Short-term streamflow prediction is essential for managing flood early warning and water resources systems. Although numerical models are widely used for this purpose, they require various types of data and experience to operate the model and often tedious calibration processes. Under the digital revolution, the application of data-driven approaches to predict streamflow has increased in recent decades. In this work, multiple linear regression (MLR) and random forest (RF) models with three different input combinations are developed and assessed for multi-step ahead short-term streamflow predictions, using 14 years of hydrological datasets from the Kulim River catchment, Malaysia. Introducing more precedent streamflow events as predictor improves the performance of these data-driven models, especially in predicting peak streamflow during the high-flow event. The RF model (Nash-Sutcliffe efficiency (NSE): 0.599-0.962) outperforms the MLR model (NSE: 0.584-0.963) in terms of overall prediction accuracy. However, with the increasing lead-time length, the models' overall prediction accuracy on the arrival time and magnitude of peak streamflow decrease. These findings demonstrate the potential of decision tree-based models, such as RF, for short-term streamflow prediction and offer insights into enhancing the accuracy of these data-driven models.
Efficacious operation for dam and reservoir system could guarantee not only a defenselessness policy against natural hazard but also identify rule to meet the water demand. Successful operation of dam and reservoir systems to ensure optimal use of water resources could be unattainable without accurate and reliable simulation models. According to the highly stochastic nature of hydrologic parameters, developing accurate predictive model that efficiently mimic such a complex pattern is an increasing domain of research. During the last two decades, artificial intelligence (AI) techniques have been significantly utilized for attaining a robust modeling to handle different stochastic hydrological parameters. AI techniques have also shown considerable progress in finding optimal rules for reservoir operation. This review research explores the history of developing AI in reservoir inflow forecasting and prediction of evaporation from a reservoir as the major components of the reservoir simulation. In addition, critical assessment of the advantages and disadvantages of integrated AI simulation methods with optimization methods has been reported. Future research on the potential of utilizing new innovative methods based AI techniques for reservoir simulation and optimization models have also been discussed. Finally, proposal for the new mathematical procedure to accomplish the realistic evaluation of the whole optimization model performance (reliability, resilience, and vulnerability indices) has been recommended.
Analytical study of the influence of both the pumping well discharge rate and pumping time on contaminant transport and attenuation is significant for hydrological and environmental science applications. This article provides an analytical solution for investigating the influence of both pumping time and travelling time together for one-dimensional contaminant transport in riverbank filtration systems by using the Green's function approach. The basic aim of the model is to understand how the pumping time and pumping rate, which control the travelling time, can affect the contaminant concentration in riverbank filtration systems. Results of analytical solutions are compared with the results obtained using a MODFLOW numerical model. Graphically, it is found that both analytical and numerical solutions have almost the same behaviour. Additionally, the graphs indicate that any increase in the pumping rate or simulation pumping time should increase the contamination in groundwater. The results from the proposed analytical model are well matched with the data collected from a riverbank filtration site in France. After this validation, the model is then applied to the first pilot project of a riverbank filtration system conducted in Malaysia. Sensitivity analysis results highlight the importance of degradation rates of contaminants on groundwater quality, for which higher utilization rates lead to the faster consumption of pollutants.
Leachate is one of the main surface water pollution sources in Selangor State (SS), Malaysia. The prediction of leachate amounts is elementary in sustainable waste management and leachate treatment processes, before discharging to surrounding environment. In developing countries, the accurate evaluation of leachate generation rates has often considered a challenge due to the lack of reliable data and high measurement costs. Leachate generation is related to several factors, including meteorological data, waste generation rates, and landfill design conditions. The high variations in these factors lead to complicating leachate modeling processes. This study aims at identifying the key elements contributing to leachate production and developing various AI-based models to predict leachate generation rates. These models included Artificial Neural Network (ANN)-Multi-linear perceptron (MLP) with single and double hidden layers, and support vector machine (SVM) regression time series algorithms. Various performance measures were applied to evaluate the developed model's accuracy. In this study, input optimization process showed that three inputs were acceptable for modeling the leachate generation rates, namely dumped waste quantity, rainfall level, and emanated gases. The initial performance analysis showed that ANN-MLP2 model-which applies two hidden layers-achieved the best performance, then followed by ANN-MLP1 model-which applies one hidden layer and three inputs-while SVM model gave the lowest performance. Ranges and frequency of relative error (RE%) also demonstrate that ANN-MLP models outperformed SVM models. Furthermore, low and peak flow criterion (LFC and PFC) assessment of leachate inflow values in ANN-MLP model with two hidden layers made more accurate values than other models. Since minimizing data collection and processing efforts as well as minimizing modeling complexity are critical in the hydrological modeling process, the applied input optimization process and the developed models in this study were able to provide a good performance in the modeling of leachate generation efficiently.
Monitoring the groundwater chemical composition and identifying the presence of pollutants is an integral part of any comprehensive groundwater management strategy. The present study was conducted in a part of West Tripura, northeast India, to investigate the presence and sources of trace metals in groundwater and the risk to human health due to direct ingestion of groundwater. Samples were collected from 68 locations twice a year from 2016 to 2018. Mixed Ca-Mg-HCO3, Ca-Cl and Ca-Mg-Cl were the main groundwater types. Hydrogeochemical methods showed groundwater mineralization due to (1) carbonate dissolution, (2) silicate weathering, (3) cation exchange processes and (4) anthropogenic sources. Occurrence of faecal coliforms increased in groundwater after monsoons. Nitrate and microbial contamination from wastewater infiltration were apparent. Iron, manganese, lead, cadmium and arsenic were above the drinking water limits prescribed by the Bureau of Indian Standards. Water quality index indicated 1.5% had poor, 8.7% had marginal, 16.2% had fair, 66.2% had good and 7.4% had excellent water quality. Correlation and principal component analysis reiterated the sources of major ions and trace metals identified from hydrogeochemical methods. Human exposure assessment suggests health risk due to high iron in groundwater. The presence of unsafe levels of trace metals in groundwater requires proper treatment measures before domestic use.