Enhancing Air Quality Monitoring Through Spatial Classification in Central Zone of Peninsular Malaysia Using Artifical Neural Network as Prediction Tools

Abstract

Ambient air monitoring plays a crucial role in the effective implementation of air quality management systems. This practice entails systematically and over a long period assessing and quantifying specific pollutants in the outdoor environment. However, the high cost of acquiring sufficient equipment for comprehensive air monitoring poses a challenge. Thus, this study proposes that spatial classification could be a viable approach to reducing monitoring stations while still obtaining adequate air monitoring data. The objective of this study was to examine the predictive performance of artificial neural networks (ANNs) in spatial classification to support air quality monitoring. By implementing ANN in this study, the MLP-FF-ANN model successfully distinguished air quality samples in the HPC, MPC, and LPC regions. Particularly notable were the positive outcomes achieved with a configuration of ten hidden nodes, resulting in an R2 value of 0.7982, as well as the lowest RMSE (0.3799) and MR (0.1950). Additionally, the MLP-FF-ANN model demonstrated commendable performance, achieving an average correct classification rate of 76.38%. These findings suggest that air quality monitoring based on clustered data can effectively maintain data quality.