Turn off MathJax
Article Contents
CHEN Xiangyu,GUO Yonggang,ZHOU Xingbo,et al. Rapid assessment of earthquake damage of reservoir dam based on BO-GBDT[J]. Bulletin of Geological Science and Technology,2025,44(3):1-14 doi: 10.19509/j.cnki.dzkq.tb20240425
Citation: CHEN Xiangyu,GUO Yonggang,ZHOU Xingbo,et al. Rapid assessment of earthquake damage of reservoir dam based on BO-GBDT[J]. Bulletin of Geological Science and Technology,2025,44(3):1-14 doi: 10.19509/j.cnki.dzkq.tb20240425

Rapid assessment of earthquake damage of reservoir dam based on BO-GBDT

doi: 10.19509/j.cnki.dzkq.tb20240425
More Information
  • Author Bio:

    E-mail:1835461087@qq.com

  • Corresponding author: E-mail:1960373107@qq.com
  • Received Date: 31 Jul 2024
  • Accepted Date: 28 Nov 2024
  • Rev Recd Date: 18 Sep 2024
  • Available Online: 05 Dec 2024
  • <p>Reservoir dams are major lifeline projects, and how to quickly and effectively assess the damage of reservoir dams after an earthquake is of great significance to the development of rescue programs and post-disaster restoration. </p></sec><sec><title>Objective

    In order to quickly and accurately assess the damage degree of reservoir dams hit by earthquakes,

    Methods

    This paper selects the earthquake damage details of each reservoir dam of the Wenchuan 8.0 magnitude earthquake, combines the structural characteristics of the dams and the intensity of earthquakes to construct the assessment index system and data set, uses the k-nearest-neighbor interpolation method to deal with the missing value of the samples and judges the sample feature correlation, and proposed a rapid assessment model of reservoir dam earthquake damage based on gradient boosting algorithm. Four hyper-parameter optimization methods, namely Grid Search (GS), Particle swarm optimization (PSO), Bayesian optimization (BO) and HyperBand Search (HS), are used to optimize the parameters of the Gradient Boosted Tree (GBDT) regression algorithm,compare the models based on their performance metrics (coefficient of determination R2, root mean square error RMSE, mean absolute error MAE), and rank the feature importance of the optimal models.

    Conclusion

    The results show that the BO-GBDT model can assess the degree of earthquake damage of reservoir dams with the shortest time consumption as well as high accuracy, with a high coefficient of determination R2 of 0.99, and a feature importance score indicating that the maximum crack width is the most influential factor. Comparing the results of using this model with those of the earth dam damage assessment model based on the improved empirical statistical model, the accuracy is further improved, which verifies the reliability of the model in the application of rapid investigation and assessment of post-earthquake damage of reservoir dams.

     

  • loading
  • [1]
    颜婷,肖鸿,林鹏智. 芦山地震水库震害考察及灾区大坝总风险评估[J]. 四川大学学报(工程科学版),2015,47(增刊):41-43.

    YAN T,XIAO H,LIN P Z. Examination of reservoir damage in the Lushan earthquake and total risk assessment of dams in the disaster area[J]. Journal of Sichuan University (Engineering Science Edition),2015,47(Supp. ):41-43. (in Chinese with English abstract
    [2]
    JING L P,LIANG H A,LI Y Q,et al. Characteristics and factors that infl uenced damage to dams in the Ms8.0 Wenchuan earthquake[J]. Earthquake Engineering and Engineering Vibration,2011,10:349-358.
    [3]
    梁海安. 土石坝震害预测及快速评估方法研究[D]. 哈尔滨:中国地震局工程力学研究所,2012.

    LIANG H A. Seismic damage prediction and emergency assessment of earth-rock dam[D]. Haerbing:Insititute of Engineering Mechanics,China Earthquake Administration,2012.(in Chinese with English abstract
    [4]
    PEKAU O A,CUI Y Z. Failure analysis of fractured dams during earthquakes by DEM[J]. Engineering Structures,2004,26(10):1483-1502. doi: 10.1016/j.engstruct.2004.05.019
    [5]
    SINGH R,ROY D,JAIN S K. Analysis of earth dams affected by the 2001 Bhuj earthquake[J]. Engineering Geology,2005,80(3/4):282-291.
    [6]
    DOAN N P,NGUYEN B P,PARK S S. Seismic deformation analysis of earth dams subject to liquefaction using UBCSAND2 model[J]. Soil Dynamics and Earthquake Engineering,2023,172:108003. doi: 10.1016/j.soildyn.2023.108003
    [7]
    WANG G H,LU W B,ZHOU C B,et al. The influence of initial cracks on the crack propagation process of concrete gravity dam-reservoir-foundation systems[J]. Journal of Earthquake Engineering,2015,19(6):991-1011. doi: 10.1080/13632469.2015.1021407
    [8]
    GHAEDI K,HEJAZI F,IBRAHIM Z,et al. Flexible foundation effect on seismic analysis of roller compacted concrete (RCC) dams using finite element method[J]. KSCE Journal of Civil Engineering,2018,22(4):1275-1287. doi: 10.1007/s12205-017-1088-6
    [9]
    饶为胜,杜成斌,江守燕,等. 土坝震害分类快速预测的模糊概率方法[J]. 灾害学,2017,32(2):206-209,214. doi: 10.3969/j.issn.1000-811X.2017.02.036

