A method to estimate missing AERONET AOD values based on artificial neural networks

LUIS E. OLCESE; GUSTAVO G. PALANCAR; BEATRIZ M. TOSELLI

ATMOSPHERIC ENVIRONMENT

PERGAMON-ELSEVIER SCIENCE LTD

Lugar: Amsterdam; Año: 2015 vol. 113 p. 140 - 150

1352-2310

>In this work, we present a method to predict missing aerosol optical depth (AOD) values at an AERONETstation. The aim of the method is to fill gaps and/or to extrapolate temporal series in the station datasets,i.e. to obtain AOD values under cloudy sky conditions and in other situations where there is a temporaryor permanent lack of data. To accomplish that, we used historical AOD values at two stations, air masstrajectories passing through both of them (calculated by using the HYSPLIT model) and ANN calculationsto process all the information. The variables included in the neural network training were the stationnumbers, parameters representing the annual average trend of meteorological conditions, the number ofhours and the distance traveled by the air mass between the stations, and the arrival height of the airmass. The method was firstly applied to predict AOD at 440 nm in 9 stations located in the East Coast ofthe US, during the years 1999e2012. The coefficient of determination r2 between measured and calculated AOD values was 0.855, which show the good performance of the method. Besides, this resultrepresents a remarkable improvement compared to three simple approaches. To further validate themethod, we applied it to another region (Iberian Peninsula) with different characteristics (lower densityof AERONET stations, different meteorology, and lower wind field spatial resolution). Although the results are still good (r2 ¼ 0.67), the performance of the method was affected by these characteristics.Considering the obtained results, this method can be used as a powerful tool to predict AOD values inseveral conditions. The methodology can also be easily adapted to predict AOD values at other wavelengths or other aerosol optical properties.