A Surrogate-Based Optimization Methodology for the Optimal Design of an Air Quality Monitoring Network

Abstract

A surrogate-based optimization methodology was proposed for identifying and determining the optimal location and configuration of an air quality monitoring network (AQMN) in an industrial area for different pollutants such as sulfur dioxide (SO2), nitrogen oxide (NOx), and carbon monoxide (CO). Within the framework of the described methodology, an optimal AQMN design was proposed to assess the violation and pattern scores for each pollutant. For this purpose, a criterion for assessing the allocation of monitoring stations was developed by applying a utility function that could describe the spatial coverage of the network and its ability to detect violations of standards for multiple pollutants. An air dispersion model based on the multiple cell approach was used to create monthly spatial distributions for the concentrations of the pollutants emitted from different sources. The data was used to develop the surrogate models. The proposed methodology was applied to a network of existing refinery stacks, and the locations of monitoring stations and their area coverage percentage were obtained. Results clearly indicated that the proposed methodology was successful in designing AQMNs and could be used for as many stations as required.