Method of the Decade Air's Temperature Long-Range Prognosis with Robust Inductive Models and Analogy Principle Usage. Zubov D.A., Vlasov Y.N., Grigorenko M.S.

Abstract. The method of the average decade air's temperature long-range prognosis on the polynomial robust inductive models basis and the analogy principle (the average month model's structure is used for the average decade prognosis) usage is offered. The 2003-2007 years research results analysis shows advantage of polynomial models by comparison to polynomial-harmonic - middle quality and absolute deviation is 72,0% (2,4'C) and 69,0% (2,6'C) accordingly. Polynomial basis shows the middle quality 75% on the mean absolute deviation in every half year prognosis interval.

Keywords. Inductive model, long-range prognosis, analogy principle, meteorology.

References.
1. Ivakhnenko A.G.: Inductive Method of Complex Systems Models Self-organization. Kiev, Ukraine 1981. -  http://www.gmdh.net/articles/theory/zmInduct.htm
2. Zubov D.A., Vlasov Y.N.: Long-term Forecasting of the Air Average Temperature and Atmospheric Precipitations on the Linear Auto Regression Model and Maximal Error's Minimisation Criterion Basis. In: Proceedings of Scientists of East Ukrainian National University named V.Dal, p.40-49. Lugansk, Ukraine 2004.
3. Zubov D.A., Vlasov Y.N.: Research of Combinatorial Algorithm of Long-term Prognosis of Air's Temperature on the Base of Linear Autoregressive Model and Criterion of Regularity. In: Proceedings of Scientists of East Ukrainian National University named V.Dal, N 2(72), p.77-85. Lugansk, Ukraine 2002.
4. Zubov D.A., Bolotova M.S.: Long-term Prognosis of the Air's Average Decade Temperature on the Polynomial-harmonic Models Basis and "Well" Conditioned Teaching Data. In: Proceedings of Scientists of East Ukrainian National University named V.Dal, N 11(117), p.55-61. Lugansk, Ukraine 2007.
5. Vlasov Y.N., Ulshin V.A., Zubov D.A.: Research of the Long-term Prognosis Method of the Air's Average Decade Temperature on the Self-organized Polynomial-harmonic Models Base. In: Proceedings of Scientists of Lugansk Regional Dept. of International Informatics Academy, N 2(13), p.81-86. Lugansk, Ukraine 2006.