Safety monitoring functions as the “doctor” of concrete dams, ensuring their safety by providing long-term, periodic, or continuous historical observation data. Through mathematical statistics, data mining, and expert knowledge, the working state of concrete dams can be comprehended, their health status diagnosed, and real-time safety monitoring realized. However, raw monitoring data is complex and requires meticulous analysis to identify outliers. Mining and analyzing this data are important for accurately detecting anomalies. This study explores the application and comparative efficiency of three advanced outlier detection techniques: Isolation Forest (IF), Local Outlier Factor (LOF), and the ensemble approach “cascade” IF-LOF. The ensemble approach leverages the complementary capabilities of IF and LOF techniques to provide a more robust and accurate anomaly detection (AD) system. The proposed hierarchical IF-LOF model was evaluated on real-world dam displacement datasets, where it demonstrated superior performance in identifying subtle anomalies that individual methods often missed, achieving an accuracy rate of 98% and F1-scores consistently above 92% across all monitoring points. This study emphasizes the value of combining techniques to overcome single-algorithm limitations, especially with high-dimensional, noisy data. It enhances AD reliability, advancing safety monitoring for concrete dams. The findings highlight the potential of the ensemble methods in structural health monitoring and support further research on infrastructure safety and maintenance optimization.
VörösmartyCJGreenPSalisburyJ, et al. Global water resources: vulnerability from climate change and population growth. Science2000; 289(5477): 284–288.
2.
JhaAKBlochRLamondJ. Cities and flooding: a guide to integrated urban flood risk management for the 21st century. Washington, DC, USA: World Bank Publications, 2012.
3.
KiranRTeodoriuCDadmohammadiY, et al., Identification and evaluation of well integrity and causes of failure of well integrity barriers (a review). J Nat Gas Sci Eng2017; 45: 511–526.
4.
LiH-NRenLJiaZ-G, et al. State-of-the-art in structural health monitoring of large and complex civil infrastructures. J Civ Struct Health Monit2016; 6(1): 3–16.
5.
BrownjohnJMW. Structural health monitoring of civil infrastructure. Philos Trans R Soc A Math Phys Eng Sci2007; 365(1851): 589–622.
6.
BehniaAChaiHKShiotaniT.Advanced structural health monitoring of concrete structures with the aid of acoustic emission. Constr Build Mater2014; 65: 282–302.
7.
DaiBGuCZhaoE, et al. Statistical model optimized random forest regression model for concrete dam deformation monitoring. Struct Control Health Monit2018; 25(6): e2170.
8.
MoustafaNSlayJ.The evaluation of network anomaly detection systems: statistical analysis of the UNSW-NB15 data set and the comparison with the KDD99 data set. Inf Secur J2016; 25(1–3): 18–31.
9.
LiXLiYZhangP, et al. An online anomaly recognition and early warning model for dam safety monitoring data. Struct Health Monit2020; 19(3): 796–809.
10.
ShaoCZhengSGuC, et al. A novel outlier detection method for monitoring data in dam engineering. Expert Syst Appl2022; 193: 116476.
11.
SalazarFToledoMAGonzálezJM, et al. Early detection of anomalies in dam performance: a methodology based on boosted regression trees. Struct Control Health Monit2017; 24(11): e2012.
12.
RicoJBarateiroJMataJ, et al. Applying advanced data analytics and machine learning to enhance the safety control of dams. In: TsihrintzisGAVirvouMSakkopoulosE, et al. (eds) Machine learning paradigms: applications of learning and analytics in intelligent systems. Cham: Springer International Publishing, 2019, 315–350.
13.
ZhangFLuXLiY, et al. A self-matching model for online anomaly recognition of safety monitoring data in dams. Struct Health Monit2023; 22(1): 746–773.
14.
SalazarFCondeAIrazabalJ, et al. Anomaly detection in dam behaviour with machine learning classification models. Water2021; 13(17): 2387.
15.
RongZPangRXuB, et al. Dam safety monitoring data anomaly recognition using multiple-point model with local outlier factor. Autom Constr2024; 159: 105290.
16.
ChandolaVBanerjeeAKumarV.Anomaly detection: a survey. ACM Comput Surv2009; 41(3): Article 15.
17.
Ariyaluran HabeebRANasaruddinFGaniA, et al. Real-time big data processing for anomaly detection: a survey. Int J Inf Manage2019; 45: 289–307.
18.
LaskarMTRHuangJXSmetanaV, et al. Extending isolation forest for anomaly detection in big data via k-means. ACM Trans Cyber Phys Syst2021; 5(4): Article 41.
19.
TaoXPengYZhaoF, et al. A parallel algorithm for network traffic anomaly detection based on isolation forest. Int J Distrib Sens Netw2018; 14(11): 1550147718 814471.
ChengZZouCDongJ.Outlier detection using isolation forest and local outlier factor. In: Proceedings of the conference on research in adaptive and convergent systems, Chongqing, China, September 24–27, 2019. Chongqing: Association for Computing Machinery.
25.
AlghushairyOAlsiniRSouleT, et al. A review of local outlier factor algorithms for outlier detection in big data streams. Big Data Cogn Comput2021; 5(1): 1.
26.
XuHZhangLLiP, et al. Outlier detection algorithm based on k-nearest neighbors-local outlier factor. J Algorithms Comput Technol2022; 16: 1748302622107 8111.
