Multi-step ahead short-term predictions of storm surge level using CNN and LSTM network

Bao Wang Shichao Liu Bin Wang Wenzhou Wu Jiechen Wang Dingtao Shen

Bao Wang, Shichao Liu, Bin Wang, Wenzhou Wu, Jiechen Wang, Dingtao Shen. Multi-step ahead short-term predictions of storm surge level using CNN and LSTM network[J]. Acta Oceanologica Sinica. doi: 10.1007/s13131-021-1763-9
Citation: Bao Wang, Shichao Liu, Bin Wang, Wenzhou Wu, Jiechen Wang, Dingtao Shen. Multi-step ahead short-term predictions of storm surge level using CNN and LSTM network[J]. Acta Oceanologica Sinica. doi: 10.1007/s13131-021-1763-9

doi: 10.1007/s13131-021-1763-9

Multi-step ahead short-term predictions of storm surge level using CNN and LSTM network

Funds: The National Key Research and Development Program of China (2016YFC1402609), Open Fund of the Key Laboratory of Marine Hazards Forecasting, Ministry of Natural Resources (LOMF 1804) and National Natural Science Foundation of China (42077438).
More Information
    • 关键词:
    •  / 
    •  / 
    •  / 
    •  / 
    •  
  • Figure  1.  Structural illustration of conv1D.

    Figure  2.  Structural illustration of LSTM.

    Figure  3.  Frameworks of LSTM–CNN and CNN–LSTM.

    Figure  4.  Location of Xiuying station and tracks of typhoon Khanum and Mangkhut (TD is tropical depression, TS is tropical storm, STS is severe tropical storm, TY is typhoon, STY is severe typhoon, and Super TY is super typhoon).

    Figure  5.  Time-sharing MASL curves and cumulative percentages of typhoon track nodes.

    Figure  6.  Data organization for multi-step predictions and architectures of selected models

    Figure  7.  Scatter plots of observed SLs and 1 h ahead predicted SLs of SVR, MLP, LSTM, and CNN–LSTM.

    Figure  8.  Error distributions with ascending data blocks at 1-, 2-, 4-, and 6-h ahead steps.

    Figure  9.  1-h ahead predicted hourly SLs of SVR, MLP, CNN, LSTM and CNN–LSTM.

    Figure  10.  2-h ahead predicted hourly SLs of SVR, MLP, CNN, LSTM, and CNN–LSTM.

    Figure  11.  Radar charts of different modes for multi-step ahead SL predictions for the period of typhoons Khanum and Mangkhut and the year from 2017 to 2018.

    Table  1.   Delineation of 6 ROIs around Xiuying station and corresponding information about typhoons crossing each region from 2008 to 2018

    IDROICount of crossing
    typhoon
    Total track
    nodes
    Maximum crossing
    time/h
    Mean absolute
    surge level/cm
    1(18°N, 22°N, 108°E, 112°E)48113511331.9953
    2(16°N, 24°N, 106°E, 114°E)76347118826.2972
    3(14°N, 26°N, 104°E, 116°E)88539219725.1812
    4(12°N, 26°N, 102°E, 118°E)112780120524.0656
    5(10°N, 26°N, 102°E, 120°E)1331002225923.0555
    6(8°N, 26°N, 102°E, 122°E)1371201529622.2679
    下载: 导出CSV

    Table  2.   Details of sample data and its comparison with original data

    IndexSample DataOriginal Data
    Training and ValidationTesting2008–20162017–2018
    SL
    /cm
    U10
    /(m·s–1)
    V10
    /(m·s–1)
    SL
    /cm
    U10
    /(m·s–1)
    V10
    /(m·s–1)
    SL
    /cm
    U10
    /(m·s–1)
    V10
    /(m·s–1)
    SL
    /cm
    U10
    /(m·s–1)
    V10
    /(m·s–1)
    Samples1148931917558817166
    Max21516.018.47611.37.921516.018.47611.37.9
    Min–67–17.3–17.8–27–12.9–10.8–67–17.3–17.8–39–12.9–10.8
    MAV21.023.732.7823.253.662.4617.843.252.5319.683.402.41
    Kurtosis11.980.431.161.120.18–0.415.881.07–0.050.481.77–0.59
    Note: U10: 10–meter U wind component; V10: 10–meter V wind component; MAV: Mean absolute value
    下载: 导出CSV

