arXiv subjects

Surajit Chattopadhyay

Publications and source records attributed to Surajit Chattopadhyay.

98 records · Page 6Linked to original sources

arXiv2007

A Soft Computing technique in rainfall forecasting

Soft Computing techniques have opened up new avenues to the forecasters of complex systems. Atmosphere is a complex system and all the atmospheric parameters carry different degrees of complexity within themselves. Endeavor of the present research is to adopt Artificial Neural Network as a Soft Computing technique to anticipate the average monsoon rainfall over India. After a rigorous study, the said Neural Net technique has been found adroit and results have been compared with those obtained through conventional techniques.

nlin.AO↗

arXiv2006

Anticipation of summer monsoon rainfall over India by Artificial Neural Network with Conjugate Gradient Descent Learning

Present study aims to develop a predictive model for the average summer monsoon rainfall amount over India. The dataset made available by the Indian Institute of Tropical Meteorology, Pune, has been explored. To develop the predictive model, Backpropagation method with Conjugate Gradient Descent algorithm has been implemented. The Neural Net model with the said algorithm has been learned thrice to reach a good result. After three runs of the model, it is found that a high prediction yield is available. Ultimately, Artificial Neural Network with Conjugate Gradient Descent based Backpropagation algorithm is found to be skillful in predicting average summer monsoon rainfall amount over India.

nlin.AO↗

arXiv2006

A probe into the chaotic nature of total ozone time series by Correlation Dimension method

Present paper deals with mean monthly total ozone concentration over Arosa, Switzerland. The basic rationale is to investigate the existence of chaos within the relevant time series. Method of correlation dimension is adopted here as the research methodology. After a rigorous investigation a low dimensional chaos is identified within the time series pertaining to mean monthly total ozone concentration over Arosa, Switzerland.

nlin.CD↗

arXiv2006

Multilayered feed forward Artificial Neural Network model to predict the average summer-monsoon rainfall in India

In the present research, possibility of predicting average summer-monsoon rainfall over India has been analyzed through Artificial Neural Network models. In formulating the Artificial Neural Network based predictive model, three layered networks have been constructed with sigmoid non-linearity. The models under study are different in the number of hidden neurons. After a thorough training and test procedure, neural net with three nodes in the hidden layer is found to be the best predictive model.

nlin.AO↗

arXiv2006

Predicting Pre-monsoon Thunderstorms -A Statistical View through Propositional Logic

Thunderstorms very close to a monsoon and not so close to a monsoon are considered in this analysis. Some important predictors are considered. Pearson Correlation Coefficient and lag-1 autocorrelation coefficients are calculated to create necessary universes of discourse for prepositional logic. The purpose is to make regression analysis more convenient for prediction of the pre-monsoon thunderstorm weather phenomenon.

nlin.AO↗

arXiv2006

Soft Computing Techniques in combating the complexity of the atmosphere- a review

The purpose of the present review is to discuss the role of Soft Computing techniques in understanding the complexity associated with atmospheric phenomena and thus developing predictive models. Problems in atmospheric data analysis are discussed in brief and the relevance of Soft Computing to the atmospheric data analysis and their advantage over the conventional methods are also conversed. Applicability of different Soft Computing techniques is precisely discussed. In the last section, up-to-date literature appraisal is incorporated.

nlin.AO↗

arXiv2006

Artificial Neural Network to predict mean monthly total ozone in Arosa, Switzerland

Present study deals with the mean monthly total ozone time series over Arosa, Switzerland. The study period is 1932-1971. First of all, the total ozone time series has been identified as a complex system and then Artificial Neural Networks models in the form of Multilayer Perceptron with back propagation learning have been developed. The models are Single-hidden-layer and Two-hidden-layer Perceptrons with sigmoid activation function. After sequential learning with learning rate 0.9 the peak total ozone period (February-May) concentrations of mean monthly total ozone have been predicted by the two neural net models. After training and validation, both of the models are found skillful. But, Two-hidden-layer Perceptron is found to be more adroit in predicting the mean monthly total ozone concentrations over the aforesaid period.

nlin.AO↗

arXiv2006

An Artificial Neural Net approach to forecast the population of India

Present paper endeavors to forecast the population of India through Artificial Neural Network. A non-linear Artificial Neural Net model has been developed and the prediction has been found to be sufficiently accurate. It has been found that the model is performing more efficiently in predicting female population than the male population. Results have been presented graphically.

nlin.AO↗