COMPUTATIONAL INTELLIGENCE ESTIMATION OF NATURAL BACKGROUND OZONE LEVEL AND ITS DISTRIBUTION FOR AIR QUALITY MODELLING AND EMISSION CONTROL Herman Wahid 1 *, Q. P. Ha 2 , and H. Nguyen Duc 3 1 Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Malaysia/ Faculty of Engineering and IT, University of Technology, Sydney, Australia 2 Faculty of Engineering and IT, University of Technology, Sydney, Australia 3 Department of Environment, Water and Climate Change NSW, Australia * Corresponding author (hbinwahi@eng.uts.edu.au ) ABSTRACT: Background ozone, known as the ozone that occurs in the troposphere as a result of biogenic emissions without photochemical influences, has a close relationship with human health risk. The prediction of the background ozone level by an air quality model could cover a wider region, whereas a measurement method can only record at monitoring sites. The problem is that simulation with deterministic models is quite tedious because of the nonlinear nature of some particular chemical reactions involved in the pollutant formulation. In this work, we present a reliable method for determination of the background ozone using the ambient measurement data. Our proposed definition can be used to determine the background level at any part of the globe and in any seasons without relying on data obtained at remote sites. A statistical model approach will be used for the estimation of the background ozone concentration, and a method for extrapolating the site data will be utilised to approximate the spatial distribution on the region. The proposed method will be applied in the Sydney basin to evaluate its effectiveness in background ozone determination. The results show the advantage of the proposed approach as a globally generic and computationally efficient way for the background ozone estimation with a reasonable accuracy. Keywords: Background Ozone, Air Quality Modelling, Radial Basis Function, Spatial Distribution 1. INTRODUCTION Natural background ozone level (BOL) can be referred to as the concentration of ozone (O 3 ) that is formed from only natural emissions (i.e. biogenic or geogenic contaminations) of the precursors in the absence of the local anthropogenic influences. Biogenic emissions (e.g. oxides of nitrogen, NO x ) are generated from the natural sources such as plants, trees, and wildfires, whereas geogenic emissions may come from lightning and soil conditions. Unfortunately, contributions of the background ozone at most places may include a combination of local natural emissions, photochemical effects as well as long-range transports from other regions. Thus, it is difficult to distinguish between the ozone that is produced by the anthropogenic and natural effects. One method to determine the BOL is by measuring the ozone concentration at the clean pristine sites of a rural area, considered as a clean environment. This method was widely used in the literature, see e.g., Saitanis [1] and Oltmans et al. [2]. However, Matveev et al. [3] reported that measurements at remote rural sites do not necessarily represent background levels since local pollutants can sometimes be re-circulated. The US EPA refers the BOL as the ozone concentrations that would occur in United States (US) in the absence of anthropogenic emissions in Continental North America, but including the contributions from the natural sources everywhere in the world [4]. The BOL in the US is estimated by using modelling software called GEOS- S33-1 1157