Adaptive Warning Thresholds for Dam Safety: A KDE-Based Approach

Dams are critical infrastructures that provide essential services such as water supply, hydroelectric power generation, and flood control. As many dams age, the risk of structural failure increases, making safety assurance more urgent than ever. Traditional monitoring systems typically employ predic...

Full description

Saved in:
Bibliographic Details
Main Authors: Nathalia Silva-Cancino, Fernando Salazar, Joaquín Irazábal, Juan Mata
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Infrastructures
Subjects:
Online Access:https://www.mdpi.com/2412-3811/10/7/158
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246362848198656
author Nathalia Silva-Cancino
Fernando Salazar
Joaquín Irazábal
Juan Mata
author_facet Nathalia Silva-Cancino
Fernando Salazar
Joaquín Irazábal
Juan Mata
author_sort Nathalia Silva-Cancino
collection DOAJ
description Dams are critical infrastructures that provide essential services such as water supply, hydroelectric power generation, and flood control. As many dams age, the risk of structural failure increases, making safety assurance more urgent than ever. Traditional monitoring systems typically employ predictive models—based on techniques such as the finite element method (FEM) or machine learning (ML)—to compare real-time data against expected performance. However, these models often rely on static warning thresholds, which fail to reflect the dynamic conditions affecting dam behavior, including fluctuating water levels, temperature variations, and extreme weather events. This study introduces an adaptive warning threshold methodology for dam safety based on kernel density estimation (KDE). The approach incorporates a boosted regression tree (BRT) model for predictive analysis, identifying influential variables such as reservoir levels and ambient temperatures. KDE is then used to estimate the density of historical data, allowing for dynamic calibration of warning thresholds. In regions of low data density—where prediction uncertainty is higher—the thresholds are widened to reduce false alarms, while in high-density regions, stricter thresholds are maintained to preserve sensitivity. The methodology was validated using data from an arch dam, demonstrating improved anomaly detection capabilities. It successfully reduced false positives in data-sparse conditions while maintaining high sensitivity to true anomalies in denser data regions. These results confirm that the proposed methodology successfully meets the goals of enhancing reliability and adaptability in dam safety monitoring. This adaptive framework offers a robust enhancement to dam safety monitoring systems, enabling more reliable detection of structural issues under variable operating conditions.
format Article
id doaj-art-dda671ca62fd411c992f9eade50ef92a
institution Kabale University
issn 2412-3811
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Infrastructures
spelling doaj-art-dda671ca62fd411c992f9eade50ef92a2025-08-20T03:58:31ZengMDPI AGInfrastructures2412-38112025-06-0110715810.3390/infrastructures10070158Adaptive Warning Thresholds for Dam Safety: A KDE-Based ApproachNathalia Silva-Cancino0Fernando Salazar1Joaquín Irazábal2Juan Mata3Centre Internacional de Mètodes Numèrics en Enginyeria (CIMNE), Flumen Research Institute, Universitat Politècnica de Catalunya-BarcelonaTech (UPC), 08034 Barcelona, SpainCentre Internacional de Mètodes Numèrics en Enginyeria (CIMNE), Flumen Research Institute, Universitat Politècnica de Catalunya-BarcelonaTech (UPC), 08034 Barcelona, SpainCentre Internacional de Mètodes Numèrics en Enginyeria (CIMNE), Flumen Research Institute, Universitat Politècnica de Catalunya-BarcelonaTech (UPC), 08034 Barcelona, SpainNational Laboratory for Civil Engineering (LNEC), Concrte Dams Department, 1700-066 Lisboa, PortugalDams are critical infrastructures that provide essential services such as water supply, hydroelectric power generation, and flood control. As many dams age, the risk of structural failure increases, making safety assurance more urgent than ever. Traditional monitoring systems typically employ predictive models—based on techniques such as the finite element method (FEM) or machine learning (ML)—to compare real-time data against expected performance. However, these models often rely on static warning thresholds, which fail to reflect the dynamic conditions affecting dam behavior, including fluctuating water levels, temperature variations, and extreme weather events. This study introduces an adaptive warning threshold methodology for dam safety based on kernel density estimation (KDE). The approach incorporates a boosted regression tree (BRT) model for predictive analysis, identifying influential variables such as reservoir levels and ambient temperatures. KDE is then used to estimate the density of historical data, allowing for dynamic calibration of warning thresholds. In regions of low data density—where prediction uncertainty is higher—the thresholds are widened to reduce false alarms, while in high-density regions, stricter thresholds are maintained to preserve sensitivity. The methodology was validated using data from an arch dam, demonstrating improved anomaly detection capabilities. It successfully reduced false positives in data-sparse conditions while maintaining high sensitivity to true anomalies in denser data regions. These results confirm that the proposed methodology successfully meets the goals of enhancing reliability and adaptability in dam safety monitoring. This adaptive framework offers a robust enhancement to dam safety monitoring systems, enabling more reliable detection of structural issues under variable operating conditions.https://www.mdpi.com/2412-3811/10/7/158warning thresholdsdam safetykernel density estimation (KDE)anomaly detectionBoosted Regression Tree (BRT)
spellingShingle Nathalia Silva-Cancino
Fernando Salazar
Joaquín Irazábal
Juan Mata
Adaptive Warning Thresholds for Dam Safety: A KDE-Based Approach
Infrastructures
warning thresholds
dam safety
kernel density estimation (KDE)
anomaly detection
Boosted Regression Tree (BRT)
title Adaptive Warning Thresholds for Dam Safety: A KDE-Based Approach
title_full Adaptive Warning Thresholds for Dam Safety: A KDE-Based Approach
title_fullStr Adaptive Warning Thresholds for Dam Safety: A KDE-Based Approach
title_full_unstemmed Adaptive Warning Thresholds for Dam Safety: A KDE-Based Approach
title_short Adaptive Warning Thresholds for Dam Safety: A KDE-Based Approach
title_sort adaptive warning thresholds for dam safety a kde based approach
topic warning thresholds
dam safety
kernel density estimation (KDE)
anomaly detection
Boosted Regression Tree (BRT)
url https://www.mdpi.com/2412-3811/10/7/158
work_keys_str_mv AT nathaliasilvacancino adaptivewarningthresholdsfordamsafetyakdebasedapproach
AT fernandosalazar adaptivewarningthresholdsfordamsafetyakdebasedapproach
AT joaquinirazabal adaptivewarningthresholdsfordamsafetyakdebasedapproach
AT juanmata adaptivewarningthresholdsfordamsafetyakdebasedapproach