27.
WangGChenY.Robust feature matching using guided local outlier factor. Pattern Recognit2021; 117: 107986.
28.
ELHadadRTanYFTanWN. Comparison of enhanced isolation forest and enhanced local outlier factor in anomalous power consumption labelling. In: 2023 IEEE 3rd international conference in power engineering applications (ICPEA), Putrajaya, Malaysia, March 6–7, 2023. Piscataway, New Jersey, USA: IEEE
29.
ElmahalwyAMousaHAminK.New hybrid ensemble method for anomaly detection in data science. Int J Electr Comput Eng2023; 13: 3498.
30.
SaheedYKAbdulganiyuOHTchakouchtTA.A novel hybrid ensemble learning for anomaly detection in industrial sensor networks and SCADA systems for smart city infrastructures. J King Saud Univ Comput Inf Sci2023; 35(5): 101532.
31.
JiLZhangXZhaoY, et al., Anomaly detection of dam monitoring data based on improved spectral clustering. J Internet Technol2022; 23(4): 11.
32.
LiuYZhuLDingL, et al. Selective ensemble method for anomaly detection based on parallel learning. Sci Rep2024; 14: 1420.
33.
NawazAKhanSAhmadA.Ensemble of autoencoders for anomaly detection in biomedical data: a narrative review. IEEE Access2024; 12: 17273–17289.
34.
LiuFTTingKMZhouZH.Isolation forest. In: Proceedings of the 2008 Eighth IEEE international conference on data mining, December 15–19, pp. 413–422, 2008. Pisa, Italy: IEEE.
35.
DarrabSAllipilliHGhaniS, et al. Anomaly detection algorithms: comparative analysis and explainability perspectives. In: Benavides-PradoDErfaniSFournier-VigerPBooYLKohYS (eds.) Data science and machine earning: Proceedings of the 21st Australasian onference on data science and machine learning (AusDM 2023)Singapore: Springer Nature, 2023; pp. 90–104.
36.
KimS-YMukhiddinovM.Data anomaly detection for structural health monitoring based on a convolutional neural network. Sensors2023; 23(20): 8525.
37.
FarrarCRWordenK.An introduction to structural health monitoring. Philos Trans R Soc A Math Phys Eng Sci2007; 365(1851): 303–315.
38.
LiuXLiZSunL, et al. A critical review of statistical model of dam monitoring data. J Build Eng2023; 80: 108106.
39.
Salazar GonzálezF. A machine learning-based methodology for anomaly detection in dam behaviour. Ph.D. thesis, Universitat Politécnica de Catalunya, Barcelona, Spain, 2017.
40.
QuatriniECostantinoFDi GravioG, et al. Machine learning for anomaly detection and process phase classification to improve safety and maintenance activities. J Manuf Syst2020; 56: 117–132.
41.
SohnH.Effects of environmental and operational variability on structural health monitoring. Philos Trans R Soc A Math Phys Eng Sci2007; 365(1851): 539–560.
42.
WangYLiuG.Self-supervised dam deformation anomaly detection based on temporal-spatial contrast learning. Sensors2024; 24(17): 5858.
ZhouYBaoTShuX, et al. BIM and ontology-based knowledge management for dam safety monitoring. Autom Constr2023; 145: 104649.
45.
LiYPangRXuB, et al. Jaya-ICSM: a rapid inverse method driven by monitoring data for concrete-faced rockfill dams static displacement simulation. Adv Eng Inform2023; 57: 102080.
46.
HeiglMAnandKAUrmannA, et al. On the improvement of the isolation forest algorithm for outlier detection with streaming data. Electronics2021; 10(13): 1534.
47.
BreunigMMKriegelH-PNgRT, et al. LOF: identifying density-based local outliers. Sigmod Rec2000; 29(2): 93–104.
48.
BaoYTangZLiH, et al. Computer vision and deep learning–based data anomaly detection method for structural health monitoring. Struct Health Monit2019; 18(2): 401–421.
49.
YangJQuX-dChangM.An intelligent singular value diagnostic method for concrete dam deformation monitoring. Water Sci Eng2019; 12: 205–212.
50.
LiXLiYLuX, et al. An online anomaly recognition and early warning model for dam safety monitoring data. Struct Health Monit2019; 19: 147592171986426.
51.
GaleanoPPeñaDTsayR.Outlier detection in multivariate time series by projection pursuit. J Am Stat Assoc2006; 101: 654–669.
52.
CongTTanROttewillJR, et al. Anomaly detection and mode identification in multimode processes using the field Kalman filter. IEEE Trans Control Syst Technol2021; 29(5): 2192–2205.
53.
ShuXBaoTXuR, et al. Dam anomaly assessment based on sequential variational autoencoder and evidence theory. Appl Math Model2021; 98: 576–594.
54.
SchleglTSeeböckPWaldsteinSM, et al. F-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks. Med Image Anal2019; 54: 30–44.
55.
ZhouYShuXBaoT, et al. Dam safety assessment through data-level anomaly detection and information fusion. Struct Health Monit2022; 22: 147592172211174.
56.
RuffLKauffmannJRVandermeulenRA, et al. A unifying review of deep and shallow anomaly detection. Proc IEEE2021; 109(5): 756–795.
