Monitoring and Forecasting Air Pollution Levels by Exploiting Satellite, Ground-Based, and Synoptic Data, Elaborated with Regression Models

Abstract

This paper presents some of the results of a project that aimed at the design and implementation of a system for the spatial mapping and forecasting the temporal evolution of air pollution from dust transport from the Sahara Desert into the eastern Mediterranean and secondarily from anthropogenic sources, focusing over Cyprus. Monitoring air pollution (aerosols) in near real-time is accomplished by using spaceborne and in situ platforms. The results of the development of a system for forecasting pollution levels in terms of particulate matter concentrations are presented. The aim of the present study is to utilize the recorded PM10 (particulate matter with aerodynamic diameter less than 10 μm) ground measurements, Aerosol Optical Depth retrievals from satellite, and the prevailing synoptic conditions established by Artificial Neural Networks, in order to develop regression models that will be able to predict the spatial and temporal variability of PM10 in Cyprus. The core of the forecasting system comprises an appropriately designed neural classification system which clusters synoptic maps, Aerosol Optical Depth data from the Aqua satellite, and ground measurements of particulate matter. By exploiting the above resources, statistical models for forecasting pollution levels were developed.

Forecasting air quality index considering socioeconomic indicators and meteorological factors: A data granularity perspective

“…Most of them rely on experienced experts and panel discussions to reach a consensus. In contrast, quantitative techniques depend more on time series, statistical regression, machine learning, and deep learning (Athira et al, 2018; Castelli et al, 2020; Freeman et al, 2018; Liu et al, 2019; Michaelides et al, 2017). Traditional forecasting usually depends on historical data without considering the causalities of influential predictors.…”

Untitled

“…measure of the amount of the depletion that a beam of solar radiation undergoes as it passes through the atmosphere. Michaelides et al (2017) analyzed satellite data with a resolution of 10 × 10 km.…”

Sub‐City Scale Hourly Air Quality Forecasting by Combining Models, Satellite Observations, and Ground Measurements

“…Much recent research has focused on 1‐km daily‐average surface PM 2.5 estimation combining similar data sources (Cleland et al., 2020 ; Danesh Yazdi et al., 2020 ; Just et al., 2020 ; Mhawish et al., 2020 ), with some research into hourly average concentration estimation (Jiang et al., 2021 ) and into forecasting daily averages (Zhang et al., 2020 ). Similar efforts include regional forecasting of coarse particulate matter (Michaelides et al., 2017 ) and global estimation of 8‐h maximum surface ozone concentrations (Chang et al., 2019 ) by combining model, satellite, and/or ground data.…”

“…Much recent research has focused on 1-km daily-average surface PM 2.5 estimation combining similar data sources (Cleland et al, 2020;Danesh Yazdi et al, 2020;Just et al, 2020;Mhawish et al, 2020), with some research into hourly average concentration estimation (Jiang et al, 2021) and into forecasting daily averages (Zhang et al, 2020). Similar efforts include regional forecasting of coarse particulate matter (Michaelides et al, 2017) and global estimation of 8-h maximum surface ozone concentrations (Chang et al, 2019) Building on this previous work, this study proposes and demonstrates an approach for using globally available atmospheric composition historical estimates and forecasts and satellite information together with localized surface measurements for generating sub-city-scale and hourly resolution estimates and near-term forecasts up to 24 h in advance of surface-level pollutant concentrations relevant for air quality. We make use of the Global Earth Observing System Composition Forecasting (GEOS-CF) atmospheric chemistry model system and satellite data from the TROPOspheric Monitoring Instrument, TROPOMI.…”