Air Quality Prediction Based on Singular Spectrum Analysis and Artificial Neural Networks

Javier Linkolk López‐Gonzales; Rodrigo Salas; Daira Velandia; Paulo Canas Rodrigues

doi:10.3390/e26121062

Air Quality Prediction Based on Singular Spectrum Analysis and Artificial Neural Networks

Author(s)

Javier Linkolk López‐Gonzales

Rodrigo Salas

Daira Velandia

Paulo Canas Rodrigues

Date Issued

6 de diciembre de 2024

Type

Article

Volume

26

Issue

12

Start Page

1062

End Page

1062

DOI

10.3390/e26121062

Abstract

Singular spectrum analysis is a powerful nonparametric technique used to decompose the original time series into a set of components that can be interpreted as trend, seasonal, and noise. For their part, neural networks are a family of information-processing techniques capable of approximating highly nonlinear functions. This study proposes to improve the precision in the prediction of air quality. For this purpose, a hybrid adaptation is considered. It is based on an integration of the singular spectrum analysis and the recurrent neural network long short-term memory; the SSA is applied to the original time series to split signal and noise, which are then predicted separately and added together to obtain the final forecasts. This hybrid method provided better performance when compared with other methods.