancing pollution mitigation efforts.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Science, Beijing 100012, China; State Environmental Protection Key Laboratory of Estuarine and Coastal Enviro…
- State Key Joint Laboratory of Environment Simulation and Pollution Control (SKLESPC), School of Environment, Tsinghua University, Beijing 100084, China.
- State Key Laboratory of Heavy Oil Processing, Beijing Key Laboratory of Biogas Upgrading Utilization, College of New Energy and Materials, China University of Petroleum Beijing (CUPB), Beijing, 102249, China.
Förderung
- China Scholarship Council
- Chinese Research Academy of Environmental Sciences
Zitieren
APA
Jing, Z., Zhang, Y., Liu, X., Li, Q., Hao, Y., Li, Y., & Gao, H. (2025). Identifying human activities causing water pollution based on microbial community sequencing and source classifier machine learning. Environment International, 195, 109240. https://doi.org/10.1016/j.envint.2024.109240
Vancouver
Jing Z, Zhang Y, Liu X, Li Q, Hao Y, Li Y, et al. Identifying human activities causing water pollution based on microbial community sequencing and source classifier machine learning. Environment International. 2025;195:109240. doi:10.1016/j.envint.2024.109240
BibTeX
@article{Jing2025,
author = {Jing, Zhangmu and Zhang, Yi and Liu, Xiaoling and Li, Qingqian and Hao, Yanji and Li, Yeqing and Gao, Hongjie},
title = {Identifying human activities causing water pollution based on microbial community sequencing and source classifier machine learning},
journal = {Environment International},
year = {2025},
volume = {195},
pages = {109240},
doi = {10.1016/j.envint.2024.109240}
}
EUVIMED