    Table  3.   Hyper-parameter details of the six models

    ModelHyper-parameterValueReason
    shape input layer nodes(None, 72)shape of feature inputs
    SVRkernel functionRBFa competitive kernel function
    parameters adjustment method‘GridSearchCV’an exhaustive search method in ‘sklearn’
    MLP
    CNN
    LSTM
    shape of input layer(None, 72) for MLP, (None, 24, 3) for CNN, (None, 3, 24) for LSTMshape of feature inputs
    number of 1st hidden layer nodes128common value [16, 32, 64, 128, 256]
    number of 2nd hidden layer nodes32common value [8, 16, 32, 64, 128]
    size of batch256common value [64, 128, 256]
    early stopping patience5a common value
    early stopping minimum delta1×10–4minimum gap of loss in ‘Keras’
    early stopping loop count7 for 1-h model, 5 for otherscommon value [1, 3, 5, 7]
    LSTM–CNNshape of input layer(None, 3,24)shape of feature inputs
    number of 1st LSTM layer nodes128same as LSTM
    number of 2nd LSTM layer nodes32same as LSTM
    number of 1st CNN layer nodes128same as CNN
    number of 2nd CNN layer nodes32same as CNN
    size of batch256same as CNN
    early stopping patience5same as CNN
    early stopping minimum delta1×10–4same as CNN
    early stopping loop count7 for 1-h model,
    5 for others
    common value [1, 3, 5, 7]
    CNN–LSTMshape of input layer(None, 24, 3)shape of feature inputs
    number of 1st CNN layer nodes128same as CNN
    number of 2nd CNN layer nodes32same as CNN
    number of 1st LSTM layer nodes128same as LSTM
    number of 2nd LSTM layer nodes32same as LSTM
    size of batch256same as LSTM
    early stopping patience5same as LSTM
    early stopping minimum delta1×10–4same as LSTM
    early stopping loop count7 for 1-h model, 1 for 6-h model, 5 for otherscommon value [1, 3, 5, 7]
    下载: 导出CSV

    Table  4.   Experimental results of six algorithms on testing data at multi-hour steps

