For concrete arch dams, the displacement at different monitoring points exhibits a high degree of correlation and uncertainty. In order to improve the accuracy of displacement prediction by using displacement correlation, this study first employs adaptive weighted derivative dynamic time warping and clustering algorithms to determine the regional segmentation of the arch dam. Furthermore, the residual network (ResNet) was enhanced by incorporating convolution kernels of varying sizes and introducing squeeze and excitation (SE) blocks, resulting in the development of multi-path ResNet with SE block (SE-MPRN). Next, the maximal information coefficient was employed to assess the displacement correlation of monitoring points within the region, followed by adjustments to the regressor chain (RC), the corrected ensemble of RCs (CERC) was proposed. By integrating CERC with SE-MPRN, the multi-target (MT) displacement prediction method for arch dams, SE-MPRNCERC, was established. Finally, to quantify the uncertainty in arch dam displacement prediction, SE-MPRNCERC was combined with upper and lower bound estimation (LUBE) to establish a MT displacement interval prediction method. The results of the engineering case study demonstrate that SE-MPRN exhibits exceptional ability in learning the complex relationship between influencing factors and displacement. Compared to other deep learning-based MT prediction methods, the proposed MT method, SE-MPRNCERC, significantly enhances the accuracy of arch dam point value predictions. The integration of SE-MPRNCERC with LUBE for MT displacement interval prediction greatly improves the quality of the prediction intervals, providing a new reliable technological support for arch dam safety monitoring.
AriffinWNHWSidekLMBasriH, et al. Overtop risk of high-hazard embankment dam under climate change condition. PLoS One2025; 20(2): e0311181.
2.
Marchamalo-SacristánMRuiz-ArmenterosAMLamas-FernándezF, et al. MT-InSAR and dam modeling for the comprehensive monitoring of an Earth-fill dam: the case of the Benínar dam. Remote Sens2023; 15(11): 2802.
3.
FuCZhaoTLiH, et al. Investigating the failure mechanisms of cascade landslide dams under overtop conditions: an experimental approach. Sci Rep2025; 15(1): 5835.
4.
KaralarMCavusliM.Seismic effects of epicenter distance of earthquake on 3D damage performance of CG dams. Earthq Struct2020; 18(2): 201–213.
5.
KaralarMCavusluM.Determination of 3D near fault seismic behaviour of Oroville earth fill dam using burger material model and free field-quiet boundary conditions. Math Comput Model Dyn Syst2022; 28(1): 55–77.
6.
SuHLiXYangB, et al. Wavelet support vector machine-based prediction model of dam deformation. Mech Syst Signal Process2018; 110: 412–427.
7.
ShaoCZhengSGuC, et al. A novel outlier detection method for monitoring data in dam engineering. Expert Syst Appl2022; 193: 116476.
8.
ChenBHuTHuangZ, et al. A spatio-temporal clustering and diagnosis method for concrete arch dams using deformation monitoring data. Struct Health Monit2019; 18(5–6): 1355–1371.
9.
XuBChenZWangX, et al. Combined prediction model of concrete arch dam displacement based on cluster analysis considering signal residual correction. Mech Syst Signal Process2023; 203: 110721.
10.
HuangBKangFLiJ, et al. Displacement prediction model for high arch dams using long short-term memory based encoder-decoder with dual-stage attention considering measured dam temperature. Eng Struct2023; 280: 115686.
11.
WangSSuiXLiuY, et al. Prediction and interpretation of the deformation behaviour of high arch dams based on a measured temperature field. J Civ Struct Health Monit2023; 13(2): 661–675.
12.
WangSXuYGuC, et al. Two spatial association–considered mathematical models for diagnosing the long-term balanced relationship and short-term fluctuation of the deformation behaviour of high concrete arch dams. Struct Health Monit2020; 19(5): 1421–1439.
13.
WangSXuCLiuY, et al. Mixed-coefficient panel model for evaluating the overall deformation behavior of high arch dams using the spatial clustering. Struct Control Health Monit2021; 28(10): e2809.
14.
CaoXShengJJiangC, et al. Concrete dam deformation prediction model considering the time delay of monitoring variables. Sci Rep2025; 15(1): 8458.
15.
LiuRRenQLiM, et al. A similarity-aware ensemble method for displacement prediction of concrete dams based on temporal division and fully Bayesian learning. Adv Eng Inform2024; 62: 102921.
16.
WangLCaoHYeZ, et al. Bayesian large-kernel attention network for bearing remaining useful life prediction and uncertainty quantification. Reliab Eng Syst Saf2023; 238: 109421.
17.
YangXXiangYShenG, et al. A combination model for displacement interval prediction of concrete dams based on residual estimation. Sustainability2022; 14(23): 16025.
18.
GuCWuBChenY.A High-robust displacement prediction model for super-high arch dams integrating wavelet de-noising and improved random forest. Water2023; 15(7): 1271.
19.
LiMPanJLiuY, et al. Dam deformation forecasting using SVM-DEGWO algorithm based on phase space reconstruction. PLoS One2022; 17(6): e0267434.
20.
KangFLiuJLiJ, et al. Concrete dam deformation prediction model for health monitoring based on extreme learning machine. Struct Control Health Monit2017; 24(10): e1997.
21.
