Abstract
The seepage of the dam is an important representation of the operation characteristics of the dam, and there are many factors affecting the seepage with a certain lag. It is still difficult to predict its change and sensitivity because of complex operating conditions. At present, the lag-sensitivity of influence factors of the dam seepage has not been studied. The time series influence factors of seepage are determined by HTRT (hydrostatic-thermal-rainfall-time) model in this paper. To avoid the pseudo fitting of conventional methods, HTRT model nested random forest algorithm is used to establish the predicting model of the dam seepage. And MIC algorithm is used to achieve the dual purposes of time lag and sensitivity analysis. Firstly, the time lag of relationship between seepage and its influencing factors is characterized, and the most appropriate lag time of the HTRT model factors is determined. Secondly, independent correlation analysis on all influencing factors is carried out and the sensitivity of each factor is analyzed by MIC. Meanwhile, the sensitivity of the factors to seepage is quantitatively analyzed by the two parameters of %IncMSE and IncNodePurity of RF algorithm. The sensitivity of influencing factors is analyzed by comparing MIC results with RF results. Combined with the case, taking the error of fitting prediction as the evaluation index of seepage prediction, the prediction accuracy of MIC-RF model, RF model and MIC-BPNN (Back Propagation neural network) model is calculated and compared. Case study showed that MIC- RF monitoring model has high prediction accuracy, strong adaptability and high robustness in dam seepage, and the sensitivity and time lag of influencing factors can be quantitatively analyzed. The water pressure and rainfall of the lag time are 14 days and 16 days respectively. The sensitivity study of the time series influencing factors of seepage showed that the water pressure component is the main controlling factor of seepage, and rainfall component is more sensitive to later stage. The MIC-RF model can be used as a new dam seepage safety monitoring model.
Similar content being viewed by others
![](https://media.springernature.com/w215h120/springer-static/image/art%3A10.1007%2Fs00366-019-00806-0/MediaObjects/366_2019_806_Fig1_HTML.png)
References
Belmokre A, Mihoubi M, Santillan D (2019) Seepage and dam deformation analyses with statistical models: Support vector regression machine and random forest. Procedia Structural Integrity 17(C):698–703, DOI: https://doi.org/10.1016/j.prostr.2019.08.093
Breiman (2001) Random forests. Mach Learn 45(1):5–32, DOI: https://doi.org/10.1023/A:1010933404324
Cao EH, Bao TF, Gu CS, Li H, Liu YT, Hu SP (2020) A novel hybrid decomposition — Ensemble prediction model for dam deformation. Applied Sciences-Basel 10(16):5700, DOI: https://doi.org/10.3390/app10165700
Chen S, He Q, Cao J (2018) Seepage simulation of high concrete-faced rockfill dams based on generalized equivalent continuum model. Water Science and Engineering 11(3):250–257, DOI: https://doi.org/10.1016/j.wse.2018.10.004
Chen Y, Hu R, Lu W, Li D, Zhou C (2011) Modeling coupled processes of non-steady seepage flow and non-linear deformation for a concrete-faced rockfill dam. Computers & Structures 89(13–14):1333–1351, DOI: https://doi.org/10.1016/j.compstruc.2011.03.012
Costa L, Alonso E (2009) Predicting the behavior of an earth and rockfill dam under construction. Journal of Geotechnical & Geoenvironmental Engineering 135(7):851–862, DOI: https://doi.org/10.1061/(ASCE)GT.1943-5606.0000058
Dai B, Gu C, Zhao E, Qin X (2018) Statistical model optimized random forest regression model for concrete dam deformation monitoring. Structural Control and Health Monitoring 25(6), DOI: https://doi.org/10.1002/stc.2170
Dan G, Zhang Y, Zhao Y (2009) Random forest algorithm for classification of multiwavelength data. Research in Astronomy and Astrophysics 9(2):220–226, DOI: https://doi.org/10.1088/1674-4527/9/2/011
Deng G, Cao K, Chen R, Wen Y, Zhang Y, Chen Z (2020) A new method for dynamically estimating long-term seepage failure frequency for high concrete faced rockfill dams. Environmental Earth Sciences 79(10), DOI: https://doi.org/10.1007/s12665-020-08962-z
Fukuchi T (2018) New high-precision empirical methods for predicting the seepage discharges and free surface locations of earth dams validated by numerical analyses using the IFDM. Soils and Foundations 58(2):427–445, DOI: https://doi.org/10.1016/j.sandf.2018.02.011
