Prediction of longitudinal dispersion coefficient using multivariate adaptive regression splines

Journal of Earth system science

Amir Hamzeh Haghiabi1¹ 

[1] Water Engineering Department, Lorestan University, Khorramabad 0098-663-4200289, Iran.$$

关键词: River water quality;    artificial neural network;    longitudinal dispersion coefficient;    pollution transmission;   

DOI  :  

学科分类：天文学(综合)

来源: Indian Academy of Sciences

【 摘 要 】

In this paper, multivariate adaptive regression splines (MARS) was developed as a novel soft-computingtechnique for predicting longitudinal dispersion coefficient (DL) in rivers. As mentioned in the literature,experimental dataset related to DL was collected and used for preparing MARS model. Results of MARSmodel were compared with multi-layer neural network model and empirical formulas. To define the mosteffective parameters on DL, the Gamma test was used. Performance of MARS model was assessed bycalculation of standard error indices. Error indices showed that MARS model has suitable performanceand is more accurate compared to multi-layer neural network model and empirical formulas. Results ofthe Gamma test and MARS model showed that flow depth (H) and ratio of the mean velocity to shearvelocity (u/u^∗) were the most effective parameters on the DL.

【 授权许可】

Unknown