WuYKangFZhuS, et al. Data-driven deformation prediction model for super high arch dams based on a hybrid deep learning approach and feature selection. Eng Struct2025; 325: 119483.
22.
XuBChenZSuH, et al. A deep learning method for predicting the displacement of concrete arch dams considering the effect of cracks. Adv Eng Inform2024; 62: 102574.
23.
LiMLiMRenQ, et al. DRLSTM: a dual-stage deep learning approach driven by raw monitoring data for dam displacement prediction. Adv Eng Inform2022; 51: 101510.
24.
ZhangHXuBChenZ.A novel reconstruction method for displacement missing data of arch dam via hierarchical clustering and deep learning. Eng Appl Artif Intell2024; 133: 108586.
25.
JiaoRZengSLiC, et al. Handling constrained many-objective optimization problems via problem transformation. IEEE Trans Cybern2020; 51(10): 4834–4847.
26.
TsoumakasGSpyromitros-XioufisEVrekouA, et al. Multi-target regression via random linear target combinations. In: Joint European conference on machine learning and knowledge discovery in databases, Berlin, Heidelberg, 15–19 September 2014, pp. 225–240. Cham: Springer.
27.
Spyromitros-XioufisETsoumakasGGrovesW, et al. Multi-target regression via input space expansion: treating targets as inputs. Mach Learn2016; 104: 55–98.
28.
PengTSellamiSBoucelmaO, et al. Multi-output regression for imbalanced data stream. Expert Syst2023; 40(10): e13417.
29.
ZhenXYuMZhengF, et al. Multi-target sparse latent regression. IEEE Trans Neural Netw Learn Syst2017; 29(5): 1575–1586.
30.
ZhenXYuMHeX, et al. Multi-target regression via robust low-rank learning. IEEE Trans Patt Anal Mach Intell2017; 40(2): 497–504.
31.
ChenSGuCLinC, et al. Prediction of arch dam deformation via correlated multi-target stacking. Appl Math Model2021; 91: 1175–1193.
32.
XuBZhuZQiuX, et al. Real measurement data-driven correlated hysteresis monitoring model for concrete arch dam displacement. Expert Syst Appl2024; 238: 121752.
33.
WangSXuCLiuY, et al. A spatial association-coupled double objective support vector machine prediction model for diagnosing the deformation behaviour of high arch dams. Struct Health Monit2022; 21(3): 945–964.
34.
XuBChenZSuH, et al. Interval prediction method for dynamic zoning of displacements in super-high arch dam under significant water level fluctuations. Struct Health Monit2025; 24(6): 3825–3848.
35.
RenQLiMShenY.A new interval prediction method for displacement behavior of concrete dams based on gradient boosted quantile regression. Struct Control Health Monit2022; 29(1): e2859.
36.
ChenSGuCLinC, et al. Multi-kernel optimized relevance vector machine for probabilistic prediction of concrete dam displacement. Eng Comput2021; 37(3): 1943–1959.
37.
ChenXSunWHuS, et al. Uncertainty-informed regional deformation diagnosis of arch dams. Comput Aided Civ Infrastruct Eng2025; 40(10): 1344–1369.
38.
MelkiGCanoAKecmanV, et al. Multi-target support vector regression via correlation regressor chains. Inform Sci2017; 415: 53–69.
39.
WuZ.Safety monitoring theory and its application of hydraulic structures. Beijing: Higher Education Press, 2003 (in Chinese).
40.
DerisoDBoydS.A general optimization framework for dynamic time warping. Optim Eng2023; 24(2): 1411–1432.
41.
LiMZhuYZhaoT, et al. Weighted dynamic time warping for traffic flow clustering. Neurocomputing2022; 472: 266–279.
42.
LuczakM.Hierarchical clustering of time series data with parametric derivative dynamic time warping. Expert Syst Appl2016; 62: 116–130.
43.
JeongYJeongMOmitaomuO.Weighted dynamic time warping for time series classification. Pattern Recognit2011; 44(9): 2231–2240.
44.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 27–30 June 2016, pp. 770–778. Piscataway: IEEE.
45.
KhanMHossniY.A comparative analysis of LSTM models aided with attention and squeeze and excitation blocks for activity recognition. Sci Rep2025; 15(1): 3858.
46.
BejaniMMGhateeM.A systematic review on overfitting control in shallow and deep neural networks. Artif Intell Rev2021; 54(8): 6391–6438.
47.
SzegedyCLiuWJiaY, et al. Going deeper with convolution. In: IEEE conference on computer vision and pattern recognition, Boston, MA, USA, 8–10 June 2015, pp. 1–9. Piscataway: IEEE.
48.
XuJLiZDuB, et al. Reluplex made more practical: leaky ReLU. In: IEEE symposium on computers and communications, Rennes, 7–10 July 2020, pp. 1–7. Piscataway: IEEE.
49.
GuoZYuBHaoM, et al. A novel hybrid method for flight departure delay prediction using random forest regression and maximal information coefficient. Aerosp Sci Technol2021; 116: 106822.
50.
LianCZengZWangX, et al. Landslide displacement interval prediction using lower upper bound estimation method with pre-trained random vector functional link network initialization. Neural Netw2020; 130: 286–296.
51.
HuYShaoCGuC, et al. Concrete dam displacement prediction based on an ISODATA-GMM clustering and random coefficient model. Water2019; 11(4): 714.
