Hybrid Machine Learning Ensemble Techniques for Modeling Dissolved Oxygen Concentration

Abstract

The reliable prediction of dissolved oxygen concentration (DO) is significantly crucial for protecting the health of the aquatic ecosystem. The current research employed four different single AI-based models, namely long short-term memory neural network (LSTM), extreme learning machine (ELM), Hammerstein-Weiner (HW) and general regression neural network (GRNN) for modeling the DO concentration of Kinta River, Malaysia using available water quality (WQ) parameters. Afterwards, the first scenario used four different ensemble techniques (ET). Two linear, i.e. simple averaging ensemble (SAE) and weighted averaging ensemble (WAE) and two nonlinear namely; backpropagation neural network ensemble (BPNN-E) and HW ensemble (HW-E). The second scenario employed a hybrid random forest (RF) ensemble in order to enhance the prediction accuracy of the single models. The WQ parameters were subjected to a different pre-analysis test to ascertain their stability. The four-model combinations are generated using the nonlinear sensitivity input selection approach. The modeling performance was assessed using the statistical measures of Nash-Sutcliffe coefficient efficiency (NSE), Willmott's index of agreement (WI), root mean square error (RMSE), mean absolute error (MAE) and mean square error (MSE) and correlation coefficient (CC). The results of the single AI-based models demonstrated that HW (M3) served as the best model for predicting DO concentration. For ensemble results, BPNN-E (WI=0.9764) was superior to the other three ET with average decreased of more than 2% with regards to MAE. Investigation on the hybrid RF ensemble demonstrated the reliable accuracy for all the hybrid models with better predictive skill shown by the HW-RF (CC=0.981) ensemble. The overall results verified the promising impact of HW-M3, ET and hybrid RF ensemble for the prediction of the DO concentration in the Kinta River, Malaysia.

Implementation of TQM and the Integration of BIM in the Construction Management Sector in Saudi Arabia Validated with Hybridized Emerging Harris Hawks Optimization (HHO)

“…It should be noted that for any time-series, the preliminary analysis of single parameter or input is quite significant for the reason that their prediction accuracy could potentially add to the performance efficiency of the models. As reported in literature [48], [49], the internal consistency of the parameter can be a positive impact if the Cronbach's alpha values exceed the threshold of 0.7 (see, Table 6). According to Dickey et al, (2012), in order to obtain reliable and valid outcomes that safeguard the stationarity of all the parameters the ADF test is paramount.…”

Effluents quality prediction by using nonlinear dynamic block-oriented models: a system identification approach

“…From these figures, it can be seen that the 0.6044 and 0.9902 are the lowest and highest value of CC obtained from all the models in the validation phase. As it was reported in several research that the high-value of CC attributes in providing the best performing model [34].…”

“…Hammerstein-Wiener is a model that follows and precedes a linear dynamic even though it's a nonlinear block (Fig. 3) [26,[33][34][35][36]. For the identification of a nonlinear system, a black box model as HW was developed [37].…”

Multi-Regional Modeling of Cumulative COVID-19 Cases Integrated with Environmental Forest Knowledge Estimation: A Deep Learning Ensemble Approach

“…Random forest (RF) is an effective supervised learning technique mainly used for classification and regression problems in machine learning [ 29 ]. Breiman, [ 30 ] introduced RF as a practical ensemble algorithm which provides an additional non-stationarity layer to the bagging approach [ 29 , 30 , 31 , 32 ]. RF fulfils its role by using a random sampling mechanism to generate several decision trees.…”