    StepsIndexSVRMLPCNNLSTMLSTM–CNNCNN–LSTM
    1 hCC0.85050.95430.96550.96290.96580.9661
    MAE/cm5.89583.20832.69562.79572.66822.6303
    RMSE/cm7.54424.21243.53113.62203.47843.4631
    2 hCC0.77160.88300.90020.90290.90460.9086
    MAE/cm6.86924.82114.50214.45564.38324.2676
    RMSE/cm8.86856.29195.83245.76765.72235.6125
    4 hCC0.67150.73340.78070.78920.79420.7991
    MAE/cm7.64496.83106.40716.36836.19196.0918
    RMSE/cm10.04739.02198.33518.19628.06347.9821
    6 hCC0.46080.65880.70560.71830.72040.7361
    MAE/cm9.50737.68777.11846.93536.92116.7380
    RMSE/cm12.06089.81329.13278.94538.91478.7095
    下载: 导出CSV
  • [1] Araya I A, Valle C, Allende H. 2020. A Multi-Scale Model based on the Long Short-Term Memory for day ahead hourly wind speed forecasting. Pattern Recognition Letters, 136: 333–340. doi: 10.1016/j.patrec.2019.10.011
    [2] Balas C E, Koç M L, Tür R. 2010. Artificial neural networks based on principal component analysis, fuzzy systems and fuzzy neural networks for preliminary design of rubble mound breakwaters. Applied Ocean Research, 32(4): 425–433. doi: 10.1016/j.apor.2010.09.005
    [3] Chang H K, Lin L C. 2006. Multi-point tidal prediction using artificial neural network with tide-generating forces. Coastal Engineering, 53(10): 857–864. doi: 10.1016/j.coastaleng.2006.05.001
    [4] Chen Yong, Zhang Shuai, Zhang Wenyu, et al. 2019. Multifactor spatio-temporal correlation model based on a combination of convolutional neural network and long short-term memory neural network for wind speed forecasting. Energy Conversion and Management, 185(4): 783–799
    [5] Cox D T, Tissot P, Michaud P. 2002. Water level observations and short-term predictions including meteorological events for entrance of Galveston bay, Texas. Journal of Waterway, Port, Coastal, and Ocean Engineering, 128(1): 21–29. doi: 10.1061/(ASCE)0733-950X(2002)128:1(21)
    [6] Dong Na, Chang Jianfang, Wu Aiguo, et al. 2020. A novel convolutional neural network framework based solar irradiance prediction method. International Journal of Electrical Power & Energy Systems, 114(3): 105411
    [7] El-Diasty M, Al-Harbi S, Pagiatakis S. 2018. Hybrid harmonic analysis and wavelet network model for sea water level prediction. Applied Ocean Research, 70(2): 14–21
    [8] Hochreiter S, Schmidhuber J. 1997. Long Short-term Memory. Neural Computation, 9(8): 1735–1780. doi: 10.1162/neco.1997.9.8.1735
    [9] Imani M, Kao H C, Lan W H, et al. 2018. Daily sea level prediction at Chiayi coast, Taiwan using extreme learning machine and relevance vector machine. Global and Planetary Change, 161: 211–221. doi: 10.1016/j.gloplacha.2017.12.018
    [10] Ishida K, Tsujimoto G, Ercan A, et al. 2020. Hourly-scale coastal sea level modeling in a changing climate using long short-term memory neural network. Science of the Total Environment, 720: 137613. doi: 10.1016/j.scitotenv.2020.137613
    [11] Kao I F, Zhou Yanlai, Chang L C, et al. 2020. Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting. Journal of Hydrology, 583: 124631. doi: 10.1016/j.jhydrol.2020.124631
    [12] Karimi S, Kisi O, Shiri J, et al. 2013. Neuro-fuzzy and neural network techniques for forecasting sea level in Darwin Harbor, Australia. Computers & Geosciences, 52: 50–59
    [13] Kim S, Matsumi Y, Pan Shunqi, et al. 2016. A real-time forecast model using artificial neural network for after-runner storm surges on the Tottori coast, Japan. Ocean Engineering, 122: 44–53. doi: 10.1016/j.oceaneng.2016.06.017
    [14] Kim S W, Melby J A, Nadal-Caraballo N C, et al. 2015. A time-dependent surrogate model for storm surge prediction based on an artificial neural network using high-fidelity synthetic hurricane modeling. Natural Hazards, 76: 565–585. doi: 10.1007/s11069-014-1508-6
    [15] Kim S, Pan Shunqi, Mase H. 2019. Artificial neural network-based storm surge forecast model: Practical application to Sakai Minato, Japan. Applied Ocean Research, 91: 101871. doi: 10.1016/j.apor.2019.101871
    [16] Lee T L. 2006. Neural network prediction of a storm surge. Ocean Engineering, 33(3–4): 483–494. doi: 10.1016/j.oceaneng.2005.04.012
    [17] Lee T L. 2008. Back-propagation neural network for the prediction of the short-term storm surge in Taichung harbor, Taiwan. Engineering Applications of Artificial Intelligence, 21(1): 63–72. doi: 10.1016/j.engappai.2007.03.002
    [18] Lee T L. 2009. Predictions of typhoon storm surge in Taiwan using artificial neural networks. Advances in Engineering Software, 40(11): 1200–1206. doi: 10.1016/j.advengsoft.2007.06.005
    [19] Li Youru, Zhu Zhenfeng, Kong Deqiang, et al. 2019. EA-LSTM: Evolutionary attention-based LSTM for time series prediction. Knowledge-Based Systems, 181: 104785. doi: 10.1016/j.knosys.2019.05.028
