DOWNSCALING AEROSOL OPTICAL THICKNESS TO 1 KM2 SPATIAL RESOLUTION USING SUPPORT VECTOR REGRESSION REPLIED ON DOMAIN KNOWLEDGE

Thi Nhat Thanh Nguyen, Simone Mantovani, Piero Campalani, Gian Piero Limone

2012

Abstract

Processing of data recorded by MODIS sensors on board the polar orbiting satellite Terra and Aqua usually provides Aerosol Optical Thickness maps at a coarse spatial resolution. It is appropriate for applications of air pollution monitoring at the global scale but not adequate enough for monitoring at local scales. Different from the traditional approach based on physical algorithms to downscale the spatial resolution, in this article, we propose a methodology to derive AOT maps over land at 1 km2 of spatial resolution from MODIS data using support vector regression relied on domain knowledge. Experiments carried out on data recorded in three years over Europe areas show promising results on limited areas located around ground measurement sites where data are collected to make empirical data models as well as on large areas over satellite maps.

References

  1. Chang, C. and Lin, C. (2011). LIBSVM: A Library for Support Vector Machines.
  2. Chen, Q. and Shao, Y. (2008). The Application of Improved BP Neural Network Algorithm in Urban Air Quality Prediction: Evidence from China. In Proceeding of 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application (PACIIA 2008), pages 160-163.
  3. Cherkassky, V. and Ma, Y. (2004). Practical Selection of SVM Parameters and Noise Estimation for SVM Regression. In Neural Networks, volume 17, pages 113- 126.
  4. Han, B., Vucetic, S., Braverman, A., and Obradovic, Z. (2006). A Statistical Complement to Deterministic Algorithms for the Retrieval of Aerosol Optical Thickness from Radiance Data. In Engineering Applications of Artificial Intelligence, volume 19, pages 787- 795. Pergamon Pess.
  5. Ichoku, C., Chu, D., Mattoo, S., Kaufman, Y., Remer, L., Tanr, D., Slutsker, I., and Holben, B. (2002). A spatiotemporal approach for global validation and analysis of MODIS aerosol products. In Geophysical Research Letter, volume 29, pages 1-4.
  6. Kaufman, Y. J. and Tanre, D. (1997). Algorithm for remote sensing of tropospheric aerosol from modis. In MODIS ATBD. NASA.
  7. Lary, D., Remer, L., MacNeill, D., Roscoe, B., and Paradise, S. (2009). Machine Learning Bias Correction of MODIS Aerosol Optical Depth. In IEEE Geoscience and Remote Sensing Letters, volume 4, pages 694- 698.
  8. Li, C., Lau, A., Mao, J., and Chu, D. (2005). Retrieval, Validation, and Application of the 1-km Aerosol Optical Depth from MODIS Measurements over Hong Kong. In IEEE Transactions on Geoscience and Remote Sensing, volume 43, pages 2650-2658.
  9. Lu, W., Wang, W., Leung, A., Lo, S., Yuen, R., Xu, Z., and Fan, H. (2002). Air Pollutant Parameter Forecasting Using Support Vector Machine. In Proceeding of the 2002 International Joint Conference on Neural Network (IJCNN02), pages 630-635.
  10. Martins, J., Tanr, D., Remer, L., Kaufman, Y., Matto, S., and Levy, R. (2009). MODIS cloud screening for remote sensing of aerosols over oceans using spatial variability. In Geophysical Research Letters, volume 29.
  11. MEEO, M. E. E. O. (2011). SOIL MAPPER R .
  12. NASA (2011). AErosol Robotic Network (AERONET).
  13. Nguyen, T., Mantovani, S., and Bottoni, M. (2010a). Estimation of Aerosol and Air Quality Fields with PM MAPPER An Optical Multispectral Data Processing Package. In ISPRS TC VII Symposium 100 year ISPRS, volume XXXVIII(7A), pages 257-261.
  14. Nguyen, T., Mantovani, S., Campalani, P., Cavicchi, M., and Bottoni, M. (2010b). Aerosol Optical Thickness Retrieval from Satellite Observation Using Support Vector Regression. In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - 15th Iberoamerican Congress on Pattern Recognition (CIARP2010), pages 492-499. Springer.
  15. Obradovic, S., Das, D., Radosavljevic, V., Ristovski, K., and Vucetic, S. (2010). Spatio-Temporal Characterization of Aerosols through Active Use of Data from Multiple Sensors. In ISPRS TC VII Symposium 100 year ISPRS, volume XXXVIII(7B), pages 424-429.
  16. Okada, Y., Mukai, S., and Sano, I. (2001). Neural Network Approach for Aerosol Retrieval. In IEEE 2001 International Geoscience and Remote Sensing Symposium (IGARSS01), volume 4, pages 1716-1718.
  17. Oo, M., Hernandez, E., Jerg, M., Moshary, B., and Ahmed, S. (2008). Improved MODIS Aerosol Retrieval Using Modified VIS/MIR Surface Albedo Ratio over Urban Scenes. In IEEE 2008 International Geoscience and Remote Sensing Symposium (IGARSS08), volume 3, pages 977-979.
  18. Osowski, S. and Garanty, K. (2006). Wavelets and Support Vector Machine for Forecasting the Meteorological Pollution. In Proceeding of the 7th Nordic Signal Processing Symposium (NORSIG), pages 158-61.
  19. Ramakrishnan, R., Schauer, J., Chen, L., Huang, Z., Shafer, M., Gross, D., and Musicant, D. (2005). The EDAM project: Mining atmospheric aerosol datasets. In International Journal of Intelligent Systems, volume 20 (7), pages 759-787.
  20. Remer, L., Tanr, D., and Kaufman, Y. (2004). Algorithm for Remote Sensing of Tropospheric Aerosol from MODIS: Collection 5. In MODIS ATBD. NASA.
  21. Ren, R., Guo, S., and Gu, L. (2010). Fast bowtie effect elimination for MODIS L1B data. In The Journal of China Universities of Posts and Telecommunications, volume 17(1), pages 120-126. Elsevier.
  22. Siwek, K., Osowski, S., Garanty, K., and Sowinski, M. (2008). Ensemble of Neural Predictors for Forecasting the Atmospheric Pollution. In IEEE International Joint Conference on Neural Network, pages 643-648.
  23. Vapnik, V. (1995). The nature of statistical learning theory. Springer-Verlag, Berlin.
  24. Vucetic, S., Han, B., Mi, W., Li, Z., and Obradovic, Z. (2008). A Data-Mining Approach for the Validation of Aerosol Retrievals. In IEEE Geoscience and Remote Sensing Letter, volume 5(1), pages 113-117.
  25. Xu, Q., Obradovic, Z., Han, B., Li, Y., Braverman, A., and Vucetic, S. (2005). Improving Aerosol Retrieval Accuracy by Integrating AERONET, MISR and MODIS Data. In The 8th Intenational Conference on Information Fusion, volume 1.
Download


