Autoregressive forecast of monthly total ozone concentration: A neurocomputing approach

Authors:
Goutami Chattopadhyay;Surajit Chattopadhyay
Affiliations:
Formerly, Department of Atmospheric Sciences, University of Calcutta, Kolkata 700019, India;Department of Computer Application, Pailan College of Management and Technology, Kolkata 700104, India
Venue:
Computers & Geosciences
Year:
2009

Citing 8
Cited 2

Accelerating neural network training using weight extrapolations

Neural Networks
Stationarity and stability of autoregressive neural network processes

Proceedings of the 1998 conference on Advances in neural information processing systems II
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
A probe into the chaotic nature of total ozone time series by correlation dimension method

Soft Computing - A Fusion of Foundations, Methodologies and Applications
Artificial neural network with backpropagation learning to predict mean monthly total ozone in Arosa, Switzerland

International Journal of Remote Sensing
Prediction of mean monthly total ozone time series-application of radial basis function network

International Journal of Remote Sensing
Fast generic selection of features for neural network classifiers

IEEE Transactions on Neural Networks
Quarterly Time-Series Forecasting With Neural Networks

IEEE Transactions on Neural Networks

Letters: Improving the prediction of average total ozone in column over the Iberian Peninsula using neural networks banks

Neurocomputing
Improvement of the multilayer perceptron for air quality modelling through an adaptive learning scheme

Computers & Geosciences

Quantified Score

Hi-index	0.00

Visualization

Abstract

The present study endeavors to generate autoregressive neural network (AR-NN) models to forecast the monthly total ozone concentration over Kolkata (22^o34', 88^o22'), India. The issues associated with the applicability of neural network to geophysical processes are discussed. The autocorrelation structure of the monthly total ozone time series is investigated, and stationarity of the time series is established through the periodogram. From various autoregressive moving average (ARMA) and autoregressive models fit to the time series, the autoregressive model of order 10 is identified as the best. Subsequently, 10 autoregressive neural network (AR-NN) models are generated; the 10th order autoregressive neural network model with extensive input variable selection performs the best among all the competitive models in forecasting the monthly total ozone concentration over the study zone.