A neural network model for three-hours-ahead prediction of ozone concentration in the urban area of Palermo

Abstract

The purpose of this study is to use a recurrent neural network (Jordan model) to forecast ozone concentrations (O 3 ) with a short lead-time (1-3h) in the lower atmosphere. The network has been trained using a time series that was recorded between January 1 st 2003 to December 31 st 2003 and at two monitoring stations in Palermo (Italy). Each input pattern is composed of twelve (hourly) values: wind direction and intensity, barometric pressure, and ambient temperature; respectively gathered at the meteorological stations in Bellolampo, Boccadifalco and Castelnuovo. Ozone predictions are notoriously complex when using either deterministic or stochastic models which explains why this model was developed using a Neural Network. Neural Networks possess the ability to learn about nonlinear relationships between the variables used. The model developed is a potential tool for the predictions air quality parameters and it is superior to the traditional stochastic model.

A novel model based on SOM2W network for listed reality companies analysis

“…At present, there are many problems that are difficult or incapable to solve using usual methods have been solved by applying artificial neural network, which accelerates greatly the progress of science and the development of society [2][3][4][5][6][7][8][9][10]. Recently, there are some economists, mathematicians, politicians and computer experts who are devoting their attention to use artificial neural network method to solve some problems of finance.…”

An Immune Algorithm-Based Atmospheric Quality Assessment Model and Its Applications

“…In general, it is difficult to provide directly scientific basis for environmental renovation planning. Some researchers have explored some methods based on artificial intelligence and applied them to the field of atmospheric pollution assessment [1][2][3][4][5][6][7][8].…”