Abstract
The current study investigates an improved version of Least Square Support Vector Machines integrated with a Bat Algorithm (LSSVM-BA) for modeling the dissolved oxygen (DO) concentration in rivers. The LSSVM-BA model results are compared with those obtained using M5 Tree and Multivariate Adaptive Regression Spline (MARS) models to show the efficacy of this novel integrated model. The river water quality data at three monitoring stations located in the USA are considered for the simulation of DO concentration. Eight input combinations of four water quality parameters, namely, water temperature, discharge, pH, and specific conductance, are used to simulate the DO concentration. The results revealed the superiority of the LSSVM-BA model over the M5 Tree and MARS models in the prediction of river DO. The accuracy of the LSSVM-BA model compared with those of the M5 Tree and MARS models is found to increase by 20% and 42%, respectively, in terms of the root-mean-square error. All the predictive models are found to perform best when all the four water quality variables are used as input, which indicates that it is possible to supply more information to the predictive model by way of incorporation of all the water quality variables.
Highlights
Assessment of river water quality is a challenging issue in field environmental modeling
This is due to several causes: (1) knowledge of many of the biotic/abiotic processes responsible for dissolved oxygen (DO) concentration in water bodies is still not clear and the data/information required for modeling many of the interactions are difficult to acquire; (2) many of the biotic/abiotic processes are highly nonlinear and cannot be described perfectly with mathematical equations and (3) hydro-biological data are often prone to errors which cause high uncertainties in prediction [9,10]
The support vector machines (SVMs) acts based on a set of quadratic programming problems [68] while the least square SVM (LSSVM) acts based on linear programming and linear equations to improve the performance of the SVM
Summary
Assessment of river water quality is a challenging issue in field environmental modeling. Bayram et al [29] compared the regression and teaching–learning-based optimization approaches to estimate DO concentration in Turkey by employing temperature of air and water as predictors and indicated improvement in model performance through optimization. Liu et al [34] optimized the parameters of SVM using PSO to develop an SVM-PSO model for the prediction of DO concentration They compared the results of SVM-PSO with those of ANN and GP and reported better performance of SVM-PSO. All the studies reported that the efficiency of LSSVM models significantly depends on the values of the kernel (σ) and regularization (γ) parameters These hyper-parameters can be considered as decision variables and should be determined accurately by optimization algorithms for better performance of LSSVM models. Comparison of performance of LSSVM-BA with MARS and M5 will help to assess the improvement of the performance of LSSVM after integration with BA
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
