Forecasting Daily Source Air Quality Using Multivariate Statistical Analysis and Radial Basis Function Networks

Abstract

It is vital to forecast gas and particle matter concentrations and emission rates (GPCER) from livestock production facilities to assess the impact of airborne pollutants on human health, ecological environment, and global warming. Modeling source air quality is a complex process because of abundant nonlinear interactions between GPCER and other factors. The objective of this study was to introduce statistical methods and radial basis function (RBF) neural network to predict daily source air quality in Iowa swine deep-pit finishing buildings. The results show that four variables (outdoor and indoor temperature, animal units, and ventilation rates) were identified as relative important model inputs using statistical methods. It can be further demonstrated that only two factors, the environment factor and the animal factor, were capable of explaining more than 94% of the total variability after performing principal component analysis. The introduction of fewer uncorrelated variables to the neural network would result in the reduction of the model structure complexity, minimize computation cost, and eliminate model overfitting problems. The obtained results of RBF network prediction were in good agreement with the actual measurements, with values of the correlation coefficient between 0.741 and 0.995 and very low values of systemic performance indexes for all the models. The good results indicated the RBF network could be trained to model these highly nonlinear relationships. Thus, the RBF neural network technology combined with multivariate statistical methods is a promising tool for air pollutant emissions modeling.

Predicting Atmospheric Concentrations of Benzene in the Southeast of Tehran using Artificial Neural Network

“…Therefore, we could not compare the results of our work with similar studies. However, the result of our work indicates the RBF neural network prediction is much closer to the observed data than the MLP neural network, which is similar to the results of Sun et al (2008) and Haiming and Xiaoxiao (2013). The results of the work may be applicable for short time prediction of benzene because of the duration of the data collection.…”

Improving Ammonia Emission Modeling and Inventories by Data Mining and Intelligent Interpretation of the National Air Emission Monitoring Study Database

“…A two-layer neural network topology [48,54] will be adapted (Figure 2). Regression will be run to find functions which model the data or data subsets with the least error.…”

Development and Comparison of Backpropagation and Generalized Regression Neural Network Models to Predict Diurnal and Seasonal Gas and PM10 Concentrations and Emissions from Swine Buildings

“…The data set presented diurnal (hourly) and seasonal (16 continuous measurement months) variations of gas and PM 10 concentrations and emission rates. A multivariate statistical analysis (Sun et al, 2008b) was conducted, and from this analysis it was determined that four main variables were significant contributors to the GPCER models. These four input variables include: outdoor temperature (T out ), animal units (AU), total building ventilation rate (VR), and indoor temperature (T in ).…”