Huang H, Chen B (2012). Dam seepage monitoring model based on dynamic effect weight of reservoir water level. Energy Procedia 16: 159–165, DOI: https://doi.org/10.1016/j.egypro.2012.01.027
Jayatilaka CJ, Gillham RW (1996) A deterministic-empirical model of the effect of the capillary fringe on near-stream area runoff 1. Description of the model. Journal of Hydrology 184(3–4): 299–315, DOI: https://doi.org/10.1016/0022-1694(95)02985-0
Kumar S, Sahu AK, Kumar M (2021) Modeling the effect of central impervious core and downstream filter geometry on seepage through earth dams. Ain Shams Engineering Journal 13(1):101510, DOI: https://doi.org/10.1016/j.asej.2021.05.024
Li D, Shen L, Zha W, Liu X, Tan J (2021a). Physics-constrained deep learning for solving seepage equation. Journal of Petroleum Science and Engineering 206:109046, DOI: https://doi.org/10.1016/j.petrol.2021.109046
Li X, Wen Z, Su H (2019) An approach using random forest intelligent algorithm to construct a monitoring model for dam safety. Engineering with Computers 37(1):39–56, DOI: https://doi.org/10.1007/s00366-019-00806-0
Li W, Zhu J, Fu L, Zhu Q, Guo Y, Gong Y (2021b) A rapid 3D reproduction system of dam-break floods constrained by post-disaster information. Environmental Modelling & Software 139, DOI: https://doi.org/10.1016/j.envsoft.2021.104994
Ma H, Chi F (2016) Technical progress on researches for the safety of high concrete-faced rockfill dams. Engineering 2(3):332–339, DOI: https://doi.org/10.1016/j.Eng.2016.03.010
Mardanirad S, Wood DA, Zakeri H (2021) The application of deep learning algorithms to classify subsurface drilling lost circulation severity in large oil field datasets. SN Applied Sciences 3(9), DOI: https://doi.org/10.1007/s42452-021-04769-0
Ranković V, Grujović N, Divac D, Mlivojević N, Novaković A (2012). Modelling of dam behaviour based on neuro-fuzzy identification. Engineering Structures 35:107–113, DOI: https://doi.org/10.1016/j.engstruct.2011.11.011
Refaiy AR, AboulAtta NM, Saad NY, El-Molla DA (2021) Modeling the effect of downstream drain geometry on seepage through earth dams. Ain Shams Engineering Journal 12(3):2511–2531, DOI: https://doi.org/10.1016/j.asej.2021.02.011
Rehamnia I, Benlaoukli B, Jamei M, Karbasi M, Malik A (2021) Simulation of seepage flow through embankment dam by using a novel extended Kalman filter based neural network paradigm: Case study of Fontaine Gazelles Dam, Algeria. Measurement 176, DOI: https://doi.org/10.1016/j.measurement.2021.109219
Reshef DN, Reshef YA, Finucane HK, Grossman SR, McVean G, Turnbaugh PJ, Lander ES, Mitzenmacher M, Sabeti PC (2011) Detecting novel associations in large data sets. Science 334(6062): 1518–1524, DOI: https://doi.org/10.1126/science.1205438
Salazar F, Toledo MA, Oñate E, Morán R (2015). An empirical comparison of machine learning techniques for dam behaviour modelling. Structural Safety 56:9–17, DOI: https://doi.org/10.1016/j.strusafe.2015.05.001
Salmasi F, Abraham J (2020) Predicting seepage from unlined earthen channels using the finite element method and multi variable nonlinear regression. Agricultural Water Management 234, DOI: https://doi.org/10.1016/j.agwat.2020.106148
Shao F, Li K, Xu X (2016). Railway accidents analysis based on the improved algorithm of the maximal information coefficient. Intelligent Data Analysis 20:597–613, DOI: https://doi.org/10.3233/IDA-160822
Shi Y, Zhao C, Peng Z, Yang H, He J (2018). Analysis of the lag effect of embankment dam seepage based on delayed mutual information. Engineering Geology 234:132–137, DOI: https://doi.org/10.1016/j.enggeo.2018.01.009
Shrestha BB, Kawasaki A (2020) Quantitative assessment of flood risk with evaluation of the effectiveness of dam operation for flood control: A case of the Bago River Basin of Myanmar. International Journal of Disaster Risk Reduction 50, DOI: https://doi.org/10.1016/j.ijdrr.2020.101707
Strobl C, Boulesteix AL, Kneib T, Augustin T, Zeileis A (2008). Conditional variable importance for random forests. BMC Bioinformatics 9:307, DOI: https://doi.org/10.1186/1471-2105-9-307
Sun Y, Lan S, Yan J, Song L (2016) Research on seepage problem and character of concrete face rock-fill dam under operating period. Journal of China Institute of Water Resources and Hydropower Research 14(6):431–436+442, http://en.cnki.com.cn/Article_en/CJFDTotal-ZGSX201606005.htm
