Pollutant Profile Estimation Using Unscented Kalman Filter
- 141 Downloads
In this paper, we develop an estimation model for carbon monoxide (CO) air pollution concentrations. CO is an important pollutant which is used to calculate an air quality index (AQI). AQI becomes less reliable as the proportion of data missing due to equipment failure and periods of calibration increases. This paper presents the Unscented Kalman filter (UKF) to predict missing data of atmospheric carbon monoxide concentrations using the time series data of monitoring stations.
KeywordsCarbon monoxide (CO) Unscented Kalman filter (UKF) Air quality index (AQI)
- 8.Hartikainen J, Särkkä S (2010) Kalman filtering and smoothing solutions to temporal Gaussian process regression models. In: 2010 IEEE international workshop on machine learning for signal processing, August 2010, pp. 379–384Google Scholar