Improved prediction of monthly streamflow in a mountainous region by Metaheuristic-Enhanced deep learning and machine learning models using hydroclimatic data

被引:15
作者
Adnan, Rana Muhammad [1 ]
Mirboluki, Amin [2 ]
Mehraein, Mojtaba [2 ]
Malik, Anurag [3 ]
Heddam, Salim [4 ]
Kisi, Ozgur [5 ,6 ]
机构
[1] Guangzhou Univ, Sch Econ & Stat, Guangzhou 510006, Peoples R China
[2] Kharazmi Univ, Fac Engn, Tehran, Iran
[3] Punjab Agr Univ, Reg Res Stn, Bathinda 151001, Punjab, India
[4] Univ 20 Aout 1955, Fac Sci, Agron Dept, BP 26, Skikda, Algeria
[5] Univ Appl Sci, Dept Civil Engn, D-23562 Lubeck, Germany
[6] Ilia State Univ, Civil Engn Dept, Tbilisi, Georgia
基金
英国科研创新办公室;
关键词
ARTIFICIAL NEURAL-NETWORK; SUPPORT VECTOR REGRESSION; FUZZY INFERENCE SYSTEM; TIME-SERIES; WAVELET TRANSFORMS; INPUT SELECTION; ANFIS; FLOW; PRECIPITATION; ALGORITHMS;
D O I
10.1007/s00704-023-04624-9
中图分类号
P4 [大气科学(气象学)];
学科分类号
0706 ; 070601 ;
摘要
This study compares the ability of Long Short-Term Memory (LSTM) tuned with Grey Wolf Optimization (GWO) and machine learning models, artificial neural network (ANN), Adaptive-Network-based Fuzzy Inference System (ANFIS), and support vector machine (SVM) enhanced with GWO in the prediction of monthly streamflow. Precipitation, temperature, and streamflow data obtained from stations in Pakistan are used as inputs to the implemented models. The first application focused on streamflow prediction using local data and applying four different input scenarios; i) precipitation-based inputs, ii) temperature-based inputs, iii) lagged streamflow inputs, and iv) combinations of previous input scenarios. In the second application, streamflow data of one station are predicted using data from another station and similar input scenarios are considered. In the first application, the LSTM-GWO performed the best in one station, whereas the ANN-GWO produced the best predictions in another station. The mean absolute percentage error in LSTM-GWO and ANN-GWO are 17.9% and 22.63, respectively. Furthermore, it is observed that the LSTM-GWO generally offers the best accuracy in peak streamflow prediction with a maximum relative error of 113%. In the second application, the LSTM-GWO is the superior model which improves the mean absolute percentage error by 13%, 60%, and 101% compared to SVR-GWO, ANN-GWO, and ANFIS-GWO, respectively.
引用
收藏
页码:205 / 228
页数:24
相关论文
共 108 条
  • [1] Input selection and optimisation for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks
    Abbot, John
    Marohasy, Jennifer
    [J]. ATMOSPHERIC RESEARCH, 2014, 138 : 166 - 178
  • [2] Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada
    Adamowski, Jan
    Chan, Hiu Fung
    Prasher, Shiv O.
    Ozga-Zielinski, Bogdan
    Sliusarieva, Anna
    [J]. WATER RESOURCES RESEARCH, 2012, 48
  • [3] Precipitation Trends over Time Using Mann-Kendall and Spearman's rho Tests in Swat River Basin, Pakistan
    Ahmad, Ijaz
    Tang, Deshan
    Wang, TianFang
    Wang, Mei
    Wagan, Bakhtawar
    [J]. ADVANCES IN METEOROLOGY, 2015, 2015
  • [4] Feasibility of ANFIS-PSO and ANFIS-GA Models in Predicting Thermophysical Properties of Al2O3-MWCNT/Oil Hybrid Nanofluid
    Alarifi, Ibrahim M.
    Nguyen, Hoang M.
    Bakhtiyari, Ali Naderi
    Asadi, Amin
    [J]. MATERIALS, 2019, 12 (21)
  • [5] An ensemble-ANFIS based uncertainty assessment model for forecasting multi-scalar standardized precipitation index
    Ali, Mumtaz
    Deo, Ravinesh C.
    Downs, Nathan J.
    Maraseni, Tek
    [J]. ATMOSPHERIC RESEARCH, 2018, 207 : 155 - 180
  • [6] A comparative study of several machine learning based non-linear regression methods in estimating solar radiation: Case studies of the USA and Turkey regions
    Alizamir, Meysam
    Kim, Sungwon
    Kisi, Ozgur
    Zounemat-Kermani, Mohammad
    [J]. ENERGY, 2020, 197
  • [7] An improved support vector regression model for estimation of saturation pressure of crude oils
    Ansari, Hamid Reza
    Gholami, Amin
    [J]. FLUID PHASE EQUILIBRIA, 2015, 402 : 124 - 132
  • [8] A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runoff
    Aqil, Muhammad
    Kita, Ichiro
    Yano, Akira
    Nishiyama, Soichi
    [J]. JOURNAL OF HYDROLOGY, 2007, 337 (1-2) : 22 - 34
  • [9] Application of artificial neural network ensembles in probabilistic hydrological forecasting
    Araghinejad, Shahab
    Azmi, Mohammad
    Kholghi, Majid
    [J]. JOURNAL OF HYDROLOGY, 2011, 407 (1-4) : 94 - 104
  • [10] Applicability of ε-Support Vector Machine and Artificial Neural Network for Flood Forecasting in Humid, Semi-Humid and Semi-Arid Basins in China
    Bafitlhile, Thabo Michael
    Li, Zhijia
    [J]. WATER, 2019, 11 (01)