In: Wagner W., Szekely, B. (eds.): ISPRS TC VII Symposium - 100 Years ISPRS, Vienna, Austria, July 5-7, 2010, IAPRS, Vol. XXXVIII, Part 7B 
SPATIO-TEMPORAL CHARACTERIZATION OF AEROSOLS THROUGH ACTIVE USE 
OF DATA FROM MULTIPLE SENSORS 
Z. Obradovic 3 ’ *, D. Das 3 , V.Radosavljevic 3 , K.Ristovski 3 , S.Vucetic 3 
a Center for Information Science and Technology, Temple University, Philadelphia, PA, USA 
Technical Commission VII Symposium 2010 
KEY WORDS: Atmosphere, Environment, Analysis, Data Mining, Retrieval, Algorithms, Spatial, Temporal 
ABSTRACT: 
One of the main challenges of current climate research is providing Earth-wide characterization of Aerosol Optical Depth (AOD), 
which indicates the amount of depletion that a beam of radiation undergoes as it passes through the atmosphere. Here, a 
comprehensive overview will be presented of our ongoing data mining based study aimed at better understanding of spatio-temporal 
distribution of AOD by taking advantage of measurements collected from multiple ground and satellite-based sensors. In contrast to 
domain-driven methods for AOD retrieval (prediction from satellite observations), our approach is completely data-driven. This 
statistical method consists of training a nonlinear regression model to predict AOD using the satellite observations as inputs where 
the targets are obtained from a network of unevenly distributed ground-based sites over the world. Challenges and our proposed 
solutions discussed here in context of global scale AOD estimation include (i) AOD regression from mixed-distribution spatio- 
temporal data; (ii) training such a statistical predictor for robust performance across multiple accuracy measures; (iii) uncertainty 
analysis of AOD estimation, (iv) active selection of sites for ground based observations, (v) discovery of major sources of correctable 
errors in deterministic models, and (vi) using conditional random fields to combine nonlinear regression models and a variety of 
correlated knowledge sources in a unified and more accurate AOD prediction model. The proposed methods is illustrated on 
experiments conducted using three years of global observations obtained by merging satellite data of high spatial resolution (MODIS 
Level 2 data from NASA’s Terra and Aqua satellites) with ground-based observations of high temporal resolution (a remote-sensing 
network of radiometers called AERONET network). The experiments revealed that the proposed methods result in more accurate 
AOD retrieval than the baseline statistical and domain-based predictors'. 
1. INTRODUCTION 
The global impact of environment change to climate is 
monitored largely by use of remote sensing instruments that 
measure radiances emitted or reflected from Earth. The 
observed radiances are used to estimate underlying geophysical 
characteristics through the predictive process called retrieval. 
The retrieved parameters are then used in various applications 
ranging from monitoring change of atmospheric temperature, 
the extent of snow, ice or vegetation cover, cloud and aerosol 
properties to the development of general circulation models for 
climate studies. Accurate and timely retrievals of geophysical 
parameters are therefore critical for the success of many climate 
change related studies. 
In recent years remote sensing instruments of various properties 
have been employed in an attempt to better characterize 
important geophysical phenomena. The technology of new 
generation sensors has improved dramatically, but the collected 
data still contain large uncertainties due to high noise and a 
large fraction of missing values. As a consequence, retrieval 
from such high dimensional spatio-temporal observations is a 
very challenging problem (Jeong et al, 2005). 
Aerosols are small particles produced by natural and man-made 
sources that both reflect and absorb incoming solar radiation. 
Aerosol concentration and chemical properties are important 
parameters in climate change models, in studies of regional 
radiation balances, and studies of the hydrological cycle 
(Ramanathan et al, 2002). Using radiance observations, it is 
possible to estimate the attenuation of solar energy as it passes 
through a column of atmosphere, a quantity commonly known 
as aerosol optical depth (AOD). 
The AOD can be retrieved using ground (Levy et al, 2005) or 
satellite (Remer et al, 2006) based observations. Ground-based 
observations are mostly obtained by the AEROsol robotic 
NETwork (AERONET) which is the global remote sensing 
network of about 250 radiometers (spatial distribution shown at 
Fig. 1) that measure AOD several times an hour at specific 
locations. AERONET AOD prediction is considered very 
accurate and is often taken as the ground truth for validation of 
various satellite-based AOD prediction algorithms aimed at 
providing global coverage . 
Figure 1: Spatial distribution of AERONET sites. 
Corresponding author (e-mail zoran.obradovic@temple.edu).