Shelestov A.,National University of Life and Environmental Sciences of Ukraine |
Shelestov A.,Ukrainian Academy of Sciences |
Kolotii A.,National University of Life and Environmental Sciences of Ukraine |
Kolotii A.,Ukrainian Academy of Sciences |
And 5 more authors.
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2015
In this paper, we propose an approach for estimation biophysical parameters, namely LAI effective, FAPAR, and FCOVER, based on in-situ and satellite measurements. In-situ data were collected during 2013-2014 within several field campaigns at the JECAM test site in Ukraine. We have built 30-meter resolution crop specific maps of biophysical parameters based on regression dependencies between ground measurements and NDVI derived from high resolution imagery (Landsat, SPOT) and Proba-V (100 m). In this paper, we discuss the best model selection for LAI effective, FAPAR and FCOVER mapping as well as selection of optimal source of satellite images. Obtained results are compared to available coarse resolution global biophysical products such as MODIS and SPOT-Vegetation. © 2015 IEEE.
Lavreniuk M.S.,Ukrainian Academy of Sciences |
Skakun S.V.,Integration Plus Ltd. |
Shelestov A.J.,National University of Life and Environmental Sciences of Ukraine |
Yalimov B.Y.,Ukrainian Academy of Sciences |
And 3 more authors.
Cybernetics and Systems Analysis | Year: 2016
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. © 2016 Springer Science+Business Media New York