    RAO W S,DU C B,JIANG S Y,et al. Fuzzy probability method for fast predicting earthquake damage type of earth dam[J]. Journal of Catastrophology,2017,32(2):206-209,214. (in Chinese with English abstract doi: 10.3969/j.issn.1000-811X.2017.02.036
    [10]
    郭恩栋,张丽娜,王亚东,等. 土坝震害评估模型研究[J]. 岩土力学,2011,32(12):3667-3671. doi: 10.3969/j.issn.1000-7598.2011.12.022

    GUO E D,ZHANG L N,WANG Y D,et al. Study of evaluation model of earthquake damage to earth dams[J]. Rock and Soil Mechanics,2011,32(12):3667-3671. (in Chinese with English abstract doi: 10.3969/j.issn.1000-7598.2011.12.022
    [11]
    吴云星,谷艳昌,王士军,等. 基于信息熵-变权模糊模型的土石坝震损评估[J]. 水利水运工程学报,2018(4):38-45.

    WU Y X,GU Y C,WANG S J,et al. Assessment of seismic damage for earth-rockfill dam based on information entropy variable weight fuzzy model[J]. Hydro-Science and Engineering,2018(4):38-45. (in Chinese with English abstract
    [12]
    陆耀波,欧阳志勇. 灰关联分析与BP人工神经网络在土石坝震害群体预测中的运用[J]. 华南地震,2014,34(增刊):90-94.

    LU Y B,OUYANG Z Y. Forecasting seismic damage to buildings based on grey relation and artificial neural network model[J]. South China Journal of Seismology,2014,34(Supp.):90-94. (in Chinese with English abstract
    [13]
    杨灿,刘磊磊,张遗立,等. 基于贝叶斯优化机器学习超参数的滑坡易发性评价[J]. 地质科技通报,2022,41(2):228-238.

    YANG C,LIU L L,ZHANG Y L,et al. Machine learning based on landslide susceptibility assessment with Bayesian optimized the hyperparameters[J]. Bulletin of Geological Science and Technology,2022,41(2):228-238. (in Chinese with English abstract
    [14]
    郭衍昊,窦杰,向子林,等. 基于优化负样本采样策略的梯度提升决策树与随机森林的汶川同震滑坡易发性评价[J]. 地质科技通报,2024,43(3):251-265.

    GUO Y H,DOU J,XIANG Z L,et al. Optimized negative sampling strategy of Gradient Boosting Decision Tree and Random Forest for evaluating Wenchuan coseismic landslides susceptibility mapping[J]. Bulletin of Geological Science and Technology,2024,43(3):251-265. (in Chinese with English abstract
    [15]
    林琴,郭永刚,吴升杰,等. 基于梯度提升的优化集成机器学习算法对滑坡易发性评价:以雅鲁藏布江与尼洋河两岸为例[J]. 西北地质,2024,57(1):12-22. doi: 10.12401/j.nwg.2023031

    LIN Q,GUO Y G,WU S J,et al. Evaluation of landslide susceptibility by optimization integrated machine learning Algorithm based on gradient boosting:Take both banks of Yarlung Zangbo river and Niyang river as examples[J]. Northwestern Geology,2024,57(1):12-22. (in Chinese with English abstract doi: 10.12401/j.nwg.2023031
    [16]
    LIU X,LIANG Y Q,FU X. et al. Assessment of typhoon disaster loss based on the factor analysis-random forest model[J]. Journal of Physics:Conference Series,2024,2718:012043. doi: 10.1088/1742-6596/2718/1/012043
    [17]
    ZHANG Y X,ZHANG T Y,SHEN W Q,et al. Economic loss assessment of typhoon-induced storm surge disasters in the South China Sea based on GSA-BP model[J]. Frontiers in Earth Science,2023,11:1258524.
    [18]
    邓日朗,张庆华,刘伟,等. 基于改进两步法采样策略和卷积神经网络的崩塌易发性评价[J]. 地质科技通报,2024,43(2):186-200.

