Академическое издательство «Гео»

Sea ice, extent change, solar radiation, statistical methods, neural networks

copy the whole article (116 Kb)

«Earth`s Cryosphere», 2016, Vol. XX, № 3, p. 41-47

The experience of medium-term forecast of the sea ice extent in the Northern Hemisphere on the basis of calculated incoming solar radiation and neuronet modeling

V.M. Fedorov, O.E. Buharov*, D.P. Bogolyubov*, P.B. Grebennikov

Lomonosov Moscow State University, Department of Geography,
1, Leninskie Gory, Moscow, 119991, Russia; fedorov.msu@mail.ru
* Moscow Institute of Electronics and Mathematics, National Research University Higher School of Economics,
34, Tallinskaya str., Moscow, 123458, Russia; oleg_bukh.box@mail.ru

Medium-term forecast of the sea ice extent has been carried out by determining of the relationship between incoming solar radiation and the sea ice extent in the Northern Hemisphere. Different methods of statistic and neuronic modeling have been used. The forecast shows that the chief factor determining the variation in the maximum and minimum sea ice extent in the medium-term scale is the variability of solar radiation arriving at the top of the atmosphere. Evaluation of the medium-term forecasts of the sea ice extent demonstrates effectiveness of using the averaged results of the regression analysis and of neural network modeling.

Sea ice, extent change, solar radiation, statistical methods, neural networks
главная

www.izdatgeo.ru