    [20] Liang S X, Li M C, Sun Z C. 2008. Prediction models for tidal level including strong meteorologic effects using a neural network. Ocean Engineering, 35(7): 666–675. doi: 10.1016/j.oceaneng.2007.12.006
    [21] Liu Hui, Mi Xiwei, Li Yanfei. 2018. Smart deep learning based wind speed prediction model using wavelet packet decomposition, convolutional neural network and convolutional long short term memory network. Energy Conversion and Management, 166(3): 120–131
    [22] Mel R, Viero D P, Carniello L, et al. 2014. Simplified methods for real-time prediction of storm surge uncertainty: The city of Venice case study. Advances in Water Resources, 71: 177–185. doi: 10.1016/j.advwatres.2014.06.014
    [23] Mok K M, Lai U H, Hoi K I. 2016. Development of an adaptive Kalman filter-based storm tide forecasting model. Journal of Hydrodynamics, 28(6): 1029–1036. doi: 10.1016/S1001-6058(16)60707-2
    [24] Nitsure S P, Londhe S N, Khare K C. 2014. Prediction of sea water levels using wind information and soft computing techniques. Applied Ocean Research, 47: 344–351. doi: 10.1016/j.apor.2014.07.003
    [25] Oh S L, Ng E Y K, Tan R S, et al. 2018. Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats. Computers in Biology and Medicine, 102: 278–287. doi: 10.1016/j.compbiomed.2018.06.002
    [26] Pak U, Ma Jun, Ryu U, et al. 2020. Deep learning-based PM2.5 prediction considering the spatiotemporal correlations: A case study of Beijing, China. Science of the Total Environment, 699: 133561. doi: 10.1016/j.scitotenv.2019.07.367
    [27] Petersen N C, Rodrigues F, Pereira F C. 2019. Multi-output bus travel time prediction with convolutional LSTM neural network. Expert Systems with Applications, 120: 426–435. doi: 10.1016/j.eswa.2018.11.028
    [28] Qing Xiangyun, Niu Yugang. 2018. Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy, 148: 461–468. doi: 10.1016/j.energy.2018.01.177
    [29] Rajasekaran S, Gayathri S, Lee T L. 2008. Support vector regression methodology for storm surge predictions. Ocean Engineering, 35(16): 1578–1587. doi: 10.1016/j.oceaneng.2008.08.004
    [30] Sadaei H J, de Lima e Silva P C, Guimarães F G, et al. 2019. Short-term load forecasting by using a combined method of convolutional neural networks and fuzzy time series. Energy, 175: 365–377. doi: 10.1016/j.energy.2019.03.081
    [31] Sagheer A, Kotb M. 2019. Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing, 323: 203–213. doi: 10.1016/j.neucom.2018.09.082
    [32] Shi Xingjian, Chen Zhourong, Wang Hao, et al. 2015. Convolutional LSTM Network: a machine learning approach for precipitation nowcasting. In: Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge, MA, United States: MIT Press, 802-810
    [33] Song Xuanyi, Liu Yuetian, Xue Liang, et al. 2020. Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model. Journal of Petroleum Science and Engineering, 186: 106682. doi: 10.1016/j.petrol.2019.106682
    [34] Sztobryn M. 2003. Forecast of storm surge by means of artificial neural network. Journal of Sea Research, 49(4): 317–322. doi: 10.1016/S1385-1101(03)00024-8
    [35] Wang Kang, Li Kenli, Zhou Liqian, et al. 2019. Multiple convolutional neural networks for multivariate time series prediction. Neurocomputing, 360: 107–119. doi: 10.1016/j.neucom.2019.05.023
    [36] Wang Bao, Wang Bin, Wu Wenzhou, et al. 2020. Sea-water-level prediction via combined wavelet decomposition, neuro-fuzzy and neural networks using SLA and wind information. Acta Oceanologica Sinica, 39(5): 157–167. doi: 10.1007/s13131-020-1569-1
    [37] Xiao Changjiang, Chen Nengcheng, Hu Chuli, et al. 2019. Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach. Remote Sensing of Environment, 233: 111358. doi: 10.1016/j.rse.2019.111358
    [38] Yin Jianchuan, Wang Nini. 2016. An online sequential extreme learning machine for tidal prediction based on improved Gath-Geva fuzzy segmentation. Neurocomputing, 174: 85–98. doi: 10.1016/j.neucom.2015.02.094
    [39] You S H, Seo J W. 2009. Storm surge prediction using an artificial neural network model and cluster analysis. Natural Hazards, 51(1): 97–114. doi: 10.1007/s11069-009-9396-x
    [40] Zhang Zeguo, Yin Jianchuan, Wang Nini, et al. 2017. A precise tidal prediction mechanism based on the combination of harmonic analysis and adaptive network-based fuzzy inference system model. Acta Oceanologica Sinica, 36: 94–105
    [41] Zhao Xinyu, Jiang Na, Liu Jinfu, et al. 2020. Short-term average wind speed and turbulent standard deviation forecasts based on one-dimensional convolutional neural network and the integrate method for probabilistic framework. Energy Conversion and Management, 203: 112239. doi: 10.1016/j.enconman.2019.112239
  • 加载中
图(11) / 表(4)
计量
  • 文章访问数:  192
  • HTML全文浏览量:  86
  • PDF下载量:  19
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-10-07
  • 录用日期:  2020-11-13
  • 网络出版日期:  2021-06-29

目录

    /

    返回文章
    返回