A physically based and machine learning hybrid approach for accurate rainfall-runoff modeling during extreme typhoon events

被引:107
|
作者
Young, Chih-Chieh [1 ]
Liu, Wen-Cheng [2 ,3 ]
Wu, Ming-Chang [3 ]
机构
[1] Natl Taiwan Univ, Hydrotech Res Inst, Taipei 10617, Taiwan
[2] Natl United Univ, Dept Civil & Disaster Prevent Engn, Miaoli 36063, Taiwan
[3] Taiwan Typhoon & Flood Res Inst, Natl Appl Res Labs, Taipei 10093, Taiwan
关键词
Rainfall-runoff; Typhoon events; Hydrologic modeling system (HEC-HMS); Support vector regression (SVR); Artificial neural network (ANN); Hybrid approach; SUPPORT VECTOR REGRESSION; ARTIFICIAL NEURAL-NETWORKS; HYDROLOGICAL DATA ASSIMILATION; ENSEMBLE KALMAN FILTER; STREAMFLOW; FORECASTS; IDENTIFICATION; COMBINATION; SIMULATION; PREDICTION;
D O I
10.1016/j.asoc.2016.12.052
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Accurate rainfall-runoff modeling during typhoon events is an essential task for natural disaster reduction. In this study, a novel hybrid model which integrates the outputs of physically based hydrologic modeling system into support vector machine is developed to predict hourly runoff discharges in Chishan Creek basin in southern Taiwan. Seven storms (with a total of 1200 data sets) are used for model calibration (training) and validation. Six statistical indices (mean absolute error, root mean square error, correlation coefficient, error of time to peak discharge, error of peak discharge, and coefficient of efficiency) are employed to assess prediction performance. Overall, superiority of the present approach especially for a longer (6-h) lead time prediction is revealed through a systematic comparison among three individual methods (i.e., the physically based hydrologic model, artificial neural network, and support vector machine) as well as their two hybrid combinations. Besides, our analysis and in-depth discussions further clarify the roles of physically based and data-driven components in the proposed framework. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:205 / 216
页数:12
相关论文
共 50 条
  • [31] Hydrologically Informed Machine Learning for Rainfall-Runoff Modeling: A Genetic Programming-Based Toolkit for Automatic Model Induction
    Chadalawada, Jayashree
    Herath, H. M. V. V.
    Babovic, Vladan
    WATER RESOURCES RESEARCH, 2020, 56 (04)
  • [32] Rainfall-runoff modeling using conceptual, data driven, and wavelet based computing approach
    Nayak, P. C.
    Venkatesh, B.
    Krishna, B.
    Jain, Sharad K.
    JOURNAL OF HYDROLOGY, 2013, 493 : 57 - 67
  • [33] Conjunction of SOM-based feature extraction method and hybrid wavelet-ANN approach for rainfall-runoff modeling
    Nourani, Vahid
    Parhizkar, Masoumeh
    JOURNAL OF HYDROINFORMATICS, 2013, 15 (03) : 829 - 848
  • [34] Rainfall-runoff modeling using machine learning in the ungauged urban watershed of Quetta Valley, Balochistan (Pakistan)
    Shah, Ghunwa
    Zaidi, Arjumand
    Qureshi, Abdul Latif
    Hussain, Shahzad
    Aziz, Tarique
    EARTH SCIENCE INFORMATICS, 2024, 17 (03) : 2661 - 2677
  • [35] Modeling of Monthly Rainfall-Runoff Using Various Machine Learning Techniques in Wadi Ouahrane Basin, Algeria
    Anaraki, Mahdi Valikhan
    Achite, Mohammed
    Farzin, Saeed
    Elshaboury, Nehal
    Al-Ansari, Nadhir
    Elkhrachy, Ismail
    WATER, 2023, 15 (20)
  • [36] Comparisons of Different Machine Learning-Based Rainfall-Runoff Simulations under Changing Environments
    Li, Chenliang
    Jiao, Ying
    Kan, Guangyuan
    Fu, Xiaodi
    Chai, Fuxin
    Yu, Haijun
    Liang, Ke
    WATER, 2024, 16 (02)
  • [37] Ensemble rainfall-runoff modeling of physically based semi-distributed models using multi-source rainfall data fusion
    Gichamo, Tagesse
    Nourani, Vahid
    Gokcekus, Huseyin
    Gelete, Gebre
    JOURNAL OF WATER AND CLIMATE CHANGE, 2024, 15 (02) : 325 - 347
  • [38] Assessing climate change impact on river flow extreme events in different climates of Iran using hybrid application of LARS-WG6 and rainfall-runoff modeling of deep learning
    Shahani, Mohammad Hossein
    Rezaverdinejad, Vahid
    Hosseini, Seyed Abbas
    Azad, Nasrin
    ECOHYDROLOGY & HYDROBIOLOGY, 2023, 23 (02) : 224 - 239
  • [39] Cascade-based multi-scale AI approach for modeling rainfall-runoff process
    Nourani, Vahid
    Andalib, Gholamreza
    Sadikoglu, Fahreddin
    Sharghi, Elnaz
    HYDROLOGY RESEARCH, 2018, 49 (04): : 1191 - 1207
  • [40] Daily Rainfall-Runoff Modeling at Watershed Scale: A Comparison Between Physically-Based and Data-Driven Models
    Vilaseca, Federico
    Castro, Alberto
    Chreties, Christian
    Gorgoglione, Angela
    COMPUTATIONAL SCIENCE AND ITS APPLICATIONS, ICCSA 2021, PT VII, 2021, 12955 : 18 - 33