ß-Variational autoencoders and transformers for reduced-order modelling of fluid flows.

Variational autoencoder architectures have the potential to develop reduced-order models for chaotic fluid flows. We propose a method for learning compact and near-orthogonal reduced-order models using a combination of a ß-variational autoencoder and a transformer, tested on numerical data from a two-dimensional viscous flow in both periodic and chaotic regimes. The ß-variational autoencoder is trained to learn a compact latent representation of the flow velocity, and the transformer is trained to predict the temporal dynamics in latent-space. Using the ß-variational autoencoder to learn disentangled representations in latent-space, we obtain a more interpretable flow model with features that resemble those observed in the proper orthogonal decomposition, but with a more efficient representation. Using Poincaré maps, the results show that our method can capture the underlying dynamics of the flow outperforming other prediction models. The proposed method has potential applications in other fields such as weather forecasting, structural dynamics or biomedical engineering.

Effect of the ultraviolet unweighted irradiance on the compliance of sunbeds in Spain.

The use of tanning devices in Spain is regulated by the Royal Decree 1002/2002, which is based on the European standard EN60335-2-27. The European standard establishes that the total unweighted irradiance between 200 and 280 nm must not exceed 0.003 Wm-2, a requirement that the Spanish regulation modified to 0.03 Wm-2 from 250 to 295 nm. With these differences, the compliance consideration of an artificial tanning device can vary. Spectral irradiance measurements of 41 tanning devices performed with a high-resolution spectroradiometer were analyzed. None of the tanning devices had irradiances higher than 0.003 Wm-2 between 250 (the shortest wavelength measured by the spectroradiometer) and 280 nm, but the limit required by Spanish regulation was exceeded by 11 devices, of which one would have been considered compliant according to the European standard since the effective irradiance was lower than 0.3 Wm-2. Beyond noting the differences that can occur in sunbed inspections according to the established criteria, this work has shown the differences in the spectral and total values of devices in use in Spain, validating the need for periodic inspections.