Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
36 results
Search Results
Item Support vector machine applications in the field of hydrology: A review(Elsevier BV, 2014) Naganna, S.; Deka, P.C.In the recent few decades there has been very significant developments in the theoretical understanding of Support vector machines (SVMs) as well as algorithmic strategies for implementing them, and applications of the approach to practical problems. SVMs introduced by Vapnik and others in the early 1990s are machine learning systems that utilize a hypothesis space of linear functions in a high dimensional feature space, trained with optimization algorithms that implements a learning bias derived from statistical learning theory. This paper reviews the state-of-the-art and focuses over a wide range of applications of SVMs in the field of hydrology. To use SVM aided hydrological models, which have increasingly extended during the last years; comprehensive knowledge about their theory and modelling approaches seems to be necessary. Furthermore, this review provides a brief synopsis of the techniques of SVMs and other emerging ones (hybrid models), which have proven useful in the analysis of the various hydrological parameters. Moreover, various examples of successful applications of SVMs for modelling different hydrological processes are also provided. © 2014 Elsevier B.V.Item Factors influencing streambed hydraulic conductivity and their implications on stream–aquifer interaction: a conceptual review(Springer Verlag service@springer.de, 2017) Naganna, S.R.; Deka, P.C.; Ch, S.; Hansen, W.F.The estimation and modeling of streambed hydraulic conductivity (K) is an emerging interest due to its connection to water quality, aquatic habitat, and groundwater recharge. Existing research has found ways to sample and measure K at specific sites and with laboratory tests. The challenge undertaken was to review progress, relevance, complexity in understanding and modeling via statistical and geostatistical approaches, literature gaps, and suggestions toward future needs. This article provides an overview of factors and processes influencing streambed hydraulic conductivity (K) and its role in the stream–aquifer interaction. During our synthesis, we discuss the influence of geological, hydrological, biological, and anthropogenic factors that lead to variability of streambed substrates. Literature examples document findings to specific sites that help to portray the role of streambed K and other interrelated factors in the modeling of hyporheic and groundwater flow systems. However, studies utilizing an integrated, comprehensive database are limited, restricting the ability of broader application and understanding. Examples of in situ and laboratory methods of estimating hydraulic conductivity suggest challenges in acquiring representative samples and comparing results, considering the anisotropy and heterogeneity of fluvial bed materials and geohydrological conditions. Arriving at realistic statistical and spatial inference based on field and lab data collected is challenging, considering the possible sediment sources, processes, and complexity. Recognizing that the K for a given particle size group includes several to many orders of magnitude, modeling of streambed K and groundwater interaction remain conceptual and experimental. Advanced geostatistical techniques offer a wide range of univariate or multi-variate interpolation procedures such as kriging and variogram analysis that can be applied to these complex systems. Research available from various studies has been instrumental in developing sampling options, recognizing the significance of fluvial dynamics, the potential for filtration, transfer, and storage of high-quality groundwater, and importance to aquatic habitat and refuge during extreme conditions. Efforts in the characterization of natural and anthropogenic conditions, substrate materials, sediment loading, colmation, and other details highlight the great complexity and perhaps need for a database to compile relevant data. The effects on streambed hydraulic conductivity due to anthropogenic disturbances (in-stream gravel mining, contaminant release, benthic activity, etc.) are the areas that still need focus. An interdisciplinary (hydro-geo-biological) approach may be necessary to characterize the magnitude and variability of streambed K and fluxes at local, regional scales. © 2017, Springer-Verlag GmbH Germany.Item A basic review of fuzzy logic applications in hydrology and water resources(Springer Science and Business Media Deutschland GmbH, 2020) Kambalimath S, S.; Deka, P.C.In recent years, fuzzy logic has emerged as a powerful technique in the analysis of hydrologic components and decision making in water resources. Problems related to hydrology often deal with imprecision and vagueness, which can be very well handled by fuzzy logic-based models. This paper reviews a variety of applications of fuzzy logic in the domain of hydrology and water resources in brief. So far in the literature, fuzzy logic-based hybrid models have been significantly applied in hydrologic studies. Furthermore, in this paper, the literature is reviewed on the basis of applications using pure fuzzy logic models and applications using hybrid-fuzzy modeling approach. This review suggests that hybrid-fuzzy modeling approach works well in many applications of hydrology when compared with pure fuzzy logic modeling. © 2020, The Author(s).Item Remote sensing and GIS application in assessment of coastal vulnerability and shoreline changes: a review(Taylor and Francis Ltd., 2021) Kulithalai Shiyam Sundar, K.S.S.; Deka, P.C.Coastal zones are the transition between the land and sea. With the advancements in the technology in past few decades lead to the increase in the need for the transportation in turn leading to the construction of harbors, roads, industries, settlements and recreational activities making the coastal environment a fragile one. Spite of overexploitation and unsustainable use of the resources leads the researchers to assess the rate of change and the vulnerability of the coast. In this review two aspects, shoreline changes and the coastal vulnerability index (CVI), had been reviewed and discussed in detail. Authors refined the set of parameters to determine the vulnerability, depending on the physical and socio-economic condition of the coast. Finally, an attempt is made to review the research work carried out in the vulnerability assessment and