Title:	TRAINABLE METHOD FOR PREDICTING CHARACTERISTICS OF LAND SURFACE OBJECTS
Author(s):	Alexander Murynin, Konstantin Gorokhovskiy, Vladimir Ignatiev
ISBN:	978-972-8939-89-2
Editors:	Yingcai Xiao
Year:	2013
Edition:	Single
Keywords:	Image mining, remote sensing, forecasting, nonlinear regression
Type:	Full Paper
First Page:	119
Last Page:	125
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	A new method for predicting characteristics of land surface objects has been proposed. The method is based on finding annual periodical patterns and comparison with a pattern obtained for year of observation. An example of the method application is considered. In the example authors propose, train and test a model for forecasting of crop yields based on multi-year remote observations of vegetation conditions in several regions of Russian Federation.
	Go Back