Indian Institute of Technology Kharagpur

About: Indian Institute of Technology Kharagpur is a education organization based out in Kharagpur, India. It is known for research contribution in the topics: Computer science & Dielectric. The organization has 16887 authors who have published 38658 publications receiving 714526 citations.

Temporal Trends in Estimates of Reference Evapotranspiration over India

Abstract: Evapotranspiration (ET) is likely to be greatly affected by global warming because of the dependence of ET on surface temperature. The increasing atmospheric concentration of carbon dioxide (C O2 ) and other greenhouse gases is expected to increase precipitation and evaporation proportionally. However, a few studies have shown a decreasing trend for evaporation over the last 50 years globally. In India, earlier works showed that there was a significant increasing temporal trend in surface temperature and a decreasing trend in grass reference ET (ETo). To study the temporal trend of ETo along with its regionwise spatial variation, 32 years (1971–2002) monthly meteorological data were collected for 133 selected stations evenly distributed over different agro-ecological regions (AERs) of India. ETo was estimated by the globally accepted Food and Agriculture Organization (FAO) Penman Monteith (PM) method (FAO-56 PM). These ETo values were then analyzed by a nonparametric Mann–Kendall (MK) test (with modified ...

River flow forecasting using recurrent neural networks

Abstract: Forecasting a hydrologic time series has been one of the most complicated tasks owing to the wide range of data, the uncertainties in the parameters influencing the time series and also due to the non availability of adequate data. Recently, Artificial Neural Networks (ANNs) have become quite popular in time series forecasting in various fields. This paper demonstrates the use of ANNs to forecast monthly river flows. Two different networks, namely the feed forward network and the recurrent neural network, have been chosen. The feed forward network is trained using the conventional back propagation algorithm with many improvements and the recurrent neural network is trained using the method of ordered partial derivatives. The selection of architecture and the training procedure for both the networks are presented. The selected ANN models were used to train and forecast the monthly flows of a river in India, with a catchment area of 5189 km2 up to the gauging site. The trained networks are used for both single step ahead and multiple step ahead forecasting. A comparative study of both networks indicates that the recurrent neural networks performed better than the feed forward networks. In addition, the size of the architecture and the training time required were less for the recurrent neural networks. The recurrent neural network gave better results for both single step ahead and multiple step ahead forecasting. Hence recurrent neural networks are recommended as a tool for river flow forecasting.