Simulation of titicaca lake water level fluctuations using hybrid machine learning technique integrated with grey wolf optimizer algorithm
(2020) In Water 12(11). p.1-18- Abstract
Lakes have an important role in storing water for drinking, producing hydroelectric power, and environmental, agricultural, and industrial uses. In order to optimize the use of lakes, precise prediction of the lake water level (LWL) is a main issue in water resources management. Due to the existence of nonlinear relations, uncertainty, and characteristics of the time series variables, the exact prediction of the lake water leveAl is difficult. In this study the hybrid support vector regression (SVR) and the grey wolf algorithm (GWO) are used to predict lake water level fluctuations. Also, three types of data preprocessing methods, namely Principal component analysis, Random forest, and Relief algorithm were used for finding the best... (More)
Lakes have an important role in storing water for drinking, producing hydroelectric power, and environmental, agricultural, and industrial uses. In order to optimize the use of lakes, precise prediction of the lake water level (LWL) is a main issue in water resources management. Due to the existence of nonlinear relations, uncertainty, and characteristics of the time series variables, the exact prediction of the lake water leveAl is difficult. In this study the hybrid support vector regression (SVR) and the grey wolf algorithm (GWO) are used to predict lake water level fluctuations. Also, three types of data preprocessing methods, namely Principal component analysis, Random forest, and Relief algorithm were used for finding the best input variables for prediction LWL by the SVR and SVR-GWO models. Before the LWL simulation on monthly time step using the hybrid model, an evolutionary approach based on different monthly lags was conducted for determining the best mask of the input variables. Results showed that based on the random forest method, the best scenario of the inputs was Xt−1, Xt−2, Xt−3, Xt−4 for the SVR-GWO model. Also, the performance of the SVR-GWO model indicated that it could simulate the LWL with acceptable accuracy (with RMSE = 0.08 m, MAE = 0.06 m, and R2 = 0.96).
(Less)
- author
- Mohammadi, Babak LU ; Guan, Yiqing ; Aghelpour, Pouya ; Emamgholizadeh, Samad ; Zolá, Ramiro Pillco LU and Zhang, Danrong
- publishing date
- 2020-11
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Data-driven techniques, Hybrid model, Lake water level, Prediction, Support vector regression, Titicaca Lake
- in
- Water
- volume
- 12
- issue
- 11
- article number
- 3015
- pages
- 18 pages
- publisher
- MDPI AG
- external identifiers
-
- scopus:85095971887
- ISSN
- 2073-4441
- DOI
- 10.3390/w12113015
- language
- English
- LU publication?
- no
- id
- 3c68dacd-cb1a-4eda-99f8-35b207b3ebe2
- date added to LUP
- 2020-12-30 05:07:12
- date last changed
- 2022-04-26 22:52:49
@article{3c68dacd-cb1a-4eda-99f8-35b207b3ebe2, abstract = {{<p>Lakes have an important role in storing water for drinking, producing hydroelectric power, and environmental, agricultural, and industrial uses. In order to optimize the use of lakes, precise prediction of the lake water level (LWL) is a main issue in water resources management. Due to the existence of nonlinear relations, uncertainty, and characteristics of the time series variables, the exact prediction of the lake water leveAl is difficult. In this study the hybrid support vector regression (SVR) and the grey wolf algorithm (GWO) are used to predict lake water level fluctuations. Also, three types of data preprocessing methods, namely Principal component analysis, Random forest, and Relief algorithm were used for finding the best input variables for prediction LWL by the SVR and SVR-GWO models. Before the LWL simulation on monthly time step using the hybrid model, an evolutionary approach based on different monthly lags was conducted for determining the best mask of the input variables. Results showed that based on the random forest method, the best scenario of the inputs was X<sub>t−1</sub>, X<sub>t−2</sub>, X<sub>t−3</sub>, X<sub>t−4</sub> for the SVR-GWO model. Also, the performance of the SVR-GWO model indicated that it could simulate the LWL with acceptable accuracy (with RMSE = 0.08 m, MAE = 0.06 m, and R<sup>2</sup> = 0.96).</p>}}, author = {{Mohammadi, Babak and Guan, Yiqing and Aghelpour, Pouya and Emamgholizadeh, Samad and Zolá, Ramiro Pillco and Zhang, Danrong}}, issn = {{2073-4441}}, keywords = {{Data-driven techniques; Hybrid model; Lake water level; Prediction; Support vector regression; Titicaca Lake}}, language = {{eng}}, number = {{11}}, pages = {{1--18}}, publisher = {{MDPI AG}}, series = {{Water}}, title = {{Simulation of titicaca lake water level fluctuations using hybrid machine learning technique integrated with grey wolf optimizer algorithm}}, url = {{http://dx.doi.org/10.3390/w12113015}}, doi = {{10.3390/w12113015}}, volume = {{12}}, year = {{2020}}, }