PREDICTING GROUND-BASED AEROSOL OPTICAL DEPTH WITH SATELLITE IMAGES VIA GAUSSIAN PROCESSES

Goo Jun, Joydeep Ghosh, Vladan Radosavljevic, Zoran Obradovic

2010

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.

References

  1. Baron, P. (2006). Generation and Behavior of Airborne Particles (Aerosols). National Institute of Occupational Health and Safety, http://www. cdc. gov/niosh/topics/aerosols/pdfs/Aerosol 101. pdf. Retrieved on June.
  2. Cressie, N. (1993). Statistics for Spatial Data. Wiley, New York.
  3. Das, D., Obradovic, Z., and Vucetic, S. (2009). Active selection of sensor sites in remote sensing applications. In IEEE International Conference on Data Mining (ICDM 09).
  4. Dubovik, O. and King, M. (2000). A flexible inversion algorithm for retrieval of aerosol optical properties from Sun and sky radiance measurements. Journal of Geophysical Research, 105(D16):20676.
  5. Han, B., Obradovic, Z., Li, Z., and Vucetic, S. (2006). Data Mining Support for the Improvement of MODIS Aerosol Retrievals. In IEEE International Conference on Geoscience and Remote Sensing Symposium, 2006. IGARSS 2006, pages 2453-2456.
  6. Han, B., Vucetic, S., Braverman, A., and Obradovic, Z. (2005). Construction of a geospatial predictor by fusion of global and local models. In Proccedings of 8th International Conference on Information Fusion. Citeseer.
  7. Holben, B., Eck, T., Slutsker, I., Tanre, D., Buis, J., Setzer, A., Vermote, E., Reagan, J., Kaufman, Y., Nakajima, T., et al. (1998). AERONET-A federated instrument network and data archive for aerosol characterization. Remote Sensing of Environment, 66(1):1-16.
  8. Kaufman, Y., Tanré, D., Remer, L., Vermote, E., Chu, A., and Holben, B. (1997). Operational remote sensing of tropospheric aerosol over land from EOS moderate resolution imaging spectroradiometer. J. Geophys. Res, 102(17):051-17.
  9. King, M. and Kaufman, J. (1992). Remote sensing of cloud, aerosol, and water vapor properties from the Moderate Resolution Imaging Spectrometer (MODIS). IEEE Transactions on Geoscience and Remote Sensing, 30(1).
  10. Lewis, D. D. and Gale, W. A. (1994). A sequential algorithm for training text classifiers. In Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 3-12. Springer-Verlag New York, Inc.
  11. Müller, M., Kaifel, A., Weber, M., Tellmann, S., Burrows, J., and Loyola, D. (2003). Ozone profile retrieval from Global Ozone Monitoring Experiment (GOME) data using a neural network approach (neural network ozone retrieval system (NNORSY)). J. Geophys. Res, 108(D16):4497.
  12. NASA (retrieved in 2010). http://modis.gsfc.nasa.gov/.
  13. Radosavljevic, V., Vucetic, S., and Obradovic, Z. (2009). Reduction of ground-based sensor sites for spatiotemporal analysis of aerosols. In SensorKDD 7809: Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data, pages 71- 78, New York, NY, USA. ACM.
  14. Rasmussen, C. (1996). Evaluation of Gaussian processes and other methods for non-linear regression. PhD thesis, University of Toronto.
  15. Rasmussen, C. E. and Williams, C. K. I. (2005). Gaussian Processes for Machine Learning. The MIT Press.
  16. Remer, L., Tanré, D., Kaufman, Y., Levy, R., and Mattoo, S. (2006). Algorithm for remote sensing of tropospheric aerosol from MODIS: Collection 005. modis. gsfc. nasa. gov/data/atbd/atbd mod02. pdf.
  17. Seung, H. S., Opper, M., and Sompolinsky, H. (1992). Query by committee. In Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pages 287-294, Pittsburgh, PA, USA. ACM Press.
  18. Sinnott, R. (1984). Virtues of the Haversine. Sky and telescope, 68:158.
  19. Solomon, S., Qin, D., Manning, M., Chen, Z., Marquis, M., Averyt, K., Tignor, M., and Miller, H. (2007). IPCC 2007. Climate Change 2007: the Physical Science Basis Contribution of Working Group I to the Fourth Assessment Report of the Intergovernmental Panel on Climate Change.
  20. Vucetic, S., Han, B., Mi, W., Li, Z., and Obradovic, Z. (2008). A Data-Mining Approach for the Validation of Aerosol Retrievals. IEEE Geoscience and Remote Sensing Letters, 5(1):113-117.
Download


Paper Citation


in Harvard Style

Jun G., Ghosh J., Radosavljevic V. and Obradovic Z. (2010). PREDICTING GROUND-BASED AEROSOL OPTICAL DEPTH WITH SATELLITE IMAGES VIA GAUSSIAN PROCESSES . In Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2010) ISBN 978-989-8425-28-7, pages 370-375. DOI: 10.5220/0003115203700375


in Bibtex Style

@conference{kdir10,
author={Goo Jun and Joydeep Ghosh and Vladan Radosavljevic and Zoran Obradovic},
title={PREDICTING GROUND-BASED AEROSOL OPTICAL DEPTH WITH SATELLITE IMAGES VIA GAUSSIAN PROCESSES},
booktitle={Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2010)},
year={2010},
pages={370-375},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003115203700375},
isbn={978-989-8425-28-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2010)
TI - PREDICTING GROUND-BASED AEROSOL OPTICAL DEPTH WITH SATELLITE IMAGES VIA GAUSSIAN PROCESSES
SN - 978-989-8425-28-7
AU - Jun G.
AU - Ghosh J.
AU - Radosavljevic V.
AU - Obradovic Z.
PY - 2010
SP - 370
EP - 375
DO - 10.5220/0003115203700375