Fluctuation of groundwater levels around the world is an important theme in hydrological research. Rising water demand, faulty irrigation practices, mismanagement of soil and uncontrolled exploitation of aquifers are some of the reasons why groundwater levels are fluctuating. In order to effectively manage groundwater resources, it is important to have accurate readings and forecasts of groundwater levels. Due to the uncertain and complex nature of groundwater systems, the development of soft computing techniques (data-driven models) in the field of hydrology has significant potential. This study employs two soft computing techniques, namely, extreme learning machine (ELM) and support vector machine (SVM) to forecast groundwater levels at two observation wells located in Canada. A monthly data set of eight years from 2006 to 2014 consisting of both hydrological and meteorological parameters (rainfall, temperature, evapotranspiration and groundwater level) was used for the comparative study of the models. These variables were used in various combinations for univariate and multivariate analysis of the models. The study demonstrates that the proposed ELM model has better forecasting ability compared to the SVM model for monthly groundwater level forecasting.

The focus of this study was to investigate the fate and transport of toluene, a light nonaqueous-phase liquids (LNAPLs) in the subsurface region under dynamic groundwater table conditions. A series of experiments were conducted using two-dimensional (2D) sand tank setup having dimensions $125\times 90\times 10\mathrm{cm}$ ($\mathrm{L}\times \mathrm{H}\times \mathrm{W}$ ) and integrated with an auxiliary column of inner diameter 14 cm and height 120 cm. Initially, a steady-state flow and LNAPL transport experiment was conducted under stable groundwater table condition. Thereafter, three groundwater table fluctuation experiments were conducted on a rising and falling groundwater table in 2, 4, and 8 h to maintain rapid, general, and slow fluctuation conditions, respectively. The pure phase of toluene was injected at a rate of $1\mathrm{mL}/\min$ for a total duration of 5 min. Soil-water and soil-vapor samples were periodically collected and analyzed for toluene concentrations. Later, the representation of the 2D sand tank setup was numerically simulated to obtain the response of flow and the LNAPL transport under varying groundwater table conditions. Analysis of the results shows that a large LNAPL pool area ($250{\mathrm{cm}}^2$ ) develops under rapidly fluctuating groundwater conditions, which significantly enhances the dissolution rate and contributes to a high concentration of dissolved LNAPLs at the receiving receptors. Estimated values of Sherwood and Peclet numbers show that the dissolution rates were highly affected by groundwater table dynamics, which may cause loss of pure-phase pollutant mass around the pollutant source. The concentration isolines of toluene show that the transport of dissolved LNAPL plumes was also comparatively fast in the case of rapidly fluctuating groundwater. A high biodegradation rate was observed in plume regions having concentration ranges of 140–160 ppm, while it decreases in plume regions having very high ($>160\mathrm{ppm}$ ) and low concentrations ($<140\mathrm{ppm}$ ) of dissolved LNAPL. In the sand tank, microbial growth was found to increase as the plume moved away from the LNAPL pool toward a low gradient, which intensifies the detrimental impact of toluene on the survival of indigenous microorganisms near the LNAPL pool. The results of this study may help in implementing effective remediation techniques to decontaminate LNAPL polluted sites under fluctuating groundwater table conditions, especially in (semi)-arid coastal aquifers.