Number of the records: 1
Nowcasting sunshine number using logistic modeling
- 1.
SYSNO ASEP 0389974 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Nowcasting sunshine number using logistic modeling Author(s) Brabec, Marek (UIVT-O) RID, SAI, ORCID
Badescu, V. (RO)
Paulescu, M. (RO)Source Title Meteorology and Atmospheric Physics - ISSN 0177-7971
Roč. 120, č. 1-2 (2013), s. 61-71Number of pages 11 s. Language eng - English Country AT - Austria Keywords logistic regression ; Markov model ; sunshine number Subject RIV BB - Applied Statistics, Operational Research R&D Projects LD12009 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) CEZ AV0Z1030915 - UIVT-O UT WOS 000316689700006 EID SCOPUS 84875401923 DOI 10.1007/s00703-013-0240-1 Annotation 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. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2014
Number of the records: 1