Estimation of sodium adsorption ratio in a river with kernel-based and decision-tree models
- PDF / 960,643 Bytes
- 13 Pages / 547.087 x 737.008 pts Page_size
- 47 Downloads / 154 Views
Estimation of sodium adsorption ratio in a river with kernel-based and decision-tree models Mohammad Taghi Sattari & Hajar Feizi Muslume Sevba Colak & Ahmet Ozturk Apaydin & Fazli Ozturk
& &
Halit
Received: 2 December 2019 / Accepted: 19 July 2020 # Springer Nature Switzerland AG 2020
Abstract The control of surface water quality plays an important role in the management of water resources. In this context, the estimation and assessment of sodium adsorption ratio (SAR) are required which is one of the significant water quality parameters in the agricultural production sector. Chemical analysis might not, M. T. Sattari (*) : H. Feizi Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz 51666, Iran e-mail: [email protected]
H. Feizi e-mail: [email protected] M. T. Sattari Institute of Research and Development, Duy Tan University, Danang 550000, Vietnam M. T. Sattari : M. S. Colak : A. Ozturk : H. Apaydin : F. Ozturk Department of Agricultural Engineering, Faculty of Agriculture, Ankara University, Ankara 06110, Turkey
M. S. Colak e-mail: [email protected] A. Ozturk e-mail: [email protected] H. Apaydin e-mail: [email protected] F. Ozturk e-mail: [email protected]
however, be feasible for a longer period of time in all the country-scale rivers. Therefore in this study, a support vector regression (SVR) model with different kernel functions; K nearest neighbour algorithm; and four decision-tree models, namely, Hoeffding tree, random forest, random tree, and REPTree, were used to estimate the SAR value with minimal parameters in the Aladag River in Turkey. In alternative scenarios, a correlation matrix and sensitivity analysis were used to ascertain the model inputs from among the 15 distinct parameters. All 15 parameters were utilized as model inputs in the first scenario, and only the sodium (Na) parameter was utilized as the model input in the final scenario. The accuracy of the aforesaid models was then assessed making use of correlation coefficient, Nash-Sutcliffe model efficiency coefficient, root mean square error, mean absolute error, and Willmott index of agreement. The results indicate that the SVR model with the poly kernel function provides the best estimates of SAR among the considered models. According to the findings, there is no considerable difference between the results acquired in the first and last scenarios, and one can determine the SAR value while making use of machine learning approaches taking into account only Na parameter.
Keywords Water quality . Sodium adsorption ratio (SAR) . Machine learning . Kernel functions . Decisiontree models . Turkey
575
Page 2 of 13
Introduction Worldwide, salinity and drainage problems exist in most irrigated lands due to poor quality of irrigation water (Yurtseven et al. 2018). Therefore, determining the surface water quality in each region is important for the development of agricultural land and for the design and operation of irrigation systems. Moreover, in order to clean u
Data Loading...
