Neural network forecasting of air pollutants hourly concentrations using optimised temporal averages of meteorological variables and pollutant concentrations

Hrust, Lovro; Klaić, Zvjezdana Bencetić; Križan, Josip; Antonić, Oleg; Hercog, Predrag

doi:10.1016/j.atmosenv.2009.07.048

Cited by 99 publications

(51 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additionally, the neural network approach has been widely used in atmospheric and air quality modeling studies [27,28] and demonstrated to be effective for air pollution estimation and prediction. In this study we analyzed and compared the PM10-AOD relationship using four models: 1) univariate linear regression model (UV); 2) multivariate linear regression model with first-order effects (MV1); 3) multivariate linear regression model with first and second-order effects of the independent variables (MV2) and 4) artificial neural network (ANN).…”

Section: Development Of Empirical Models (Univariate Model Multivarimentioning

confidence: 99%

Relationship between MODIS based Aerosol Optical Depth and PM10 over Croatia

et al. 2014

Self Cite

View full text Add to dashboard Cite

This study analyzes the relationship between Aerosol Optical Depth (AOD) obtained from Terra and Aqua Moderate Resolution Imaging Spectroradiometer (MODIS) and ground-based PM10 mass concentration distribution over a period of 5 years (2008)(2009)(2010)(2011)(2012), and investigates the applicability of satellite AOD data for ground PM10 mapping for the Croatian territory. Many studies have shown that satellite AOD data are correlated to groundbased PM mass concentration. However, the relationship between AOD and PM is not explicit and there are unknowns that cause uncertainties in this relationship. The relationship between MODIS AOD and ground-based PM10 has been studied on the basis of a large data set where daily averaged PM10 data from the 12 air quality stations across Croatia over the 5 year period are correlated with AODs retrieved from MODIS Terra and Aqua. A database was developed to associate coincident MODIS AOD (independent) and PM10 data (dependent variable). Additional tested independent variables (predictors, estimators) included season, cloud fraction, and meteorological parameters -including temperature, air pressure, relative humidity, wind speed, wind direction, as well as planetary boundary layer height -using meteorological data from WRF (Weather Research and Forecast) model. It has been found that 1) a univariate linear regression model fails at explaining the data variability well which suggests nonlinearity of the AOD-PM10 relationship, and 2) explanation of data variability can be improved with multivariate linear modeling and a neural network approach, using additional independent variables.

show abstract

Section: Development Of Empirical Models (Univariate Model Multivarimentioning

confidence: 99%

Relationship between MODIS based Aerosol Optical Depth and PM10 over Croatia

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…Easy to use and implement, simplified physics and chemistry equations systems were developed and tuned in order to estimate a probability of pollution event. This is achieved by using only meteorological parameters such as mean wind speed, solar radiation and temperature (Hrust et al, 2009). Using only few equations, these codes allowed a fast computation (a major constraint for forecast systems).…”

Section: Introductionmentioning

confidence: 99%

Atmospheric composition forecasting in Europe

Menut

Bessagnet

2010

Ann. Geophys.

View full text Add to dashboard Cite

Abstract.The atmospheric composition is a societal issue and, following new European directives, its forecast is now recommended to quantify the air quality. It concerns both gaseous and particles species, identified as potential problems for health. In Europe, numerical systems providing daily air quality forecasts are numerous and, mostly, operated by universities. Following recent European research projects (GEMS, PROMOTE), an organization of the air quality forecast is currently under development. But for the moment, many platforms exist, each of them with strengths and weaknesses. This overview paper presents all existing systems in Europe and try to identify the main remaining gaps in the air quality forecast knowledge. As modeling systems are now able to reasonably forecast gaseous species, and in a lesser extent aerosols, the future directions would concern the use of these systems with ensemble approaches and satellite data assimilation. If numerous improvements were recently done on emissions and chemistry knowledge, improvements are still needed especially concerning meteorology, which remains a weak point of forecast systems. Future directions will also concern the use of these forecast tools to better understand and quantify the air pollution impact on health.

show abstract

“…This suggests that PM 1 is governed by a large number of comparably important processes occurring at different spatio-temporal scales, which is in accordance with previous findings for outdoor PM 10 (Hrust et al, 2009 Ispitali smo vezu između jednominutnih srednjaka zimskih masenih koncentracija lebdećih čestica aerodinamičkog promjera < 1 µm (PM 1 ) izmjerenih u zatvorenom prostoru u urbanom okolišu i vanjskih atmosferskih uvjeta. Koncentracije lebdećih čestica mjerene su dvama laserskim fotometrima.…”

Section: Discussionunclassified

Influences of outdoor meteorological conditions on indoor wintertime short-term PM1 levels

et al. 2015

View full text Add to dashboard Cite

We investigated the relationship between wintertime 1-min mean urban indoor particulate matter mass concentrations for particles with aerodynamic diameter of < 1 µm (PM 1 ) and outdoor atmospheric conditions. Particle concentrations were measured by two light-scattering laser photometers. Aerosol monitors were placed in the ground and first floor corridors of an university building, with inlets at heights of 1.7 m above the floor. The building is located in residential area of Zagreb, Croatia. During the experiment usual student and employee activities were occurring within the building. Surface meteorological data were collected at a nearby outdoor location. Results show the dependence of indoor PM 1 on outdoor meteorology, with the strongest responses to air temperature and relative humidity, whilst global radiation impacts were almost negligible. Response times varied from 1.2 hours (for relative humidity) to 2.7 days (for global radiation). Furthermore, elevated mean concentrations point to the 8-9 km distant industrial zone. Both, PM 1 and meteorological data series exhibited semidiurnal, diurnal and the long-term (about 10-11 days and about 21 day) periodicity. The long-term periodicity of PM 1 time series might be associated with Rossby waves. Possible association with Rossby waves needs to be investigated further.

show abstract

Neural network forecasting of air pollutants hourly concentrations using optimised temporal averages of meteorological variables and pollutant concentrations

Cited by 99 publications

References 27 publications

Relationship between MODIS based Aerosol Optical Depth and PM10 over Croatia

Relationship between MODIS based Aerosol Optical Depth and PM10 over Croatia

Atmospheric composition forecasting in Europe

Influences of outdoor meteorological conditions on indoor wintertime short-term PM1 levels

Contact Info

Product

Resources

About