shoreline change studies that were reported from different coastal zones at different time-spans and methodologies helping the researchers to frame their parameters required for the particular study depending on the nature of the study region. Thus, providing the insight knowledge for the authors to determine the critical parameter that influences the coast to a greater extent for a particular study. © 2019 Indian Society for Hydraulics.Item Municipal Residential Water Consumption Estimation Techniques Using Traditional and Soft Computing Approach: a Review(Springer Science and Business Media B.V., 2022) Surendra, H.J.; Deka, P.C.Rate of urbanization in towns and cities is so rapid, which leads to increase in the demand of water. Any developmental activities depend on availability of water. It is necessary to serve residents with better urban infrastructure by balancing both supply and demand. Hence, identifying the factors influencing consumption of water in residential area is very important. In this paper, climatic variables and socio-economic factors influencing water consumption and its computing techniques are discussed. Many studies showed that soft computing models are excellent models for predictions; however, they have been exiguously reported. Hence, here the advantages of soft computing methods are discussed and compared with traditional methods. In the present study, soft computing techniques and its applications such as fuzzy logic (FL), artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS) and different wavelets are summarized and reviewed from problem point of view and application point of view. Several information on the possible future research, application and combinations using soft computing methods were discussed. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.Item Artificial intelligence application in drought assessment, monitoring and forecasting: a review(Springer Science and Business Media Deutschland GmbH, 2022) Kikon, A.; Deka, P.C.Drought is a natural hazard creating havoc on economic, social and environmental aspects. As a result of its slow and creeping nature, it is problematic to establish the onset as well as the termination of drought. Irrespective of its spatial and temporal variability, drought occurs in almost all regions. A wide range of drought studies has been conducted by many researchers over a long period of time. The damage caused by drought has a huge impact on the social, economic and agricultural sectors. Researchers have defined drought in different ways depending upon the parameters and its characteristics, and universally there is no proper definition for drought because of its complexity in nature. This review is focused mainly on various Artificial Intelligence techniques used in drought assessment, monitoring, management and forecasting. The findings from the study shows that drought prediction has become significance in the field of hydrology, Water Resources Management, sustainable agriculture, etc. by using the various AI techniques. In recent studies, AI has been used widely in analysing drought in different regions. The applications of AI techniques in the domain of drought assessing, monitoring, forecasting, etc., shows a rapid growth and that the impact of these will be increasing in future. For understanding the different concepts of drought study, it is needed to establish different system of drought management in order to monitor the different factors affecting drought and then take proper measures to mitigate the damage. Literature studies have been done to analyze the onset and other measures of drought management. Future research may be oriented towards Modeling and probabilistic analysis of climatic data for refining the drought vulnerability mapping, analysis of onset and termination, warning system and drought declaration process depending on the conditions of the region. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.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 Hybrid wavelet neural network model for improving forecasting accuracy of time series significant wave height(2011) Prahlada, R.; Deka, P.C.Forecasting of a time series ocean wave data for various lead times has been attempted using hybrid wavelet-Artificial neural networks (WLNN) approach in this study. To improve the model performance a wavelet transformation is attached prior to a predictor (ANN) and then analysis has been carried out. Here the wavelet transformation is used to decompose the original significant wave height (Hs) data into its sub signals in the form of approximation coefficients and detail coefficients. Further, these coefficients were fed to ANN as inputs and targets and the results obtained from the hybrid model are then reconstructed to obtain the predicted significant wave heights. The predicted results from the proposed model were compared with the single ANN results. From the results, it is concluded that the proposed model is working efficiently for predicting time series data, and also the error observed at the higher lead time was very less as compared to the single ANN. The effect of decomposition level is also analysed in thisstudy and their influence was observed significantly in the higher lead time forecasting. © 2011 CAFET-INNOVA TECHNICAL SOCIETY.Item Discrete wavelet neural network approach in significant wave height forecasting for multistep lead time(2012) Deka, P.C.; Prahlada, R.Recently Artificial Neural network (ANN) was extensively used as non-linear inter-extrapolator for ocean wave forecasting as well as other application in ocean engineering. In this current study, the Wavelet transform was hybridised with ANN naming Wavelet Neural Network (WLNN) for significant wave height forecasting near Mangalore, west coast of India, upto 48 h lead time. The main time series of significant wave height data were decomposed to multiresolution time series using discrete wavelet transformations. Then, the multiresolution time series data were used as input of the ANN to forecast the significant wave height at different multistep lead time. It was shown how the proposed model, WLNN, that makes use of multiresolution time series as input, allows for more accurate and consistent predictions with respect to classical ANN models. The proposed wavelet model (WLNN) results revealed that it was better forecasted and consistent than single ANN model because of using multiresolution time series data as inputs. © 2012 Elsevier Ltd. All rights reserved.