Nuruol Syuhadaa Mohd

Artificial intelligence and geo-statistical models for stream-flow forecasting in ungauged stations: state of the art

Developing an accurate model for discharge estimation techniques of the ungauged river basin is a crucial challenge in water resource management especially in under-development regions. This article is a thorough review of the historical improvement stages of this topic to understand previous challenges that faced researchers, the shortfalls of methods and techniques, how researchers prevailed and what deficiencies still require solutions. This revision focuses on data-driven approaches and GIS-based methods that have improved the accuracy of estimation of hydrological variables, considering their advantages and disadvantages. Past studies used artificial intelligence and geo-statistical methods to forecast the runoff at ungauged river basins, and mapping the spatial distribution has been considered in this study. A recommendation for future research on the potential of a hybrid model utilizing both approaches is proposed and described.

Reservoir inflow forecasting with a modified coactive neuro-fuzzy inference system: a case study for a semi-arid region

Existing forecast models applied for reservoir inflow forecasting encounter several drawbacks, due to the difficulty of the underlying mathematical procedures being to cope with and to mimic the naturalization and stochasticity of the inflow data patterns. In this study, appropriate adjustments to the conventional coactive neuro-fuzzy inference system (CANFIS) method are proposed to improve the mathematical procedure, thus enabling a better detection of the high nonlinearity patterns found in the reservoir inflow training data. This modification includes the updating of the back propagation algorithm, leading to a consequent update of the membership rules and the induction of the centre-weighted set rather than the global weighted set used in feature extraction. The modification also aids in constructing an integrated model that is able to not only detect the nonlinearity in the training data but also the wide range of features within the training data records used to simulate the forecasting model. To demonstrate the model’s efficacy, the proposed CANFIS method has been applied to forecast monthly inflow data at Aswan High Dam (AHD), located in southern Egypt. Comparative analyses of the forecasting skill of the modified CANFIS and the conventional ANFIS model are carried out with statistical score indicators to assess the reliability of the developed method. The statistical metrics support the better performance of the developed CANFIS model, which significantly outperforms the ANFIS model to attain a low relative error value (23%), mean absolute error (1.4 BCM month−1), root mean square error (1.14 BCM month−1), and a relative large coefficient of determination (0.94). The present study ascertains the better utility of the modified CANFIS model in respect to the traditional ANFIS model applied in reservoir inflow forecasting for a semi-arid region.

Heat Pre-Treatment of Beverages Wastewater on Hydrogen Production

At present, a large variety of alternative fuels have been investigated and hydrogen gas is considered as the possible solution for the future due to its unique characteristics. Through dark fermentation process, several factors were found to have significant impact on the hydrogen production either through process enhancement or inhibition and degradation rates or influencing parameters. This work was initiated to investigate the optimum conditions for heat pre-treatment and initial pH for the dark fermentative process under mesophilic condition using a central composite design and response surface methodology (RSM). Different heat treatment conditions and pH were performed on the seed sludge collected from the anaerobic digester of beverage wastewater treatment plant. Heat treatment of inoculum was optimized at different exposure times (30, 90, 120 min), temperatures (80, 90 and 100°C) and pH (4.5, 5.5, 6.5) in order to maximize the biohydrogen production and methanogens activity inhibition. It was found that the optimum heat pre-treatment condition and pH occurred at 100°C for 50 min and the pH of 6.00. At this optimum condition the hydrogen yield was 63.0476 ml H2/mol glucose (H2 Yield) and the COD removal efficiency was 90.87%. In conclusion, it can be hypothesized that different heat treatment conditions led to differences in the initial microbial communities (hydrogen producing bacteria) which resulted in the different hydrogen yields.

Forecasting hydrological parameters for reservoir system utilizing artificial intelligent models and exploring their influence on operation performance

Abstract Obtaining successful operation rules for dam and reservoir systems is crucial for improving water management to meet the increase in agricultural, domestic and industrial activities. Several research efforts have been developed to generate optimal operation rules for dam and reservoir systems utilizing different optimization algorithms. The main purpose of an operation rule is to minimize the gap between water supply and water demand patterns. To examine the optimized model performance, the simulation of a dam and reservoir system is usually carried out for a particular period utilizing the generated operation rule. During the simulation procedure, although reservoir inflow and evaporation are stochastic variables that are required to be forecasted during simulation, they are considered deterministic variables. This study attempts to integrate a forecasting model for reservoir inflow and evaporation with the operation rules generated from optimization models during the simulation procedure. The present study employs several optimization models to generate an optimal operation rule and two different forecasting models for reservoir inflow and reservoir evaporation. The three different optimization algorithms used in this study are the genetic algorithm (GA), particle swarm optimization (PSO) algorithm and shark machine learning algorithm (SMLA). Two different forecasting models have been developed for reservoir inflow and evaporation using the radial basis function neural network (RBF-NN) and support vector regression (SVR). It is necessary to analyze the proposed simulation procedure for examining the operation rule to comprehend the analysis under different optimal operation rules and levels of accuracy for both hydrological variables. The suggested models have been applied to generate optimal operation policies and reservoir inflow and evaporation forecasts for the Timah Tasoh dam (TTD) located in Malaysia. The results show that the major findings regarding the model performance during the simulation period indicate the necessity to pay attention to evaluating the optimized model performance by considering the results of the forecasting model for both the hydrological variables of reservoir inflow and reservoir evaporation rather than the deterministic values.

Anaerobic Digestion at 45 C for Sludge Treatment: A Trade-off between Performances and Capability in Producing Class a Biosolids

 Abstract—Anaerobic digestion at mesophilic and thermophilic temperatures have been widely studied and evaluated for the purpose of sludge stabilization. However, limited extensive research has been conducted on anaerobic digestion in the intermediate zone of 45°C, mainly due to the notion that limited microbial activity occurs within this zone. The objectives of this research were to evaluate the performance and the capability of anaerobic digestion at 45°C in producing class A biosolids, in comparison to a mesophilic and thermophilic anaerobic digestion system operated at 35°C and 55°C, respectively. 45°C anaerobic digestion systems were not able to achieve comparable methane yield and high quality effluent as mesophilic system, though the systems produced biogas with 66.08±2.83% methane. No ammonia inhibition was observed and the digesters were able to achieve volatile solids (VS) reduction of 47.79±1.86%. Moreover, the pathogen counts were less than 1,000 MPN/g dry solids, thus, producing Class A biosolids. However, the 45°C systems suffered from high acetate accumulation, but sufficient buffering capacity was observed. Correspondingly, the dominant methanogen existed in 45°C system was thermo-tolerant acetate-utilizing methanogen of Methanosarcinaceae species.