Forecasting of groundwater level variations is a significantly needed in groundwater resource management. Precise water level prediction assists in practical and optimal usage of water resources. The main objective of using an artificial neural network (ANN) was to investigate the feasibility of feed-forward, Elman and Cascade forward neural networks with different algorithms to estimate groundwater levels in the Langat Basin from 2007 to 2013. In order to examine the accuracy of monthly water level forecasts, effectiveness of the steepness coefficient in the sigmoid function of a developed ANN model was evaluated in this research. The performance of the models was evaluated using the mean squared error (MSE) and the correlation coefficient (R). The results indicated that the ANN technique was well suited for forecasting groundwater levels. All models developed had shown acceptable results. Based on the observation, the feed-forward neural network model optimized with the Levenberg-Marquardt algorithms showed the most beneficial results with the minimum MSE value of (0.048) and maximum R value of (0.839), obtained for simulation of groundwater levels. The present research conclusively showed the capability of ANNs to provide excellent estimation accuracy and valuable sensitivity analyses.
Estimation and forecast of groundwater recharge and capacity of aquifer are essential issues in water resources investigation. In the current research, groundwater recharge, recharge coefficient and effective rainfall were determined through a case study using empirical methods applicable to the tropical zones. The related climatological data between January 2000 and December 2010 were collected in Selangor, Malaysia. The results showed that groundwater recharge was326.39 mm per year, effective precipitation was 1807.97 mm per year and recharge coefficient was 18% for the study area. In summary, the precipitation converted to recharge, surface runoff and evapotranspiration are 12, 32 and 56% of rainfall, respectively. Correlation between climatic parameters and groundwater recharge showed positive and negative relationships. The highest correlation was found between precipitation and recharge. Linear multiple regressions between
recharge and measured climatologic data proved significant relationship between recharge and rainfall and wind speed. It was also proven that the proposed model provided an accurate estimation for similar projects.
The relationship between heavy metal and trophic properties in polymictic lake at Sembrong Lake, Peninsular Malaysia was assessed. Sixteen parameters, including heavy metals and trophic parameters were monitored. pH, temperature, dissolved oxygen and heavy metals level changes significantly influenced by the dynamic of polymictic mixing pattern. The mean concentrations of heavy metals in the reservoir decreased in the following order: Fe > Mn > Zn > Cu > As > Pb. The result showed that this polymictic lake is being threatened by cultural eutrophication with TSI value range from 72.40 to 80.41 and classified as a hypereutrophic lake. The levels of heavy metal pollution in the reservoir range from slightly polluted to polluted. Factor analysis was performed to determine the relationship between heavy metals and trophic parameters. Five factors were responsible for data structure and explained the 83% of total variance. These factors differentiate each group of parameters according to their common characteristics. Photosynthesis, respiration and redox processes were main factors contributing to the variability of both properties.