Explainable deep unsupervised learning for flood monitoring and anomaly detection using multivariate DWLR sensors

Saiprasad Potharaju, Swapnali N. Tambe, Ravi Kumar Tirandasu, Dudla Anil Kumar, B. Kiranmai, M. V. V. Prasad Kantipudi · 2026

Read Explainable deep unsupervised learning for flood monitoring and anomaly detection using multivariate DWLR sensors by Saiprasad Potharaju, Swapnali N. Tambe, Ravi Kumar Tirandasu, Dudla Anil Kumar, B. Kiranmai, M. V. V. Prasad Kantipudi (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/pmc-13473614.txt.

Description

Saiprasad Potharaju and five colleagues built in 2026 an explainable warning system for floods that learns normal river behaviour without labelled events. Threshold monitors react only after water passes a set level, missing the slow build-up driven by interacting weather and water chemistry. Their unsupervised framework feeds data from digital water level recorders, covering water level, rainfall, temperature, pH, and dissolved oxygen, into a sliding-window LSTM autoencoder that learns what normal looks like.

Deviations are flagged by reconstruction error with set thresholds, giving proactive alerts rather than reactive alarms. In real-world recorder data, the system spotted abnormal behaviour several weeks before water levels breached critical marks. Explainability analysis using integrated gradients showed anomalies often began with chemical shifts in pH and dissolved oxygen ahead of any visible rise in water. The authors present the approach as a transparent tool for earlier, better-informed decisions.

Catalog record

CREATORSaiprasad Potharaju, Swapnali N. Tambe, Ravi Kumar Tirandasu, Dudla Anil Kumar, B. Kiranmai, M. V. V. Prasad Kantipudi
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE56 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13473614

Browse the full library · About the Tower of Babel