Air quality prediction using optimal neural networks with stochastic variables

TL;DR

This paper introduces a method to identify a minimal set of stochastic variables that retain predictive power for air quality forecasting, enhancing neural network efficiency and potentially benefiting other geophysical applications.

Contribution

The study presents a novel approach to select optimal stochastic variables for neural network inputs, reducing complexity while maintaining accuracy in air quality prediction.

Findings

Significant reduction in input variables needed for neural networks

Maintained predictive accuracy with fewer variables

Potential for broader applications in geophysical forecasting

Abstract

We apply recent methods in stochastic data analysis for discovering a set of few stochastic variables that represent the relevant information on a multivariate stochastic system, used as input for artificial neural networks models for air quality forecast. We show that using these derived variables as input variables for training the neural networks it is possible to significantly reduce the amount of input variables necessary for the neural network model, without considerably changing the predictive power of the model. The reduced set of variables including these derived variables is therefore proposed as optimal variable set for training neural networks models in forecasting geophysical and weather properties. Finally, we briefly discuss other possible applications of such optimized neural network models.