    DENG R L,ZHANG Q H,LIU W,et al. Collapse susceptibility evaluation based on an improved two-step sampling strategy and a convolutional neural network[J]. Bulletin of Geological Science and Technology,2024,43(2):186-200. (in Chinese with English abstract
    [19]
    赵军,汪峻宇,赖强,等. 基于XGBoost 算法的走滑断裂内部特征带的精细识别[J/OL]. 地质科技通报,1-13(2024-04-19)[2024-09-17]. https://doi. org/10.19509/j. cnki. dzkq. tb20230583.

    ZHAO J,WANG J Y,LAI Q,et al. Fine-grained identification of internal characteristic zones within the strike-slip fault using the XGBoost algorithm [J]. Bulletin of Geological Science and Technology,1-13(2024-04-19)[2024-09-17]. https://doi.org/10.19509/j.cnki.dzkq.tb20230583. (in Chinese with English abstract
    [20]
    FRIEDMAN J H. Greedy function approximation:A gradient boosting machine[J]. The Annals of Statistics,2001,29(5):1189-1232. doi: 10.1214/aos/1013203450
    [21]
    BREIMAN L,FRIEDMAN J,OLSHEN R,et al. Classification and regression tree[M]. New York:Chapman,1984.
    [22]
    林森,郭桂祯,刘蓓蓓. 基于梯度提升决策树(GBDT) 算法的南方洪涝灾害房屋倒损评估模型[J]. 灾害学,2020,35(1):109-112,130.

    LIN S,GUO G Z,LIU B B. A model of house damage assessment for southern China based on gradient boosting decision three (GBDT) algorithm[J]. Journal of Catastrophology,2020,35(1):109-112,130. (in Chinese with English abstract
    [23]
    王昭栋,王自法,李兆焱,等. 基于机器学习−网格搜索优化的砂土液化预测[J]. 振动与冲击,2024,43(5):82-92.

    WANG Z D,WANG Z F,LI Z Y,et al. Prediction of sandy soil liquefaction based on machine learning GridSearch CV[J]. Journal of Vibration and Shock,2024,43(5):82-92. (in Chinese with English abstract
    [24]
    BERGSTRA J,BARDENET R,BENGIO Y,et al. Algorithms for hyper-parameter optimization[J]. Advances in Neural Information Processing Systems ,2011,2546-2554.
    [25]
    BONYADI M R,MICHALEWICZ Z. Particle swarm optimization for single objective continuous space problems:A review[J]. Evolutionary Computation,2017,25(1):1-54. doi: 10.1162/EVCO_r_00180
    [26]
    JUAN U,JUERGEN B. Bayesian optimisation for constrained problems[J]. ACM transactions on Modeling and Computer Simulation S. 2021:1-21.
    [27]
    LI L S,JAMIESON K G,DESALVO G,et al. Hyperband:A novel bandit-based approach to hyperparameter optimization[J]. Journal of Machine Learning Research,2016,18:1-52.
    [28]
    ZHANG Y Z,MA J,LIANG S L,et al. An evaluation of eight machine learning regression algorithms for forest aboveground biomass estimation from multiple satellite data products[J]. Remote Sensing,2020,12(24):4015. doi: 10.3390/rs12244015
    [29]
    叶亚三,陈国兴,王志华,等. 汶川大地震中广元市水库震害调查与分析[J]. 世界地震工程,2011,27(4):73-85.

    YE Y S,CHEN G X,WANG Z H,et al. Investigation and analysis of seismic damage of reservoirs in Guangyuan City during Wenchuan great earthquake[J]. World Earthquake Engineering,2011,27(4):73-85. (in Chinese with English abstract
    [30]
    陈国兴,景立平,汤皓,等. 汶川地震中绵竹市水库土坝震损调查与分析[J]. 南京工业大学学报(自然科学版),2009,31(9):15-23.

