Nowcasting sunshine number using logistic modeling

0389974 - ÚI 2014 RIV AT eng J - Článek v odborném periodiku
Brabec, Marek - Badescu, V. - Paulescu, M.
Nowcasting sunshine number using logistic modeling.
Meteorology and Atmospheric Physics. Roč. 120, č. 1-2 (2013), s. 61-71. ISSN 0177-7971. E-ISSN 1436-5065
Grant CEP: GA MŠMT LD12009
Grant ostatní: European Cooperation in Science and Technology(XE) COST ES1002
Výzkumný záměr: CEZ:AV0Z1030915
Klíčová slova: logistic regression * Markov model * sunshine number
Kód oboru RIV: BB - Aplikovaná statistika, operační výzkum
Impakt faktor: 1.245, rok: 2013

In this paper, we present a formalized approach to statistical modeling of the sunshine number, binary indicator of whether the Sun is covered by clouds introduced previously by Badescu (Theor Appl Climatol 72:127–136, 2002). Our statistical approach is based on Markov chain and logistic regression and yields fully specified probability models that are relatively easily identified (and their unknown parameters estimated) from a set of empirical data (observed sunshine number and sunshine stability number series). We discuss general structure of the model and its advantages, demonstrate its performance on real data and compare its results to classical ARIMA approach as to a competitor. Since the model parameters have clear interpretation, we also illustrate how, e.g., their inter-seasonal stability can be tested. We conclude with an outlook to future developments oriented to construction of models allowing for practically desirable smooth transition between data observed with different frequencies and with a short discussion of technical problems that such a goal brings.
Trvalý link: http://hdl.handle.net/11104/0218865