Unsupervised Detection of Multivariate Water Quality Anomalies via Residual Feature Embeddings
IEEE Access · 2026 · 14 · 97948-97961
DOI: 10.1109/access.2026.3704534 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Jyotirmoy Bhardwaj und 1 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Monitoring water quality in water utilities via multiple distributed sensors is critical for detecting diverse pollution events. Multivariate water-quality time series, generated by such water quality sensors, often exhibit overlapping seasonal patterns, long-term trends, and irregular disturbances, making anomaly detection challenging without extensive labeled data. In this work, we present an anomaly detection approach based on unsupervised machine learning (ML) using residual feature embeddings and multivariate clustering. To extract anomalies, for each sensor, we compute candidate seasonal periods and fit a polynomial trend, yielding residual vectors that serve as feature embeddings for Isolation Forest (IF), an unsupervised ML approach. IF was used to identify anomalous observations through residual embeddings, and K-Means clustering was used to group residual vectors into similar water-quality events. To aid interpretability, the clusters were further analyzed statistically to identify the potential signatures of anomalous events. Validation is performed on data annotated by domain experts. This approach enables robust unsupervised anomaly detection by effectively handling multiple overlapping seasonality and trends that might otherwise obscure anomalies. An experimental evaluation of multivariate water-quality datasets demonstrates that the proposed method successfully identifies unusual events and provides valuable insights for water utilities.
Zitieren
APA
Bhardwaj, J., & Cenkeramaddi, L. R. (2026). Unsupervised Detection of Multivariate Water Quality Anomalies via Residual Feature Embeddings. IEEE Access, 14, 97948-97961. https://doi.org/10.1109/access.2026.3704534
Vancouver
Bhardwaj J, Cenkeramaddi LR. Unsupervised Detection of Multivariate Water Quality Anomalies via Residual Feature Embeddings. IEEE Access. 2026;14:97948-97961. doi:10.1109/access.2026.3704534
BibTeX
@article{Bhardwaj2026,
author = {Bhardwaj, Jyotirmoy and Cenkeramaddi, Linga Reddy},
title = {Unsupervised Detection of Multivariate Water Quality Anomalies via Residual Feature Embeddings},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {97948--97961},
doi = {10.1109/access.2026.3704534}
}
EUVIMED