Improving the prediction accuracy of river inflow using two data pre-processing techniques coupled with data-driven model

被引:4
|
作者
Nazir, Hafiza Mamona [1 ]
Hussain, Ijaz [1 ]
Faisal, Muhammad [2 ,3 ]
Elashkar, Elsayed Elsherbini [4 ]
Shoukry, Alaa Mohamd [4 ,5 ]
机构
[1] Quaid I Azam Univ, Dept Stat, Islamabad, Pakistan
[2] Univ Bradford, Fac Hlth Studies, Bradford, W Yorkshire, England
[3] Bradford Teaching Hosp NHS Fdn Trust, Bradford Inst Hlth Res, Bradford, W Yorkshire, England
[4] King Saud Univ, Arriyadh Community Coll, Riyadh, Saudi Arabia
[5] KSA Workers Univ, Ksa, Egypt
来源
PEERJ | 2019年 / 7卷
关键词
Data-driven models; Variational Mode Decomposition; Ensemble Empirical Mode Decomposition; Empirical Mode Decomposition; ARTIFICIAL NEURAL-NETWORKS; SINGULAR SPECTRUM ANALYSIS; WAVELET TRANSFORM; DECOMPOSITION; ENSEMBLE; INTELLIGENCE; MACHINE;
D O I
10.7717/peerj.8043
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
River inflow prediction plays an important role in water resources management and power-generating systems. But the noises and multi-scale nature of river inflow data adds an extra layer of complexity towards accurate predictive model. To overcome this issue, we proposed a hybrid model, Variational Mode Decomposition (VMD), based on a singular spectrum analysis (SSA) denoising technique. First, SSA his applied to denoise the river inflow data. Second, VMD, a signal processing technique, is employed to decompose the denoised river inflow data into multiple intrinsic mode functions (IMFs), each with a relative frequency scale. Third, Empirical Bayes Threshold (EBT) is applied on non-linear IMF to smooth out. Fourth, predicted models of denoised and decomposed IMFs are established by learning the feature values of the Support Vector Machine (SVM). Finally, the ensemble predicted results are formulated by adding the predicted IMFs. The proposed model is demonstrated using daily river inflow data from four river stations of the Indus River Basin (IRB) system, which is the largest water system in Pakistan. To fully illustrate the superiority of our proposed approach, the SSA-VMD-EBT-SVM hybrid model was compared with SSA-VMD-SVM, VMD-SVM, Empirical Mode Decomposition (EMD) based i.e., EMD-SVM, SSA-EMD-SVM, Ensemble EMD (EEMD) based i.e., EEMD-SVM and SSA-EEMD-SVM. We found that our proposed hybrid SSA-EBT-VMD-SVM model outperformed than others based on following performance measures: the Nash-Sutcliffe Efficiency (NSE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). Therefore, SSA-VMD-EBT-SVM model can be used for water resources management and power-generating systems using non-linear time series data.
引用
收藏
页数:25
相关论文
共 50 条
  • [1] Improving the performance of data-driven techniques through data pre-processing for modelling daily reservoir inflow
    Jothiprakash, V.
    Kote, Alka S.
    [J]. HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES, 2011, 56 (01): : 168 - 186
  • [2] The generalizability of pre-processing techniques on the accuracy and fairness of data-driven building models: A case study
    Sun, Ying
    Fung, Benjamin C. M.
    Haghighat, Fariborz
    [J]. ENERGY AND BUILDINGS, 2022, 268
  • [3] Improving the prediction accuracy of monthly streamflow using a data-driven model based on a double-processing strategy
    Wang, Lili
    Li, Xin
    Ma, Chunfeng
    Bai, Yulong
    [J]. JOURNAL OF HYDROLOGY, 2019, 573 : 733 - 745
  • [4] Data-driven modelling of ship propulsion and the effect of data pre-processing on the prediction of ship fuel consumption and speed loss
    Karagiannidis, Pavlos
    Themelis, Nikos
    [J]. Ocean Engineering, 2021, 222
  • [5] Data-driven modelling of ship propulsion and the effect of data pre-processing on the prediction of ship fuel consumption and speed loss
    Karagiannidis, Pavlos
    Themelis, Nikos
    [J]. OCEAN ENGINEERING, 2021, 222
  • [6] Pre-processing of data-driven river flow forecasting models by singular value decomposition (SVD) technique
    Chitsaz, Nastaran
    Azarnivand, Ali
    Araghinejad, Shahab
    [J]. HYDROLOGICAL SCIENCES JOURNAL, 2016, 61 (12) : 2164 - 2178
  • [7] The Role of Data Pre-processing Techniques in Improving Machine Learning Accuracy for Predicting Coronary Heart Disease
    Sami, Osamah
    Elsheikh, Yousef
    Almasalha, Fadi
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2021, 12 (06) : 812 - 820
  • [8] Pre-processing DNS data to improve statistical convergence and accuracy of mean velocity fields in invariant data-driven turbulence models
    Eduardo F. Fonseca
    Victor B. Rangel
    Bernardo P. Brener
    Matheus A. Cruz
    Roney L. Thompson
    [J]. Theoretical and Computational Fluid Dynamics, 2022, 36 : 435 - 463
  • [9] Pre-processing DNS data to improve statistical convergence and accuracy of mean velocity fields in invariant data-driven turbulence models
    Fonseca, Eduardo F.
    Rangel, Victor B.
    Brener, Bernardo P.
    Cruz, Matheus A.
    Thompson, Roney L.
    [J]. THEORETICAL AND COMPUTATIONAL FLUID DYNAMICS, 2022, 36 (03) : 435 - 463
  • [10] An Improved MSR-Based Data-Driven Detection Method Using Smoothing Pre-Processing
    Yan, Yujia
    Wu, Guangxin
    Dong, Yang
    Bai, Yechao
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2021, 28 : 444 - 448