Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Author: search.filters.author.Deka, P.C.Subject: search.filters.subject.algorithm

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Prediction of daily pan evaporation using support vector machines
    (CAFET INNOVA Technical Society cafetinnova@gmail.com 1-2-18/103, Mohini Mansion, Gagan Mahal Road, Domalguda, Hyderabad 500029, 2014) Pammar, L.; Deka, P.C.
    Water scarcity globally has lead to severe problems in water management. Understanding the rate of evaporation, from surface water resources is essential for precise management of the water balance. However, evaporation is difficult to measure experimentally due to its nature. Preparing reliable forecasts of evaporation has become an essential element towards efficient water management. The objective of this paper is to predict daily pan evaporation using different kernel functions of Support Vector Machines (SVM's) based regression approach for the meteorological data obtained for the region 'Lake Abaya' which is located in the Great Rift Valley, southern part of Ethiopia. The meteorological parameters considered for study includes daily details of mean-temperature (T), wind speed (W), sunshine hours (Sh), relative humidity (Rh), rainfall (P). Among the kernel functions used for study, the polynomial kernel function proved its credibility by showing improved performance in training and testing periods. The evidence for performance of polynomial kernel function was seen in terms of correlation coefficient (CC) obtained for training and testing is respectively 0.940, 0.956 which is acceptable. © 2014 CAFET-INNOVA TECHNICAL SOCIETY.
  • No Thumbnail Available
    Item
    An extreme learning machine approach for modeling evapotranspiration using extrinsic inputs
    (Elsevier B.V., 2016) Patil, A.P.; Deka, P.C.
    Precise estimation of evapotranspiration is crucial for accurate crop-water estimation. Recently machine learning (ML) techniques like artificial neural network (ANN) are being widely used for modeling the process of evapotranspiration. However, ANN faces issues like trapping in local minima, slow learning and tuning of meta-parameters. In this study an improved extreme learning machine (ELM) algorithm was used to estimate weekly reference crop evapotranspiration (ETo). The study was carried out for Jodhpur and Pali meteorological weather stations located in the Thar Desert, India. The study evaluated the performance of three different input combinations. The first input combination used locally available maximum and minimum air temperature data while the second and third combination used ETo values from another station (extrinsic inputs) along with the locally available temperature data as inputs. The performance of ELM models was compared with the empirical Hargreaves equation, ANN and least-square support vector machine (LS-SVM) models. Root mean squared error (RMSE), Nash-Sutcliffe model efficiency coefficient (NSE) and threshold statistics (TS) were used for comparing the performance of the models. The performance of ELM model was found to be better than the Hargreaves and ANN model. The LS-SVM and ELM displayed similar performance. ELM3 models, with 36 and 33 neurons in hidden layer were found to be the best models (RMSE of 0.43 for Jodhpur and 0.33 for Pali station) for estimating weekly ETo at Jodhpur and Pali stations respectively. The results showed that ELM is a simple yet efficient algorithm which exhibited good performance; hence, can be recommended for estimating weekly ETo. Furthermore, it was also found that use of ETo values from another station can help in improving the efficiency of ML models in limited data scenario. © 2016 Elsevier B.V.
  • No Thumbnail Available
    Item
    Dew Point temperature estimation: Application of artificial intelligence model integrated with nature-inspired optimization algorithms
    (MDPI AG indexing@mdpi.com Postfach Basel CH-4005, 2019) Naganna, S.R.; Deka, P.C.; Ghorbani, M.A.; Biazar, S.M.; Al-Ansari, N.; Yaseen, Z.M.
    Dew point temperature (DPT) is known to fluctuate in space and time regardless of the climatic zone considered. The accurate estimation of the DPT is highly significant for various applications of hydro and agro-climatological researches. The current research investigated the hybridization of a multilayer perceptron (MLP) neural network with nature-inspired optimization algorithms (i.e., gravitational search (GSA) and firefly (FFA)) to model the DPT of two climatically contrasted (humid and semi-arid) regions in India. Daily time scale measured weather information, such as wet bulb temperature (WBT), vapor pressure (VP), relative humidity (RH), and dew point temperature, was used to build the proposed predictive models. The efficiencies of the proposed hybrid MLP networks (MLP-FFA and MLP-GSA) were authenticated against standard MLP tuned by a Levenberg-Marquardt back-propagation algorithm, extreme learning machine (ELM), and support vector machine (SVM) models. Statistical evaluation metrics such as Nash Sutcliffe efficiency (NSE), root mean square error (RMSE), and mean absolute error (MAE) were used to validate the model efficiency. The proposed hybrid MLP models exhibited excellent estimation accuracy. The hybridization of MLP with nature-inspired optimization algorithms boosted the estimation accuracy that is clearly owing to the tuning robustness. In general, the applied methodology showed very convincing results for both inspected climate zones. © 2019 by the authors.
  • No Thumbnail Available
    Item
    Evaluating the Performance of CHIRPS Satellite Rainfall Data for Streamflow Forecasting
    (Springer Netherlands rbk@louisiana.edu, 2019) Sulugodu, B.; Deka, P.C.
    Streamflow forecasting can offer valuable information for optimal management of water resources, flood mitigation, and drought warning. This research aims in evaluating the effectiveness of CHIRPS satellite rainfall data in comparison with IMD gridded Rainfall Data and development of various flow forecasting models. Daily rainfall data for three decades (1983–2012) over the Nethravathi Basin, Karnataka, India is used for analysis. The analysis is carried out for the monsoon season (June–September), out of which 70% data considered for training the model and remaining for testing. Different input combinations are developed, and soft-computing methods like ANFIS, GRNN, PSO-ANN, and ELM are applied for flow forecasting on a temporal scale. The model performance is evaluated using various statistical indices like NNSE, RRMSE, and MAE. The results indicate that CHIRPS rainfall showed better performance in comparison with IMD data. ELM expressed an enhanced effect when compared to all other methods. The usefulness and effectiveness of CHIRPS data compared to IMD data has been explored. © 2019, Springer Nature B.V.