SkyVis, an Application of MATLAB in Meteorological Visualization
2003 (English)In: Proceedings of Nordic Matlab Conference 2003, 2003, 295-300 p.Conference paper (Other academic)
We present a work in progress, Sky Vis, which makes it possible to synthesize realistic images of the sky using data from weather parameter data sets. A neural-network-based model is trained to predict the appearance of the sky from a weather parameter vector. Hourly measurements of weather parameters (like temperature and pressure) and corresponding images are used as training data. The images are decomposed into their eigen components using the principal component analysis (PCA) method. The image information is thus represented using a small number of coefficients. The results show that the main appearance is correct and that it is possible to distinguish between different types of weather. A limitation is that the method is not able to synthesize images with cloud details. This method is in contrast to many previous methods able to synthesize a sky image which varies with the current weather situation.
Place, publisher, year, edition, pages
2003. 295-300 p.
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-13393OAI: oai:DiVA.org:liu-13393DiVA: diva2:20596
Nordic Matlab Conference, Copenhagen, October the 21st - 22nd, 2003