Time-series forecasting of pollutant concentration levels using particle swarm optimization and artificial neural networks

Abstract

Recebido em 1/8/12; aceito em 8/2/13; publicado na web em 4/6/13This study evaluates the application of an intelligent hybrid system for time-series forecasting of atmospheric pollutant concentration levels. The proposed method consists of an artificial neural network combined with a particle swarm optimization algorithm. The method not only searches relevant time lags for the correct characterization of the time series, but also determines the best neural network architecture. An experimental analysis is performed using four real time series and the results are shown in terms of six performance measures. The experimental results demonstrate that the proposed methodology achieves a fair prediction of the presented pollutant time series by using compact networks.

A Methodology to Increase the Accuracy of Particulate Matter Predictors Based on Time Decomposition

“…In this work, we used four different neural models in the framework depicted in Figure 1: multilayer perceptron (MLP), radial basis function network (RBF), extreme learning machines (ELM), and echo state networks. These models were selected due to their extensive use in time series forecasting [8][9][10][11][12][13][14][15][16]28,46,[54][55][56]. These ANN architectures can approximate any nonlinear, continuous, limited, and differentiable function, being universal approximators [57].…”

“…In this context, we highlight the forecasting systems based on artificial neural networks (ANNs), due to the excellent performances demonstrated in the literature [8][9][10][11][12][13][14][15]. These systems generally employ two data-driven approaches for ANN adjustment: the use of only previous (historical) data of PM concentration [12,13,16,17] or the use of the historical data of PM jointly with related features, such as temperature, relative humidity, wind speed and direction, and others [8][9][10][11]14,[18][19][20][21].…”

“…Traditionally, systems based on ANN use only one forecasting model for the entire series [8][9][10][12][13][14][15][16]. However, some works [19][20][21][22][23][24][25][26][27][28] address a set of predictors for a specific part of the series.…”

A Particulate Matter Concentration Prediction Model Based on Long Short-Term Memory and an Artificial Neural Network

“…In addition, a model considering various variables was proposed by combining ensemble learning and multi-layer perceptron (MLP) [ 16 , 17 , 18 , 19 , 20 ]. Many diverse studies have been conducted, in which particle swarms have been optimized using swarm intelligence in combination with ANNs [ 21 , 22 , 23 , 24 , 25 ]. In the field of residual modeling, multiple studies have been conducted on hybrid models, in order to improve the performance of predicting PM concentration levels [ 26 , 27 ].…”

Modelado De Partículas Pm10 Y PM2.5 Mediante Redes Neuronales Artificiales Sobre Clima Tropical De San Francisco De Campeche, México

“…[1][2][3] Las partículas atmosféricas han cobrado recientemente un notable interés debido a los efectos adversos generados en la salud del ser humano, principalmente aquellas con diámetro aerodinámico menor que 10 µm y 2.5 µm. Tanto la Agencia de Protección al Ambiente (US-EPA), y la Organización Mundial de la Salud (WHO), advierten la importancia de la medición de este contaminante en el aire, debido a los efectos adversos en las poblaciones humanas.…”