A neural network-based method for modeling PM 2.5 measurements obtained from the surface particulate matter network

Abstract

Air pollution is a global problem; hence, many countries devoted lots of resources towards its study and possible eradication. The major parameter indicator for air quality is the particulate matter (PM). These particles, especially PM 2.5 , are injurious to health either under high concentration levels or after a long-term exposure. PM 2.5 particles are known to cause lung and respiratory diseases, cardiovascular diseases, and even cancer. In this research, artificial neural networks were used to train PM 2.5 measurements obtained from the Surface Particulate Matter Network (SPARTAN). The training was done using inputs that indicate time series of the measurements and the prevailing atmospheric conditions. The developed models were used to estimate PM 2.5 over a sub-Saharan site in Ilorin. Our study considered meteorological parameters and aerosol optical depth (AOD) as inputs for the neural networks. The targets are PM 2.5 measurements obtained from SPARTAN. Our models showed very high correlation with measured data. Apart from the data generated using model p which has a correlation of 0.0009, the correlation R 2 for other models ranges from 0.59 to 0.95) which has a good performance. The model PRB estimated both low and high PM better while others either under or over predict emission scenarios.

A median absolute deviation-neural network (MAD-NN) method for atmospheric temperature data cleaning

“…The feedback forward back-propagation neural network training technique [10 , 11] was used. In recent times, previous studies by [12] , [13] , [14] have also used neural networks to train atmospheric dataset collected from the region, and their results indicate that neural networks are good candidates for atmospheric modeling. In particular, [15] posits that the neural network approaches are more accurate than traditional, regression-based approaches.…”