http://dspace.library.iitb.ac.in/jspui/handle/100/3 2013-03-05T08:06:54Z http://dspace.library.iitb.ac.in/jspui/handle/100/14416 Title: Artificial Neural Network Models for Sivajisagar lake Evaporation Prediction Authors: Arunkumar, R; Jothiprakash, V Abstract: Prediction of lake evaporation is very much essential for effective water resources planning, operation and management. In India, usually, the lake evaporation is estimated from the pan evaporation and the average water spread area. Accurate prediction of lake evaporation by conventional method is a cumbersome process, since it is in non-linear relationship with the storage and other meteorological parameters. The recently evolved soft computing techniques are proved to be efficient to model these non-linear hydrological processes. Thus in the present study, two artificial neural network algorithms (ANN) namely, multi-layer perceptron (MLP) and time lagged recurrent neural network (TLRN) are compared to predict the lake evaporation. The daily Shivajisagar lake evaporation data collected from the Koyna dam circle for a period of 49 years has been used in the modelling. About 70% of the dataset is used for training the ANN models and the remaining 30% is used for testing. It is found that both the ANN algorithms predicted the lake evaporation very well with a correlation coefficient around 0.99. This shows that, if the input data series exhibits good pattern with less noise, the soft computing techniques results in better performances 2012-01-01T00:00:00Z http://dspace.library.iitb.ac.in/jspui/handle/100/14415 Title: Inter-comparison of temperature-based reference crop evapotranspiration methods Authors: Jothiprakash, V; Devamane, M.G.; Sasireka, K Abstract: This paper investigates the evaluation and possibility of recalibrating temperature-based methods for estimating reference crop evapotranspiration (ETr) at a station in Tamil Nadu. Seven temperature-based evapotranspiration methods namely Thronthwaite, Blaney-Criddle, Romanenko, Hamon, Hargreaves, Linacre, and Kharrufa methods were evaluated and compared with each other and with a standard method in estimating ETr in the selected region. All the seven methods were developed in countries other than India and hence, the empirical coefficients in the equations in each method need to be recalibrated to make them applicable to climatic conditions of the study area in India. In the present study, FAO Modified Penman method was used as the standard method for evaluation and altering the coefficients in the above temperature-based ETr methods, such that these seven methods can then be used to determine the ETr in the selected region. The evaluation was first made using the original values of the coefficients involved in each equation. All the equations were recalibrated and the coefficients in each method were calculated afresh to be appropriate to the climatic data of the study area in India. The results show that, large bias existed when the original coefficients were used for the determination of ETr. Regression equations were developed to correct the differences in magnitude of evapotranspiration. When recalibrated coefficients were substituted, all the seven methods improved the estimation of the ETr for the region. With properly recalibrated values of the coefficients, Blaney-Criddle, Thronthwaite, and Hamon methods can be recommended for estimating ETr in the study region, as far as temperature-based methods are concerned. 2007-01-01T00:00:00Z http://dspace.library.iitb.ac.in/jspui/handle/100/14414 Title: Inter-comparison of radiation -based reference crop evapotranspiration methods Authors: Jothiprakash, V; Devamane, M.G; Sasireka, K. Abstract: This paper investigates the evaluation and inter comparison of evapotranspiration models with data from a station in Tamil Nadu, India. In the present study cross comparison of the best or representative equation forms selected from each category namely (1) temperature-based methods, and (2) radiation-based methods ware made along with FAO Modified Penman method. Six representative empirical ETr equation selected from the two categories, namely Blaney-Criddly, Hamon, and Kharrufa (temperature-based), Doorenbos and Puitt, Jensen-Haise, and McGuinness and Bordne (radiation-based) were evaluated and compared. All the equations are recalibrated and the constants in each equation are redefined for the data from the selected station. The result shows that, large bias existed when the original constants were used for the determination of ETr. Regression equations were developed to correct the differences in magnitude of evapotranspiration. When recalibrated constant values were substituted for the original constant values, all the six methods have improved in the estimation of the ETr for the region. Based on the closeness in ETr value to that of FAO Modified Penman method and r2 value, radiation-based methods namely Doorenbos-Pruitt and Jensen-Haise can be recommended for estimating ETr in the study area than using temperature-based methods. 2008-01-01T00:00:00Z http://dspace.library.iitb.ac.in/jspui/handle/100/14413 Title: Stochastic and Artificial Neural Network Models for Reservoir Inflow Prediction Authors: Kote, A. S; Jothiprakash, V Abstract: The performance ofartificial neural network (ANN) model was evaluated by applying it to the observed time series of Pawana reservoir in Upper Bhima River Basin, Maharashtra. The ANN model results were compared with conventional univariate auto regressive integrated moving average (ARIMA) models. Suitability of time lagged recurrent networks (TLRN) with time delay, gamma and laguarre memory structures was investigated for predicting seasonal (June to October) reservoir inflow with a monthly time step. The performance of back propagation through time (BPTT) algorithm trained networks for various inputs was compared with genetic algorithm (GA) trained networks. Due to large variation in the observed time series, transformation of the observed series to normal distribution was also tried and found that the network predicted better. The validation of the models was performed using comparison of the principal statistics, goodness-of-fit measures, time series and scatter plots. Encouraging results indicated that the logarithmic transformed, BPTT trained TLRN resulted in better and reliable forecasts of high and low inflows (extreme) compared to GA trained neural networks as well as ARIMA models. 2009-01-01T00:00:00Z