Paper Citation


in Harvard Style

Nhat Thanh Nguyen T., Mantovani S., Campalani P. and Piero Limone G. (2012). DOWNSCALING AEROSOL OPTICAL THICKNESS TO 1 KM2 SPATIAL RESOLUTION USING SUPPORT VECTOR REGRESSION REPLIED ON DOMAIN KNOWLEDGE . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-8425-99-7, pages 230-239. DOI: 10.5220/0003791302300239


in Bibtex Style

@conference{icpram12,
author={Thi Nhat Thanh Nguyen and Simone Mantovani and Piero Campalani and Gian Piero Limone},
title={DOWNSCALING AEROSOL OPTICAL THICKNESS TO 1 KM2 SPATIAL RESOLUTION USING SUPPORT VECTOR REGRESSION REPLIED ON DOMAIN KNOWLEDGE},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2012},
pages={230-239},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003791302300239},
isbn={978-989-8425-99-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - DOWNSCALING AEROSOL OPTICAL THICKNESS TO 1 KM2 SPATIAL RESOLUTION USING SUPPORT VECTOR REGRESSION REPLIED ON DOMAIN KNOWLEDGE
SN - 978-989-8425-99-7
AU - Nhat Thanh Nguyen T.
AU - Mantovani S.
AU - Campalani P.
AU - Piero Limone G.
PY - 2012
SP - 230
EP - 239
DO - 10.5220/0003791302300239