Toward trustworthy water quality monitoring under sensor unreliability
Jin Li, Kleanthis Malialis, Demetrios G. Eliades, Marios M. Polycarpou · 2026
Read Toward trustworthy water quality monitoring under sensor unreliability by Jin Li, Kleanthis Malialis, Demetrios G. Eliades, Marios M. Polycarpou (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13630539.txt.
Description
Jin Li and three colleagues built a monitoring framework for drinking water networks that stays trustworthy even when its own sensors lie. Water quality sensors are costly and fault-prone, and a glitching sensor can trigger false contamination alarms or mask a real event, yet most detection methods assume perfect measurements. Their 2026 framework tackles faults and contamination together.
One neural network spots corrupted readings and rebuilds the clean signal, while a second isolates which sensor is faulty, and an explicit check separates sensor-induced wobbles from true contamination signatures. Tested on three realistic networks with simulated chlorine-reactive pollution, exact source pinpointing stayed hard under sparse coverage, but the system narrowed likely source regions well. The authors argue joint modelling is the practical path for real deployments.
Catalog record
| CREATOR | Jin Li, Kleanthis Malialis, Demetrios G. Eliades, Marios M. Polycarpou |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 99325 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |