The assessment of emerging data-intelligence technologies for modeling Mg+2 and SO4−2 surface water quality. (15th December 2021)

• Record Type: Journal Article
• Authors: Jamei, Mehdi; Ahmadianfar, Iman; Karbasi, Masoud; Jawad, Ali H.; Farooque, Aitazaz A.; Yaseen, Zaher Mundher
• Is Part Of: Journal of environmental management. Volume 300(2021)
• Publication Date: 2021-12-15
• Subjects: Water quality -- Wavelet transform -- Least square support vector machine -- Simulated annealing -- Extended Kalman filter; Environmental policy -- Periodicals; Environmental management -- Periodicals; Environment -- Periodicals; Ecology -- Periodicals; 363.705
• DOI: 10.1016/j.jenvman.2021.113774
• Languages: English
• ISSNs: 0301-4797

Abstract

Abstract: The concentration of soluble salts in surface water and rivers such as sodium, sulfate, chloride, magnesium ions, etc., plays an important role in the water salinity. Therefore, accurate determination of the distribution pattern of these ions can improve better management of drinking water resources and human health. The main goal of this research is to establish two novel wavelet-complementary intelligence paradigms so-called wavelet least square support vector machine coupled with improved simulated annealing (W-LSSVM-ISA) and the wavelet extended Kalman filter integrated with artificial neural network (W-EKF- ANN) for accurate forecasting of the monthly), magnesium (Mg +2 ), and sulfate (SO4 −2 ) indices at Maroon River, in Southwest of Iran. The monthly River flow (Q), electrical conductivity (EC), Mg +2, and SO4 −2 data recorded at Tange-Takab station for the period 1980–2016. Some preprocessing procedures consisting of specifying the number of lag times and decomposition of the existing original signals into multi-resolution sub-series using three mother wavelets were performed to develop predictive models. In addition, the best subset regression analysis was designed to separately assess the best selective combinations for Mg +2 and SO4 −2 . The statistical metrics and authoritative validation approaches showed that both complementary paradigms yielded promising accuracy compared with standalone artificial intelligence (AI) models. Furthermore, the results demonstrated that W-LSSVM-ISA-C1 (correlation coefficient (R) = 0.9521, root mean square error (RMSE) = 0.2637 mg/l, and Kling-Gupta efficiency (KGE) = 0.9361) and W-LSSVM-ISA-C4 (R = 0.9673, RMSE = 0.5534 mg/l and KGE = 0.9437), using Dmey mother that outperformed the W-EKF-ANN for predicting Mg +2 and SO4 −2, respectively. Graphical abstract: Image 1 Highlights: Complementary machine learning models were developed for surface water prediction. Mg +2, and SiO4 −2 were simulated based on EC, river discharge, Mg +2, and SiO4 −2 . Wavelet pre-processing approach is used to identify the essential predictors. The improved simulated annealing method is integrated to improve the accuracy. The proposed complementary machine learning models were provided optimistic results.