Authors:
Goo Jun
1
;
Joydeep Ghosh
1
;
Vladan Radosavljevic
2
and
Zoran Obradovic
2
Affiliations:
1
University of Texas, United States
;
2
Temple University, United States
Keyword(s):
Aerosol, AERONET, MODIS, Gaussian Process, Active Learning, Spatio-temporal Data Mining.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computational Intelligence
;
Evolutionary Computing
;
Interactive and Online Data Mining
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Soft Computing
;
Structured Data Analysis and Statistical Methods
;
Symbolic Systems
Abstract:
A Gaussian process regression technique is proposed to predict ground-based aerosol optical depth measurements from satellite multispectral images, and to select the most informative ground-based sites by active learning. Satellite images provide spatial and temporal information in addition to the spectral features, and such heterogeneity of available features is captured in the Gaussian process model by employing an additive set of covariance functions. By finding an optimal set of hyperparameters, relevance of each additional information is automatically determined. Experiments show that the spatio-temporal information contributes significantly to the regression results. The prediction results are not only more accurate but also more interpretable than existing approaches. For active learning, each spatio-temporal setup is evaluated by an uncertainty-sampling algorithm. The results show that the active selection process benefits most from the spatial information.