Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item Fuzzy logic modeling for groundwater level forecasting of west coast region in India(2011) Dandagala, D.; Deka, P.C.Forecasting the groundwater table in unconfined aquifer is essential for efficient planning of conjunctive use in a basin. In this study, fuzzy logic (FL) models have been developed for groundwater level forecasting in west coast humid region of Karnataka state, India. The FL modeling was carried out to forecast the groundwater table by one week lead time at three different sites over the study area. Mamdani fuzzy inference system was adopted in the present study and finally centroid of area defuzzification method has been applied to obtain crisp output. The results concluded that the FL model performed quite satisfactorily as assessed by various performance indices such as Root mean square error, Coefficient of correlation, and Mean absolute error. © 2011 CAFET-INNOVA TECHNICAL SOCIETY. All rights reserved.Item A comparative study on RBF and NARX based methods for forecasting of groundwater level(2011) Dandagala, D.; Deka, P.C.Evaluation and forecasting of groundwater levels through time series model (s) helps for the sustainable development of groundwater resources. The focus of the present study is on the application of Radial Basis Function (RBF) and Non Linear auto-regressive with exogenous variable (NARX) data driven models to forecast groundwater level for multiple input scenario's and also multiple lead time. Weekly time series groundwater level data has been used as input and the models are developed to forecast one, two, three, four, five and sixth week ahead. Root mean square error (RMSE) and correlation coefficient (Cc) are used for evaluating the accuracy of the models. Based on the comparison of results, it was found that the RBF models are superior to the NARX models in forecasting groundwater level considering RMSE and Cc. The obtained result indicates that the RBF has high performance and consistent upto fourth week lead time and decaying performance for NARX models. Hence, RBF and NARX have the potential in forecasting groundwater level efficiently for multi step lead time. © 2011 CAFET-INNOVA TECHNICAL SOCIETY. All rights reserved.Item Ground water potential assessment of Haladi River basin in Westernghat of Udupi district, Karnataka, India(2013) Mahadeve Gowda, S.K.; Nagaraj, M.K.For a sustainable development of water resources, it is imperative to make a quantitative estimation of the available water resources. It is necessary to maintain the groundwater reservoir in a state of Dynamic equilibrium over a period of time and the water level fluctuations have to be kept within a particular range over the monsoon and non-monsoon seasons. Groundwater is a dynamic system. The total annual replenishable resource is around 43 M ha-m. The development and over-exploitation of groundwater resources have raised the concern and need for judicious and scientific resource management and conservation. Among the two major water resources, surface and ground water, it is the ground water resource, which needs to be managed carefully, especially in drought prone areas. To assess the groundwater potential, a suitable and accurate technique is required for a meaningful and objective analysis. A critical study is carried out on the different methods of estimating the groundwater potential and compared to arrive the most suitable technique for practical utility. In this work, five methods of estimating groundwater recharge were studied viz., 1. Yearly water level fluctuation 2. Ten year average water level fluctuation 3. Fluctuation between the lowest and highest water levels over ten years 4. Relationship between rainfall and recharge Method. The results of this study helps in accurate prediction of groundwater availability, which in turn may avoid groundwater over exploitation and help to restore the eco-systems. © 2013 CAFET-INNOVA TECHNICAL SOCIETY.Item Regional Trends and Spatiotemporal Analysis of Rainfall and Groundwater in the West Coast Basins of India(American Society of Civil Engineers (ASCE), 2022) Krishnan, C.; Mahesha, M.The present study investigates the spatiotemporal variabilities of long-term (1950-2016) rainfall and regional groundwater levels for annual and seasonal periods over the west coast of India. The study area is a narrow strip of land between Western Ghats (mountainous terrain) and the Arabian Sea, extending over 1,500 km from south to north. The Mann Kendall (MK) and Sen's slope estimator established the long-term trend and magnitude of rainfall and groundwater. The nature of trends in the time series of hydroclimatic variables was identified through singular spectrum analysis (SSA). The SSA extracted nonlinear trends along with the shape for both increasing and decreasing trends. Annual and southwest monsoon rainfall exhibited prominent decreasing trends. The percentage departure analysis of rainfall revealed that earlier decades (1950-1980) were the wettest, followed by the drier decades (1980-2016) for Periyar, Varrar, and Netravati and vice versa for Vasishti and Bhatsol. The wavelet spectra for rainfall indicated short- and long-term modulations. The long-term groundwater level trends of 725 wells on the entire west coast showed a significant decline in 13% of wells, and 6% of wells indicated increasing trends. The Monte Carlo-based numerical investigations on the modified MK (mMK) test power indicated the influence of parent distributions on trend detection. The field significance of trends at a 5% significance level was examined using the bootstrap test. The precipitation data were then compared with groundwater level variation at each site, and correlations were established. The declining southwest monsoon rains and their uneven spatial distribution could be attributed to a subsequent decline in the region's postmonsoon groundwater levels. © 2022 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.Item Nonlinear analysis of groundwater levels: investigating trends and the impact of El Niño on groundwater drought in a southern region of India(Springer Science and Business Media Deutschland GmbH, 2025) Poojitha, K.; Dodamani, B.M.The expansion of groundwater irrigation and the cultivation of water-intensive sugarcane, combined with low rainfall, have exacerbated groundwater depletion and intensified droughts in the semi-arid Upper Krishna basin, India. This study employs an iterative singular spectrum analysis (iterative SSA) approach to impute missing groundwater level data from 25 monitoring wells. Cross-validation results show that iterative SSA effectively preserves the overall data structure when missing data was random, achieving good performance metrics with NSE > 0.79, R2 > 0.8 and RMSE < 0.88 under optimal parameters (L = 12 and k = 5). The reconstructed groundwater levels were then used to identify nonlinear trends with a 180-month smoothing SSA window and to investigate the impact of strong El Niño events on groundwater drought through cross-wavelet transform (XWT) and wavelet coherence (WTC) analyses between 1983 and 2017. The nonlinear trends revealed short-term deviations in groundwater levels during 1991–2000, 2002–2003, and 2015–2017. These deviations were corroborated by significant cross-wavelet power and high wavelet coherence between the Niño 3.4 SST Index and groundwater drought, particularly under low rainfall conditions, indicating stress on the region’s groundwater system. Although the study effectively captures the nonlinear nature of groundwater levels and the influence of climate variability on drought, the complexity of the groundwater system in the region persists due to physical water scarcity and high groundwater extraction for irrigation. This study highlights the importance of imputing missing data and applying nonlinear trend and wavelet analyses to detect short-term deviations caused by severe droughts, driven by strong El Niño events and high irrigation demands. © The Author(s) under exclusive licence to Institute of Geophysics, Polish Academy of Sciences 2025.