    CHEN G X,JING L P,TANG H,et al. Investigation and analysis of earthquake-induced earth dam damages in Mianzhu City during Wenchuan earthquake[J]. Journal of Nanjing University of Technology(Natural Science Edition),2009,31(9):15-23. (in Chinese with English abstract
    [31]
    CHEN G X,JIN D D,MAO J,et al. Seismic damage and behavior analysis of earth dams during the 2008 Wenchuan earthquake,China[J]. Engineering Geology,2014,180:99-129. doi: 10.1016/j.enggeo.2014.06.001
    [32]
    LASHGARI A,MOSS R E S. Displacement and damage analysis of earth dams during the 2023 Turkiye earthquake sequence[J]. Earthquake Spectra,2024,40(2):939-976. doi: 10.1177/87552930231223749
    [33]
    叶亚三,陈国兴,王志华. 汶川大地震中土坝破坏程度与坝体几何形状的关系分析[J]. 地震工程与工程振动,2012,31(9):146-153.

    YE Y S,CHEN G X,WANG Z H. Relationships between damage extent and geometry of reservoir’s earth dams in Wenchuan earthquake[J]. Earthquake Engineering and Engineering Dynamics,2012,31(9):146-153. (in Chinese with English abstract
    [34]
    SOYSAL B F,ARICI Y. Crack width–seismic intensity relationships for concrete gravity dams[J]. Journal of Earthquake Engineering,2024,28(2):565-581. doi: 10.1080/13632469.2023.2220048
    [35]
    TANI S,NAKASHIMA M. Earthquake damage to earth dams in Japan-Maximum epicentral distance to cause damage as a function of magnitude[J]. Soil Dynamics and Earthquake Engineering,1999,18(8):593-602. doi: 10.1016/S0267-7261(99)00017-2
    [36]
    中华人民共和国国家质量监督检验检疫总局. 生命线工程地震破坏等级划分:GB/T 24336-2009[S].

    General Administration of Quality Supervision,Inspection and Quarantine of the People's Republic of China (AQSIQ). Classification of earthquake damage to lifeline engineering:GB/T 24336-2009[S].
    [37]
    陈国兴,景立平,李永强. 汶川地震中小型水库震害与数据库[M]. 北京:科学出版社,2014.

    CHEN G X,JING L P,LI Y Q. Seismic damage of small and medium-sized reservoirs in the Wenchuan earthquake and databas[M]. Beijing:Science Publishing House,2014. (in Chinese).
    [38]
    冒进,陈国兴,王志华,等. 绵阳市东南部区域水库汶川地震典型震害分析[J]. 防灾减灾工程学报,2015,35(1):137-144.

    MAO J,CHEN G X,WANG Z H,et al. Analysis of representative seismic damage to reservoir in the southeast of Mianyang City during Wenchuan Earthquake[J]. Journal of Disaster Preventtion and Mitigation Engineering.,2015,35(1):137-144. (in Chinese with English abstract
    [39]
    单锐,杨婧,朱文元,等. 不同缺失比例下的缺失值插补方法比较[J]. 信息技术,2023(12):52-55.

    SHAN R,YANG J,ZHU W Y,et al. Comparison of interpolation methods for missing values with different missing ratios[J]. Information Technology,2023(12):52-55. (in Chinese with English abstract
    [40]
    仉文岗,唐理斌,陈福勇,等. 基于4种超参数优化算法及随机森林模型预测TBM掘进速度[J]. 应用基础与工程科学学报,2021,29(5):1186-1198.

    ZHANG W G,TANG L B,CHEN F Y,et al. Prediction for TBM penetration rate using four hyperparameter optimization methods and random forest model[J]. Journal of Basic Science and Engineering,2021,29(5):1186-1198. (in Chinese with English abstract
    [41]
    黄鹏辉,高勇. 分层抽样在电梯检验报告抽查中的应用[J]. 试验研究,2017,33(8):13-15.

    HUANG P H,GAO Y. Application of stratified sampling in sampling of elevator inspection reports[J]. Pilot Study,2017,33(8):13-15. (in Chinese with English abstract
    [42]
    YATES L,ANDAHL Z,RICHARDS S. et al. Cross validation for model selection:A review with examples from ecology[J]. Ecological Monographs,2023,93(1):1-24.
    [43]
    LIU P F,CHEN J Y,XU Q,et al. Seismic stability analysis of CSG dams considering the effect of tension crack based on genetic algorithm with an improved initial population strategy[J]. Soil Dynamics and Earthquake Engineering,2023,175:108210. doi: 10.1016/j.soildyn.2023.108210
    [44]
    郝伟,宋宁宁. 高烈度区铁路桥梁地震灾害生命年损失评估方法[J]. 自然灾害学报,2022,31(6):86-93.

    HAO W,SONG N N. Evaluation method of earthquake disaster life years loss of railway bridges in high intensity areas[J]. Journal of Nature Disaster,2022,31(6):86-93. (in Chinese with English abstract
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article Views(133) PDF Downloads(7) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return