Predicting PM2.5 Concentrations at a Regional Background Station Using Second Order Self-Organizing Fuzzy Neural Network

Abstract

This study aims to develop a second order self-organizing fuzzy neural network (SOFNN) to predict the hourly concentrations of fine particulate matter (PM 2.5) for the next 24 h at a regional background station called Shangdianzi (SDZ) in China from 14 to 23 January 2010. The structure of the SOFNN was automatically adjusted according to the sensitivity analysis (SA) of model output and the parameter-learning phase was performed applying a second order gradient (SOG) algorithm. Principal component analysis (PCA) was employed to select the dominating factors for PM 2.5 concentrations as the input variables for the SOFNN. It was found that the dominating variables (relative humidity (RH), pressure (Pre), aerosol optical depth (AOD), wind speed (WS) and wind direction (WD)) extracted by PCA agreed well with the characteristics of PM 2.5 at SDZ where the PM 2.5 concentrations were heavily affected by meteorological parameters and were closely related to AOD. The forecasting results showed that the proposed SOG-SASOFNN performed better than other models with higher coefficient of determination (R 2) during both training phase and test phase (0.89 and 0.84, respectively) in predicting PM 2.5 concentrations at SDZ. In conclusion, the developed SOG-SASOFNN provided satisfying results for modeling the hourly distribution of PM 2.5 at SDZ during the studied period.

Application of Artificial Neural Networks in the Prediction of PM10 Levels in the Winter Months: A Case Study in the Tricity Agglomeration, Poland

“…R 2 is considered the basic measure of matching the model to the observed data points; the value range is from 0-1. Its closeness to 1.0 indicates the greater explained variance [23,26,29,31,47]. The indicators used were calculated according to Equations (1)- 4:…”

“…Researchers have used statistical modelling techniques and machine learning methods to analyse, engage the proper variables within modelling framework, and, finally, predict the concentrations of particulate matter. The most preferred approaches are multiple linear regression, stepwise regression, artificial neural networks, principal component analysis, and clustering methods [21][22][23][24][25][26][27][28][29]. It should be noted that a number of studies have compared the performance of various modelling approaches to determine the best model for the prediction of PM 10 in different locations.…”

Prediction of Air Pollution Concentration Based on mRMR and Echo State Network

“…The 5 variables in the optimal subset are expressed as bold in the table. As shown in Table 1, the delay time for the obtained optimal subset is [8,8,6,4,4], and the embedding dimension is [2,2,2,4,4] for PM2.5, PM10, CO, H and WS respectively.…”

“…For a long time, many scholars have conducted in-depth research on air pollution. At the same time, a variety of predictive models have been proposed, such as autoregressive integrated moving average model [5], support vector machine [5], multiple linear regression model [6], neural networks [7,8], and so on [9]. All of them have been applied to predict air pollution concentration.…”

Prediction of $${\mathrm{PM}}_{2.5}$$ concentration based on multi-source data and self-organizing fuzzy neural network

“…A large number of people suffer from various diseases or even die every year throughout the world due to the polluted air. At the same time, poor air quality will affect people's travel and production activities [32]. Besides, the heavy pollution will not only affect the image of a city, but also cause unnecessary economic losses.…”