WIT Press

Short-term Forecasting Of Ozone By Means Of A Bi-directional Associative Memory (Mexico City: Case Study)

Price

Free (open access)

Paper DOI

10.2495/AI940101

Volume

6

Pages

8

Published

1994

Size

723 kb

Author(s)

J.C. Ruiz-Suarez, R. Smith-Perez, J. Torres-Jimenez & L.G. Ruiz-Suarez

Abstract

Short-term forecasting of ozone by means of a bi-directional associative memory (Mexico City: case study) J.C. Ruiz-Suarez," R. Smith-Perez," J. Torres-Jimenez" & L.G. Ruiz-Suarez^ "Institute Tecnologico y de Estudios Superiores de Monterrey, Campus-Morelos, Apdo. Postal 99-C, Cuernavaca, Morelos 62050, Mexico ^Centro de Ciencias de la Atmosfera, Universidad Nacional A. de Mexico, Circuito Exterior, Cd. m, M&zco D.F. 0^5JO, Mezzco ABSTRACT In this work we report preliminary results of a study aiming to set up an intel- ligent tool to perform ozone forecasting in the very polluted atmosphere of Mexico City. This tool is based in the paradigm of neural nets. Although our project involves several neural net models, this work presents results obtained by using only one of them, the Bidirectional Associative Memory (BAM), which in turn behaves as a heteroassociative content addressable memory (CAM). We analyse and preprocess daily patterns of meteorological varia

Keywords