Modelling Reservoir Turbidity Using Landsat 8 Satellite Imagery by Gene Expression Programming

Abstract

This study aimed to develop a reliable turbidity model to assess reservoir turbidity based on Landsat-8 satellite imagery. Models were established by multiple linear regression (MLR) and gene-expression programming (GEP) algorithms. Totally 55 and 18 measured turbidity data from Tseng-Wen and Nan-Hwa reservoir paired and screened with satellite imagery. Finally, MLR and GEP were applied to simulated 13 turbid water data for critical turbidity assessment. The coefficient of determination (R 2 ), root mean squared error (RMSE), and relative RMSE (R-RMSE) calculated for model performance evaluation. The result show that, in model development, MLR and GEP shows a similar consequent. However, in model testing, the R 2 , RMSE, and R-RMSE of MLR and GEP are 0.7277 and 0.8278, 0.7248 NTU and 0.5815 NTU, 22.26% and 17.86%, respectively. Accuracy assessment result shows that GEP is more reasonable than MLR, even in critical turbidity situation, GEP is more convincible. In the model performance evaluation, MLR and GEP are normal and good level, in critical turbidity condition, GEP even belongs to outstanding level. These results exhibit GEP denotes rationality and with relatively good applicability for turbidity simulation. From this study, one can conclude that GEP is suitable for turbidity modeling and is accurate enough for reservoir turbidity estimation. artificial neural networks, supper vector machine (SVM), random forest (RF), partial least squares (PLS), and principal components regression (PCR) . However, the empirical relation and observation method used to test different data with various temporal and spatial backgrounds or different measuring instruments, the results of reservoir turbidity estimation are considerably different from those of the original research area [35]. The accuracy of the simulated turbidity by the empirical equation is also influenced by the algorithms. Chang et al., using the high-resolution spectral image obtained from Formosat-2 satellite imagery have a resolution of 8 m and the SSC data of 53 mud samples, the empirical relation that is established using the stepwise regression method exhibit the R 2 of 0.84 and the relative-RMSE (R-RMSE) of 31%, however, in the case of data validation and testing, R-RMSE improved to 43%, indicating that the empirical relation between the remote sensing imagery and the water quality observations exhibited a considerable degree of error. Therefore, the rationality and applicability of the integrated assessment for relevant research related to the water quality estimation of remote sensing imagery can be improved if the simulated turbidity accuracy is improved and the difference is reduced [36]. Based on the large-area and high-repetition remote sensing imagery and the measured turbidity, this study would like to provide a simulation algorithm for the one who cannot obtain an ideal result in typical algorithms for reservoir turbidity estimation. Materials and MethodsThis study refers to Quang, N. H. et al., adopted the high-resolution multi-spectrum satell...

Estimation of Water Quality in a Reservoir From Sentinel-2 Msi and Landsat-8 Oli Sensors

“…Recent research in many parts of the world involving water quality have made use of data from Landsat-8 (Liu, Wang, 2019, González-Márquez et al, 2018, Mushtaq, Nee Lala, 2017, Sentinel-2 (Karaoui et al, 2019, Potes et al, 2018 or both (Dutra et al, 2019, Yadav et al, 2019, Watanabe et al, 2018. Table 1 gives a list of some of these authors with the sensor they used and the parameters they analysed.…”

Remote sensing-based water quality index estimation using data-driven approaches: a case study of the Kali River in Uttar Pradesh, India

“…Moreover, the GEP approach is simple and produces reliable WQI measures and reduces substantial time and effort by optimizing the computations to generate simplified prediction expressions. This technique is highly recommended by many researchers (Hashmi et al, 2011 ; Mohammadpour et al, 2016 ; Liu & Wang, 2019 ) for the water quality evaluation of wetlands and other surface water bodies. In addition, the ANN approach is relatively time-consuming and does not furnish any governing equations of the optimized models, which is considered as one of its major disadvantages.…”

“…Ferreira ( 2001 ) represented the encoded genetic information in the gene in the form of an expression tree (ET). With the help of the unequivocal Karva language, the gene composition of a given ET can be generalized on the basis of simple rules of top–down and right–left (Li and Wang, 2019 ). An example of a gene is shown in the form of an ET in Fig.…”

“…More recent studies conducted by Wang et al ( 2019 , 2020 ) inferred deep learning process as a promising tool for formulating environmental property prediction models for screening of green solvents. Several studies successfully applied GEP, along with GP, to a variety of water resources issues (Azamathulla & Ghani, 2011 ; Ghavidel & Montaseri, 2014 ; Liu & Wang, 2019 ; Zakaria et al, 2010 ). Furthermore, these techniques have been considered as substantial tools in solving complex environmental and river engineering problems (Aras et al, 2007 ; Chen et al, 2008 ; Mohammadpour et al, 2015 ).…”

“…In a significant study by Martí et al ( 2013 ), comparison of three approaches, namely ANN, GEP and MLR for estimation of outlet dissolved oxygen in micro-irrigation, was carried out, and the outcomes revealed GEP as the most effective approach. In a recent study carried out by Li and Wang ( 2019 ), a reliable turbidity model was developed to predict reservoir turbidity based on Landsat-8 satellite imagery by utilizing an MLR and GEP approach. Results revealed GEP to be more rational and accurate for turbidity simulation.…”