Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Effects of land use and climate change on water scarcity in rivers of the Western Ghats of India(Springer Science and Business Media Deutschland GmbH, 2021) Sharannya, T.M.; Venkatesh, K.; Mudbhatkal, A.; Muthuvel, M.; Mahesha, A.This paper assesses the long-term combined effects of land use (LU) and climate change on river hydrology and water scarcity of two rivers of the Western Ghats of India. The historical LU changes were studied for four decades (1988–2016) using the maximum likelihood algorithm and the long-term LU (2016–2075) was estimated using the Dyna-CLUE prediction model. Five General Circulation Models (GCMs) were utilized to assess the effects of climate change (CC) and the Soil and Water Assessment Tool (SWAT) model was used for hydrological modeling of the two river catchments. To characterize granular effects of LU and CC on regional hydrology, a scenario approach was adopted and three scenarios depicting near-future (2006–2040), mid-future (2041–2070), and far-future (2071–2100) based on climate were established. The present rate of LU change indicated a reduction in forest cover by 20% and an increase in urbanized areas by 9.5% between 1988 and 2016. It was estimated that forest cover in the catchments may be expected to halve compared to the present-day LU (55% in 2016 to 23% in 2075), along with large-scale conversion to agricultural lands (13.5% in 2016 to 49.5% in 2075). As a result of changes to LU and forecasted climate, it was found that rivers in the Western Ghats of India might face scarcity of fresh water in the next two decades until the year 2040. However, because of large-scale LU conversion toward the year 2050, streamflow in rivers might increase as high as 70.94% at certain times of the year. Although an increase in streamflow is perceived favorable, the streamflow changes during summer and winter may be expected to affect the cropping calendar and crop yield. The changes to streamflow were also linked to a 4.2% increase in ecologically sensitive wetlands of the Aghanashini river catchment. © 2021, The Author(s), under exclusive licence to Springer Nature Switzerland AG.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 Evaluation of GPM IMERG satellite precipitation for rainfall–runoff modelling in Great Britain(Taylor and Francis Ltd., 2024) Gautam, J.; O, S.; Vinod, D.; Mahesha, A.Reliable hydrological simulations require accurate precipitation data. However, data uncertainties due to the indirect nature of satellite estimates can propagate through hydrological models and lead to simulation errors. This study assesses the accuracy of Global Precipitation Measurement (GPM) Integrated Multi-satellite Retrievals for GPM (IMERG) products, comparing them directly with ground-based precipitation data and evaluating their performance in rainfall–runoff modelling across Great Britain. Three IMERG V06 products (IMERG-Early, IMERG-Late, and IMERG-Final) are examined. Utilizing the simple water balance model (SWBM), the analysis covers 250 basins, revealing that the SWBM performs well in over 50% of the basins. Runoff estimations show that European Observation (E-OBS) ground-based data yield the highest Nash-Sutcliffe efficiency (NSE) score (0.91), followed by IMERG-Final (0.85), IMERG-Late (0.82), and IMERG-Early (0.73). The findings underscore IMERG’s utility in hydrological modelling for ungauged or poorly gauged basins. © 2024 IAHS.Item Modeling non-stationary 1-hour extreme rainfall for Indian river basins under changing climate(Elsevier B.V., 2025) Vinod, D.; Mahesha, A.India's complex topography and the increasing influence of climate change have exacerbated the challenges of modeling 1-hour non-stationary extreme rainfall events. Prior studies have indicated rising intensities of such events, particularly in coastal and urban areas. This study addresses these issues by developing 155 basin-specific non-stationary surface response models, incorporating geographical, climatic, and temporal covariates. Using 13 Max-Stable Process (MSP) characterizations, extreme rainfall variability across 11 major river basins and three-time scales were effectively modeled. The Brown-Resnick, Geometric-Gaussian, and Extremal-t models demonstrated varying effectiveness across regions. The findings emphasize the critical role of region-specific analysis in water resource management and disaster preparedness, where the high temporal resolution datasets are limited for the point process-based models. The global processes and regional climate change are found to predominantly influence 1-hour extreme rainfall across the majority of river basins in India. © 2025 Elsevier B.V.