Forecasting river daily discharge using decision tree and time series methods

被引:1
|
作者
Kabootarkhani, Mohammad Ranjbar [1 ]
Kermani, Soudabeh Golestani [1 ]
Aldallal, Ammar [2 ]
Zounemat-Kermani, Mohammad [1 ]
机构
[1] Shahid Bahonar Univ Kerman, Dept Water Engn, Kerman, Iran
[2] Ahlia Univ, Coll Engn, Telecommun Engn Dept, Manama, Bahrain
关键词
data mining; modelling; river engineering; water flow; MODELS; REGRESSION; ACCURACY; STREAM;
D O I
10.1680/jwama.22.00079
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
River floods disrupt communication and transportation networks, damage buildings and infrastructure, destroy agricultural products and livestock, cause capital losses and endanger human life. Accurate and proper flood prediction and forecasting are major challenges in hydrology and water resources management. The aim of this study was to forecast and estimate the daily flows of three rivers in Iran using four tree-based data-mining methods, two ensemble bagging methods and the stochastic time series model Arima (auto-regressive integrated moving average). A comparison of these different methodologies is the main contribution of this work. Five statistical measures were used to evaluate the accuracy of these models based on 4 years of daily discharge flow data. The hold-out method was used to divide the data into training (70%) and testing (30%) sets. It was found that the ensemble tree-based chi-square automatic interaction detector provided the most precise forecasts. The overall results indicate that the data-mining methods of ensemble models and tree-based models improved the average accuracy of the models by 25.0% and 15.5% compared with the stochastic Arima model, respectively, indicating the superiority of their potential in capturing the non-linear behaviour of flow discharges.
引用
收藏
页码:294 / 307
页数:14
相关论文
共 50 条
  • [41] Kernel methods applied to time series forecasting
    Rubio, Gines
    Pomares, Hetor
    Herrera, Luis J.
    Rojas, Ignacio
    COMPUTATIONAL AND AMBIENT INTELLIGENCE, 2007, 4507 : 782 - +
  • [42] Winning methods for forecasting tourism time series
    Baker, Lee C.
    Howard, Jeremy
    INTERNATIONAL JOURNAL OF FORECASTING, 2011, 27 (03) : 850 - 852
  • [43] On projection methods for functional time series forecasting
    Elias, Antonio
    Jimenez, Raul
    Shang, Han Lin
    JOURNAL OF MULTIVARIATE ANALYSIS, 2022, 189
  • [44] Time series forecasting methods in emergency contexts
    P. Villoria Hernandez
    I. Mariñas-Collado
    A. Garcia Sipols
    C. Simon de Blas
    M. C. Rodriguez Sánchez
    Scientific Reports, 13
  • [45] Time Series Neural Network Forecasting Methods
    WEN Xinhui
    CHEN Keizhou(The Centlal of Neural Netwolk
    JournalofSystemsScienceandSystemsEngineering, 1996, (01) : 24 - 32
  • [46] TIME SERIES NEURAL NETWORK FORECASTING METHODS
    文新辉
    陈开周
    JournalofElectronics(China), 1995, (01) : 1 - 8
  • [47] TIME SERIES ANALYSIS OF MEAN DAILY RIVER FLOWS
    COLOMBI, JS
    WATER AND WATER ENGINEERING, 1972, 76 (917): : 254 - &
  • [48] Study on the daily characteristic load forecasting based on the optimizied algorithm of decision tree
    Li, Ran
    Liu, Yu
    Li, Jing-Hua
    Gu, Xue-Ping
    Niu, Dong-Xiao
    Liu, Yong-Qi
    Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering, 2005, 25 (23): : 36 - 41
  • [49] A TIME-SERIES MODEL FOR DAILY TRAFFIC VOLUME FORECASTING
    KOPANEZOU, H
    TRIVELLAS, T
    PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON CIVIL AND STRUCTURAL ENGINEERING COMPUTING, VOLS 1 & 2, 1989, : 295 - 300
  • [50] Postprocessing of Ensemble Weather Forecast Using Decision Tree-Based Probabilistic Forecasting Methods
    Benacek, Patrik
    Farda, Ales
    Stepanek, Petr
    WEATHER AND FORECASTING, 2023, 38 (01) : 69 - 82