Zaher Mundher’s research while affiliated with Ton Duc Thang University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (4)


Monthly Sodium adsorption ratio forecasting in rivers using a dual interpretable glass-box complementary intelligent system: Hybridization of Ensemble TVF-EMD-VMD, Boruta-SHAP, and eXplainable GPR
  • Article
  • Full-text available

October 2023

·

201 Reads

·

11 Citations

Expert Systems with Applications

·

·

·

[...]

·

Zaher Mundher

The sodium adsorption ratio (SAR) is the most crucial irrigation water quality indicator to diagnose the suitability of agricultural water resources. Due to this reason, accurate forecasting of SAR in the absence of its time series , based on limited input sequences, is recently considered a challenging environmental issue on a monthly scale. This research developed a dual eXplainable multivariate expert framework for the first time to forecast monthly SAR at Zayanderud River, Iran. The framework (i.e., BS-GPR-E.TVF-EMD-VMD) consisting of a Boruta coupled with SHapley Additive exPlanations (Boruta-SHAP) feature selection, an ensemble of time-varying filter-based empirical mode decomposition (TVF-EMD) and variational modal decomposition (VMD), namely (E.TVF-EMD-VMD), and eXplainable Gaussian process regression (GPR). The main novelty of this framework is converting the "black-box" nature of the forecasting model to a dual interpretable "glass box" before and during the learning process. For this purpose, among nine hydrometric and water quality parameters associated with Zayan-derud River at two stations (Regulating dam and Zaman Khan) over the period of 1969 to 2016, the significant two-month antecedent information (lags) signals were extracted using the Boruta-SHAP feature selection. Afterward, the optimal inputs signal lags for each station were decomposed into sub-components to reduce the complexity and non-stationary of original signals using three pre-processing techniques (i.e., E.TVF-EMD-VMD, TVF-EMD, and VMD). The decomposed predictors were employed as inputs into the multilayer perceptron neural network (MLP), Random Forest (RF), Elman recurrent neural network (ERNN), and eXplainable GPR approaches. Statistical validation and infographic tools revealed that the BS-G PR-E.T VF-EMD-V MD regarding the best performance in the Regulating dam (R = 0.9817, RMSE = 0.1431, and NSE = 0.8866) and Zaman Khan (R = 0.9632, RMSE = 0.0610, and NSE = 0.9233) stations, outperformed the other complementary and stand-alone counterpart frameworks followed by the BS-G PR-T VF-EMD and BS-E RNN-E.T VF-EMD-V MD , respectively. SHAP ex-plainer through the GPR model clearly interpreted the effect of the lagged-time sub-components related to each predictor and represented the impact of each decomposition technique on the input signals through E.TVF-EMD-VMD aiming to forecast SAR in standalone and complementary frameworks.

Download

Figure 1. Location of Lake Nasser in Upper Egypt (Allawi, Jaafar, Mohamad Hamzah, Mohd, et al., 2018).
Figure 2. Architecture of the co-active neuro-fuzzy inference system (CANFIS) model with multiple inputs-signal output. Note: Solid line = procedure of the back-propagation algorithm used in the original CANFIS; dashed line = new procedure of the back-propagation algorithm proposed in this study.
Figure 4. Relative error distribution obtained for support vector regression (SVR) and radial basis function neural network (RBF-NN) models with best input combination.
Figure 5. Relative error distribution obtained for adaptive neuro-fuzzy inference system (ANFIS) and co-active neuro-fuzzy inference system (CANFIS) models with best input combination.
Figure 6. Time series of observed and predicted evaporation by support vector regression (SVR) and radial basis function neural network (RBF-NN) models with best input combination during model validation.

+3

Viability of the advanced adaptive neuro fuzzy inference system model on reservoir evaporation process simulation case study of Nasser Lake in Egypt

August 2019

·

2,429 Reads

·

64 Citations

Reliable prediction of evaporative losses from reservoirs is an essential component of reservoir management and operation. Conventional models generally used for evaporation prediction have a number of drawbacks as they are based on several assumptions. A novel approach called the co-active neuro-fuzzy inference system (CANFIS) is proposed in this study for the modeling of evaporation from meteorological variables. CANFIS provides a center-weighted set rather than global weight sets for predictor-predictand relationship mapping and thus it can provide a higher prediction accuracy. In the present study, adjustments are made in the back-propagation algorithm of CANFIS for automatic updating of membership rules and further enhancement of its prediction accuracy. The predictive ability of the CANFIS model is validated with three well-established artificial intelligence (AI) models. Different statistical metrics are computed to investigate the prediction efficacy. The results reveal higher accuracy of the CANFIS model in predicting evaporation compared to the other AI models. CANFIS is found to be capable of modeling evaporation from mean temperature and relative humidity only, with a Nash-Sutcliffe efficiency of 0.93, which is much higher than that of the other models. Furthermore, CANFIS improves the prediction accuracy by 9.2-55.4% compared to the other AI models. ARTICLE HISTORY


