Change Detection of Air Quality Time-Series Using the R Package Aqeval

Abstract

In this article, we introduce the R Air Quality Evaluation package AQEval. AQEval was developed for use by those tasked with the routine detection, characterisation and quantification of discrete changes in air quality time-series, such as identifying the impacts of air quality policy interventions. The main functions use break-point/segment (BP/S) methods to first detect (as break-points) and then characterise and quantify (as segments) discrete changes in air quality time-series. Here, the objective is to introduce the main AQEval functions that provide robust and conservative estimates of change for new users, and a work-flow of methods and work-horse functions for those looking to fine-tune methods, e.g. through BP/S model optimisation and environmental signal isolation methods such as deseasonalisation, deweathering, and background subtraction.

Keywords: R, AQEval, air quality time-series, change detection, break-point/segment