Sun J, Zhao Z, Zhang Y (2011) Determination of three dimensional hydraulic conductivities using a combined analytical/neural network model. Tunnelling and Underground Space Technology 26(2):310–319, DOI: https://doi.org/10.1016/j.tust.2010.11.002
Tan Z, Yan Z, Zhu G (2019) Stock selection with random forest: An exploitation of excess return in the Chinese stock market. Heliyon 5(8):e02310, DOI: https://doi.org/10.1016/j.heliyon.2019.e02310
Thanakiatkrai P, Yaodam A, Kitpipit T (2013) Age estimation of bloodstains using smartphones and digital image analysis. Forensic Sci Int 233(1–3):288–297, DOI: https://doi.org/10.1016/j.forsciint.2013.09.027
Tourassi G, Frederick E, Markey M K, Floyd C (2001) Application of the mutual information criterion for feature selection in computer-aided diagnosis. Medical Physics 28(12):2394–2402, DOI: https://doi.org/10.1118/1.1418724
Wang W, Wang X, Hua X, Song G, Chen ZJES (2018) Vibration control of vortex-induced vibrations of a bridge deck by a single-side pounding tuned mass damper. Engineering Structures 173(OCT.15): 61–75, DOI: https://doi.org/10.1016/j.engstruct.2018.06.099
**ang Y, Fu S-y, Zhu K, Yuan H, Fang Z-y (2017) Seepage safety monitoring model for an earth rock dam under influence of high-impact typhoons based on particle swarm optimization algorithm. Water Science and Engineering 10(1):70–77, DOI: https://doi.org/10.1016/j.wse.2017.03.005
Xu Y Q, Unami K, Kawachi T (2003) Optimal hydraulic design of earth dam cross section using saturated—unsaturated seepage flow model. Advances in Water Resources 26(1):1–7, DOI: https://doi.org/10.1016/S0309-1708(02)00124-0
Yu H, Wang X, Ren B, Zeng T, Lv M, Wang C (2022) An efficient Bayesian inversion method for seepage parameters using a data-driven error model and an ensemble of surrogates considering the interactions between prediction performance indicators. Journal of Hydrology 604, DOI: https://doi.org/10.1016/j.jhydrol.2021.127235
Yuan D, Gu C, Qin X, Shao C, He J (2022). Performance-improved TSVR-based DHM model of super high arch dams using measured air temperature. Engineering Structures 250:113400, DOI: https://doi.org/10.1016/j.engstruct.2021.113400
Zhang LM, Chen Q (2006) Seepage failure mechanism of the gouhou rockfill dam during reservoir water infiltration. Soils and Foundations 46(5):557–568, DOI: https://doi.org/10.3208/sandf.46.557
Zhang Y, Shang P (2022). KM-MIC: An improved maximum information coefficient based on K-Medoids clustering. Communications in Nonlinear Science and Numerical Simulation 111:106418, DOI: https://doi.org/10.1016/j.cnsns.2022.106418
Zhang H, Song Z, Peng P, Sun Y, Ding Z, Zhang X (2021) Research on seepage field of concrete dam foundation based on artificial neural network. Alexandria Engineering Journal 60(1):1–14, DOI: https://doi.org/10.1016/j.aej.2020.03.041
Zhou L, Wang H (2012) Loan default prediction on large imbalanced data using random forests. TELKOMNIKA Indonesian Journal of Electrical Engineering 10(6), DOI: https://doi.org/10.11591/telkomnika.v10i6.1323
Zhu Q, Xu YL, Zhu LD, Li H (2018). Vortex-induced vibration analysis of long-span bridges with twin-box decks under non-uniformly distributed turbulent winds. Journal of Wind Engineering and Industrial Aerodynamics 172:31–41, DOI: https://doi.org/10.1016/j.jweia.2017.11.005
Zwolinski M, Yang Z, Kazmierski T (2000) Applying mutual information theory to behavioural analogue fault modelling. International Journal of Electronics 87(12):1461–1471, DOI: https://doi.org/10.1080/00207210050192489
Acknowledgments
This research was supported by the Fundamental Research Funds for the Central Universities (2019B70514), Postgraduate Research & Practice Innovation Program of Jiangsu Province (SJKY19_0488), National Key R&D Program of China (2018YFC1508603, 2018YFC0407104, 2018YFC0407101, 2016YFC0401601), and National Natural Science Foundation of China (Grant Nos. 51379068, 51579083, 51579085, 51579086, 51609074, 51739003, 51779086).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, Y., Zheng, D., Wu, X. et al. Research on Prediction of Dam Seepage and Dual Analysis of Lag-Sensitivity of Influencing Factors Based on MIC Optimizing Random Forest Algorithm. KSCE J Civ Eng 27, 508–520 (2023). https://doi.org/10.1007/s12205-022-0611-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-022-0611-6