An information theoretic approach based on Shannon entropy is adopted in this study to discern the influence of pre-monsoon thunderstorm on some surface parameters. A few parameters associated with pre-monsoon thunderstorms over a part of east and northeast India are considered. Maximization of Shannon entropy is employed to test the relative contributions of these parameters in creating this weather phenomenon. It follows as a consequence of this information theoretic approach that surface temperature is the most important parameter among those considered. Finally, artificial neural network in the form of multilayer perceptron with backpropagation learning is attempted to develop predictive model for surface temperature. © 2018, Springer Science+Business Media B.V., part of Springer Nature.

SUBRATA MIDYA

Atmospheric Science

S CHATTOPADHYAY

G CHATTOPADHYAY

University of Calcutta (informally known as Calcutta University or CU) is a collegiate public state university located in Kolkata, West Bengal, India.&nbsp;Within India it is recognized as a &quot;Five-Star University&quot; and accredited &quot;A&quot; Grade by National Assessment and Accreditation Council.

&nbsp;

The University of Calcutta has secured the Fifth position among the Universities of India in the prestigious &quot;Indian University Ranking 2019&quot; list, released by the NIRF of the Ministry of Human Resource Development, Government of India.

&nbsp;

It was established on 24 January 1857, and was one of the first institutions in Asia to be established as a multidisciplinary and Western-style university. Its alumni and faculty include several heads of state, heads of government, social reformers, prominent artists, only academy award winner and Dirac medal winner in India, many Fellows of the Royal Society and five Nobel laureates as of 2019 which is highest in South Asia.

University Of Calcutta

Natural Hazards

Autoregressive neural network (AR-NN) models of various orders have been generated in this work for the daily total ozone (TO) time series over Kolkata (22.56°N, 88.5°E). Artificial neural network in the form of multilayer perceptron (MLP) is implemented in order to generate the AR-NN models of orders varying from 1 to 13. An extensive variable selection method through multiple linear regression (MLR) is implemented while developing the AR-NNs. The MLPs are characterized by sigmoid non-linearity. The optimum size of the hidden layer is identified in each model and prediction are produced by validating it over the test cases using the coefficient of determination (R2) and Willmott's index (WI). It is observed that AR-NN model of order 7 having 6 nodes in the hidden layer has maximum prediction capacity. It is further observed that any increase in the orders of AR-NN leads to less accurate prediction. © 2010 Versita Warsaw and Springer-Verlag Wien.

Acta Geophysica

Identification of the best architecture of a multilayer perceptron in modeling daily total ozone concentration over Kolkata, India

The association between the monthly total ozone concentration and monthly maximum temperature over Kolkata (22.56°N, 88.30° E), India, has been explored in this paper. For this, the predictability of monthly maximum temperature based on the total ozone as predictor is investigated using Artificial Neural Network. The presence of persistence and similar cyclic patterns are revealed through autocorrelation and cross-correlation coefficients. Common cycles of length 12 and 6 have been identified through periodogram. Hence, a predictive model has been generated by Artificial Neural Network in the form of Multi Layer Perceptron (MLP) using scaled conjugate gradient learning with sigmoid non-linearity. After training and testing the network, an MLP with total ozone of month n as predictor and maximum temperature of month (n+. 1) as the target output is found as the best model. Performance of the model has been judged statistically. Finally, the MLP model has been compared with linear and non-linear regressions and the efficiency of MLP has been established over the regression models. © 2011.

Comptes Rendus - Geoscience

A neurocomputing approach to the forecasting of monthly maximum temperature over Kolkata, India using total ozone concentration as predictor

The present paper attempts to identify the type of low level clouds preferred for the genesis of severe thunderstorms over Kolkata (22° 32′, 88° 20′) during the transition period of pre-monsoon season (April-May). Soft computing technique in the form of Rough Set Theory is adopted for recognizing the pattern of low level clouds. Different possible types of clouds are explored with ten years data in the present study for the occurrence of severe thunderstorms over Kolkata confined within the northeastern part of India (20° N to 24 ° N latitude, 85 ° E to 93 ° E longitude). The results show that for the occurrence of severe thunderstorms over Kolkata the preferred type of low level cloud is cumulonimbus and the transition from stratocumulus to cumulonimbus is a significant conversion of cloud type. The result further reveals that the formation of cumulonimbus cloud at 06 GMT is an extremely favorable condition for the genesis of the severe thunderstorms over Kolkata during the pre-monsoon season. © 2007 Elsevier B.V. All rights reserved.

Atmospheric Research

Preferred type of cloud in the genesis of severe thunderstorms - A soft computing approach

The purpose of the present study is to investigate the existence of deterministic chaos in the time series of occurrence or non-occurrence of severe thunderstorms of the pre-monsoon season over the Northeastern part of India. Results from the current study reveal the existence of chaos in the relevant time series. The corresponding predictabilities are also computed quantitatively. The study recommends that the formulation of numerical weather prediction models for forecasting the occurrence of this high frequency meso-scale convective system must take into account the intrinsic chaos. © World Scientific Publishing Company.

Advances in Complex Systems

Predictability of chaos inherent in the occurrence of severe thunderstorms

A Feed forward multi-layered artificial neural network model is designed in this paper to estimate the maximum surface temperature and relative humidity needed for the genesis of severe thunderstorms over Calcutta (22° 32′, 88° 20′). The performance of the model is found to be adroit. It has, thus, been discerned that the neural network technique is of great use in forecasting the occurrence of high frequency small-scale weather systems like Severe Local Storms. Filing up the missing values and extension of time series is observed to be possible with this model. Prediction error is computed and compared for single layer network and one hidden layer neural nets. Result reveals the efficiency of the one hidden layer neural net. © Springer-Verlag 2004.

Journal	Data powered by TypesetNatural Hazards
Publisher	Data powered by TypesetSpringer Netherlands
ISSN	0921-030X
Open Access	No