Large-Scale Classification of Land Cover Using Retrospective Satellite Data
- 89 Downloads
Large-scale mapping of land cover is considered in the paper as a problem of automated processing of big geospatial data, which may contain various uncertainties. To solve it, we propose to use three different paradigms, namely, decomposition method, the method of active learning from the scope of intelligent computations, and method of satellite images reconstruction. Such an approach allows us to minimize the participation of experts in solving the problem. Within solving the problem of land cover classification we also investigated three different approaches of data fusion. The most efficient data fusion method is one that could be reduced to the problem of classification on the base of time-series images. Developed automated methodology was applied to land cover mapping and classification for the whole territory of Ukraine for 1990, 2000, and 2010 with a 30-meter spatial resolution.
Keywordsland cover classification geospatial data data fusion satellite data neural network training and test samples
Unable to display preview. Download preview PDF.
- 1.M. A. Friedl, D. K. McIver, J. C. F. Hodges, X. Y. Zhang, D. Muchoney, A. H. Strahler, C. E. Woodcock, S. Gopal, A. Schneider, A. Cooper, A. Baccini, F. Gao, and C. Schaaf, “Global land cover mapping from MODIS: Algorithms and early results,” Remote Sensing of Environment, 83, No. 2, 287–302 (2002).CrossRefGoogle Scholar
- 3.N. Kussul, S. Skakun, A. Shelestov, O. Kravchenko, J. F. Gallego, and O. Kussul, “Crop area estimation in Ukraine using satellite data within the MARS project 2012,” IEEE Intern. Geoscience and Remote Sensing Symposium (IGARSS) (2012), pp. 3756–3759.Google Scholar
- 7.N. Kussul, S. Skakun, A. Shelestov, O. Kussul, and B. Yailymov, “Resilience aspects in the sensor Web infrastructure for natural disaster monitoring and risk assessment based on Earth observation data,” IEEE J. Selected Topics in Applied Earth Observations and Remote Sensing, 7, No. 9, 3826–3832 (2014).CrossRefGoogle Scholar
- 8.N. Kussul, D. Mandl, K. Moe, J. P. Mund, J. Post, A. Shelestov, S. Skakun, J. Szarzynski, G. Van Langenhove, and M. Handy, “Interoperable infrastructure for flood monitoring: Sensor Web, Grid, and cloud,” IEEE J. Selected Topics in Applied Earth Observations and Remote Sensing, 5, No. 6, 1740–1745 (2012).CrossRefGoogle Scholar
- 10.N. Kussul, A. Shelestov, and S. Skakun, “Flood monitoring from SAR data,” NATO Science for Peace and Security Series C: Environmental Security, 19–29, 10.1007/978-90-481-9618-0_3 (2011).
- 12.M. C. Hansen, A. Egorov, D. P. Roy, P. Potapov, J. Ju, S. Turubanova, I. Kommareddy, and T. R. Loveland, “Continuous fields of land cover for the conterminous United States using Landsat data: First results from the Web-Enabled Landsat Data (WELD) project,” Remote Sensing Letters, 2, No. 4, 279–288 (2011).CrossRefGoogle Scholar
- 13.G. Buttner, J. Feranec, G. Jaffrain, L. Mari, G. Maucha, and T. Soukup, “The CORINE land cover 2000 project,” EARSeL eProceedings, 3, No. 3, 331–346 (2004).Google Scholar
- 14.N. Kussul, S. Skakun, A. Shelestov, and O. Kussul, “The use of satellite SAR imagery to crop classification in Ukraine within JECAM project,” in: IEEE Intern. Geoscience and Remote Sensing Symposium (IGARSS) (2014), pp. 1497–1500.Google Scholar
- 15.N. Kussul, S. Skakun, A. Shelestov, O. Kravchenko, and O. Kussul, “Crop classification in Ukraine using satellite optical and SAR images,” Models&Analyses, 2, No. 2, 118–128 (2013).Google Scholar
- 18.S. Haykin, Neural Networks and Learning Machines, Prentice Hall, Upper Saddle River (NJ) (2008).Google Scholar
- 19.J. Sim and C. C. Wright, “The Kappa statistic in reliability studies: Use, interpretation, and sample size requirements,” Physical Therapy, 85, No. 3, 257–268 (2005).Google Scholar
- 20.LUCAS, Land use and cover area frame survey (2009), http://ec.europa.eu/eurostat/documents/205002/208938/LUCAS2009_C1-Instructions_Revised20130925.pdf/.
- 23.N. Kussul, S. Skakun, A. Shelestov, and O. Kussul, “The use of satellite SAR imagery to crop classification in Ukraine within JECAM project,” Geoscience and Remote Sensing Symposium (IGARSS), IEEE Intern., Quebec City, QC, Canada (2014), pp. 1497–1500, DOI: 10.1109/IGARSS.2014.6946721.
- 24.V. Lavreniuk, N. Kussul, S. Skakun, A. Shelestov, and B. Yailymov, “Regional retrospective high resolution land cover for Ukraine: Methodology and results,” Intern. Geoscience and Remote Sensing Symposium (IGARSS) (2015).Google Scholar