Thin and sharp edges bodies-fluid interaction simulation using cut-cell immersed boundary method

August 2019

·

721 Reads

·

112 Citations

This study aims to develop an adaptive mesh refinement (AMR) algorithm combined with Cut-Cell IBM using two-stage pressure-velocity corrections for thin-object FSI problems. To achieve the objective of this study, the AMR-immersed boundary method (AMR-IBM) algorithm discretizes and solves the equations of motion for the flow that involves rigid thin structures boundary layer at the interface between the structure and the fluid. The body forces are computed in proportion to the fraction of the solid volume in the IBM fluid cells to incorporate fluid and solid motions into the boundary. The corrections of the velocity and pressure is determined by using a novel simplified marker and cell scheme. The new developed AMR-IBM algorithm is validated using a benchmark data of fluid past a cylinder and the results show that there is good agreement under laminar flow. Simulations are conducted for three test cases with the purpose of demonstration the accuracy of the AMR-IBM algorithm. The validation confirms the robustness of the new algorithms in simulating flow characteristics in the boundary layers of thin structures. The algorithm is performed on a staggered grid to simulate the fluid flow around thin object and determine the computational cost. ARTICLE HISTORY KEYWORDS Cut-cell method; adaptive mesh refinement; pressure and velocity corrections; thin objects and fluid structure


Engineering Applications of Computational Fluid Mechanics

August 2019

·

1,256 Reads

·

2 Citations

Engineering Applications of Computational Fluid Mechanics

Reliable prediction of evaporative losses from reservoirs is an essential component of reservoir management and operation. Conventional models generally used for evaporation prediction have a number of drawbacks as they are based on several assumptions. A novel approach called the co-active neuro-fuzzy inference system (CANFIS) is proposed in this study for the modeling of evaporation from meteorological variables. CANFIS provides a center-weighted set rather than global weight sets for predictor-predictand relationship mapping and thus it can provide a higher prediction accuracy. In the present study, adjustments are made in the back-propagation algorithm of CANFIS for automatic updating of membership rules and further enhancement of its prediction accuracy. The predictive ability of the CANFIS model is validated with three well-established artificial intelligence (AI) models. Different statistical metrics are computed to investigate the prediction efficacy. The results reveal higher accuracy of the CANFIS model in predicting evaporation compared to the other AI models. CANFIS is found to be capable of modeling evaporation from mean temperature and relative humidity only, with a Nash-Sutcliffe efficiency of 0.93, which is much higher than that of the other models. Furthermore, CANFIS improves the prediction accuracy by 9.2-55.4% compared to the other AI models. ARTICLE HISTORY

Citations (4)


... It does not require manual setting of the mode function K and can filter signals during the decomposition process. The TVF-EMD method utilizes non-uniform B-spline approximations as timevarying filters to select the cutoff frequencies, improves the stopping criteria, and offers complete adaptability [35]. It is suitable for analyzing linear and non-stationary signals and has gradually been applied to the decomposition of water quality data. ...

Reference:

A River Water Quality Prediction Method Based on Dual Signal Decomposition and Deep Learning
Monthly Sodium adsorption ratio forecasting in rivers using a dual interpretable glass-box complementary intelligent system: Hybridization of Ensemble TVF-EMD-VMD, Boruta-SHAP, and eXplainable GPR

Expert Systems with Applications

... The collapse of these bubbles (implosions) increases as the turbulence kinetic energy increases [9]. These phenomenons can contribute to the further break-up of the spray into smaller droplets which possibly increases the evaporation rate [10]. Fig. 7(b) exhibits the difference of turbulence kinetic energy (TKE) at three nozzle diameters. ...

Engineering Applications of Computational Fluid Mechanics

Engineering Applications of Computational Fluid Mechanics

... and 0.18-0.35 for different model scenarios, respectively (Salih et al. 2019). This discrepancy can be attributed to the distinct input parameters employed in Salih et al. (2019)'s study, which include temperature, relative humidity, wind speed, and solar radiation. ...

Viability of the advanced adaptive neuro fuzzy inference system model on reservoir evaporation process simulation case study of Nasser Lake in Egypt

... 7 Several researchers are engaged in further investigations on this method. [8][9][10] In sharp interface methods, immersed boundaries are introduced without eliminating the values of certain grid nodes, [11][12][13][14][15] which is a common characteristic in diffused interface methods that employ a discrete delta function. This characteristic of sharp interface methods allows them to achieve accurate results using higher-order formulations easily. ...

Thin and sharp edges bodies-fluid interaction simulation using cut-cell immersed boundary method