Statistical Modeling for Improvement of Numerical-Model-Based Solar Radiation Forecasts

Authors: Marek Brabec, Kryštof Eben, Emil Pelikán, Pavel Krč, Jaroslav Resler, Pavel Juruš
Publication year: 2018
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Proceedings of the Third International Afro-European Conference for Industrial Advancement - AECIA 2016
Projects: Advanced random field methods in data assimilation for short-term weather prediction
Bibliographic citation: BRABEC, Marek, EBEN, Kryštof, PELIKÁN, Emil, KRČ, Pavel, RESLER, Jaroslav, JURUŠ, Pavel. Statistical Modeling for Improvement of Numerical-Model-Based Solar Radiation Forecasts. In: ABRAHAM, A., HAQIQ, A., ELLA HASSANIEN, A., SNÁŠEL, V., ALIMI, A.M., eds. Proceedings of the Third International Afro-European Conference for Industrial Advancement - AECIA 2016. Cham: Springer, 2018, S. 248-257. Advances in Intelligent Systems and Computing, 565. ISBN 978-3-319-60833-4. ISSN 2194-5357
Dostupné z: doi:10.1007/978-3-319-60834-1_26.
DOI: 10.1007/978-3-319-60834-1_26
ID: 477273

Abstract

ZÁKLADNÍ ÚDAJE: Proceedings of the Third International Afro-European Conference for Industrial Advancement - AECIA 2016. Cham: Springer, 2018 - (Abraham, A., Haqiq, A., Ella Hassanien, A., Snášel, V., Alimi, A.), s. 248-257. Advances in Intelligent Systems and Computing, 565. ISBN 978-3-319-60833-4. ISSN 2194-5357. [AECIA 2016. International Afro-European Conference for Industrial Advancement /3./. Marrakesh (MA), 21.11.2016-26.11.2016]. Podpora: GA13-34856S. ANOTACE: We first analyze some features of numerical weather predictions (NWP) for global solar radiation and notice that they are undersmooth. This finding opens a way to improvements via various smoothing strategies. Then we introduce a statistical modeling framework based on modern semiparametric regression. We use a numerical weather prediction (NWP) model output as one of the inputs for our statistical model. The statistical model is build on the modern regression formalism, utilizing nonparametric B-splines for nonlinear parts whose exact shape is unknown a priori (apart from physically motivated smoothness). Then we illustrate its abilities for systematic development of strategies for NWP calibration and further development. The results are useful both for practical forecasting and as a source of feedback for NWP modelers.