Model-based clustering is considered for Gaussian multivariate functional data as an extension of the univariate functional setting. Principal components analysis is introduced and used to define an approximation of the notion of density for multivariate functional data. An EM like algorithm is proposed to estimate the parameters of the reduced model. Application on climatology data illustrates...

E. Gerasopoulos, P. Zanis, C. Papastefanou, C. S. Zerefos, A. Ioannidou, and H. Wernli Nuclear Physics Department, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece Research Center for Atmospheric Physics and Climatology, Academy of Athens, Athens, Greece Laboratory of Climatology and Atmospheric Environment, Geology Department, University of Athens, Athens, Greece Institute of A...

The effects of solar ultraviolet (UV) radiation on life Earth differ greatly. While overexposure to UV rays is harmful, small amounts exposure are necessary for the synthesis Vitamin D and good health. To optimize individual UV, it therefore crucial use data sources representative entire populations realistically accounting various influencing factors. A climatology Switzerland based satellite ...

Climatology is a comparatively new science which has been progressing rapidly in recent decades. Essentially, conceptualization of its subject—“climate”—is not yet complete. The concept of climate has been transforming along with the development of climatology. At the beginning of the new century climatology is in front of necessity to extend the sense of the concept of climate as compared to t...

The wind/wave climatology for the Arctic Seas will be developed based on altimeter observations. It will have a major scientific and applied significance as presently there is no reference climatology for this region of the ocean available. The new versions of wave models for the Beaufort and Chukchi Seas will include new physics that is already under development, and the novel physics presentl...