Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
2 results
Search Results
Item Predictive Simulation of Seawater Intrusion in a Tropical Coastal Aquifer(American Society of Civil Engineers (ASCE) onlinejls@asce.org, 2016) Lathashri, U.A.; Mahesha, A.The solute transport in a tropical, coastal aquifer of southern India is numerically simulated considering the possible cases of aquifer recharge, freshwater draft, and seawater intrusion using numerical modeling software. The aquifer considered for the study is a shallow, unconfined aquifer with lateritic formations having good monsoon rains up to about 3,000 mm during June to September and the rest of the months almost dry. The model is calibrated for a two-year period and validated against the available dataset, which gave satisfactory results. The groundwater flow pattern during the calibration period shows that for the month of May a depleted water table and during the monsoon month of August a saturated water table was predicted. The sensitivity analysis of model parameters reveals that the hydraulic conductivity and recharge rate are the most sensitive parameters. Based on seasonal investigation, the seawater intrusion is found to be more sensitive to pumping and recharge rates compared to the aquifer properties. The water balance study confirms that river seepage and rainfall recharge are the major input to the aquifer. The model is used to forecast the landward movement of seawater intrusion because of the anticipated increase in freshwater draft scenarios in combination with the decreased recharge rate over a longer period. The results of the predictive simulations indicate that seawater intrusion may still confine up to a distance of approximately 450-940 m landward for the scenarios considered and thus are sustainable. © 2015 American Society of Civil Engineers.Item Groundwater level modeling using Augmented Artificial Ecosystem Optimization(Elsevier B.V., 2023) Nguyen, N.; Deb Barma, S.D.; van Lam, T.; Kisi, O.; Mahesha, A.Nature-inspired optimization is an active area of research in the artificial intelligence (AI) field and has recently been adopted in hydrology for the calibration (training) of both process-based and statistical models. This study proposes an improved AI model, Augmented Artificial Ecosystem Optimization-based Multi-Layer Perceptron (AAEO-MLP), to build a monthly groundwater level (GWL) forecasting model. AAEO-MLP model is built on the novel Augmented version of Artificial Ecosystem Optimization and traditional MLP network. In AAEO, Levy-flight trajectory and Gaussian random are utilized in exploration and exploitation to improve the optimizing ability. The AAEO-MLP model is tested on two time-series (1989–2012) datasets collected at two wells in India. Various explanatory variables such as monthly cumulative precipitation, mean temperature, tidal height, and previous measurements of GWL were considered for predicting 1-month ahead of GWL. The performance of AAEO-MLP was benchmarked against 17 different models (original AEO, 3 different variants of AEO, and 13 well-known models) in terms of forecasting accuracy based on six metrics (e.g., mean absolute error, root mean square error, Kling–Gupta efficiency, normalized Nash–Sutcliffe efficiency, Pearson's correlation index, a20 index). Furthermore, convergence analysis and model stability are employed to indicate the effectiveness of AAEO-MLP. The compared results express that the AAEO-MLP is superior to other models in terms of prediction accuracy, convergence, and stability. Overall, the results depict that the AAEO is a promising approach for optimizing machine learning models (e.g., MLP) and should be explored for other hydrological forecasting applications (e.g., streamflow, rainfall) to further assess its strengths over existing methods. © 2022 Elsevier B.V.