Atmosphere 2026, 17(8), 749; https://doi.org/10.3390/atmos17080749 (registering DOI) - 31 Jul 2026
Abstract
Reduced visibility due to fog poses significant safety and operational risks in marine environments, emphasizing the need for accurate short-term nowcasting. Typical machine learning forecasting models fail to capture temporal meteorological dependencies that influence fog dynamics, due to the reliance on data assimilated
[...] Read more.
Reduced visibility due to fog poses significant safety and operational risks in marine environments, emphasizing the need for accurate short-term nowcasting. Typical machine learning forecasting models fail to capture temporal meteorological dependencies that influence fog dynamics, due to the reliance on data assimilated measurements for closed-loop time series prediction. This work introduces a novel multiple lookback window (MLW) architecture that utilizes the recurrent neural network model of Gated Recurrent Units (GRU) to nowcast dense fog visibility (Vis < 400 m) time series. This architecture facilitates learning the short- and long-term dependencies in meteorological data for non-data assimilation (open-loop) time series prediction. Prediction intervals were obtained using Bayesian approximation at
(This article belongs to the Section Atmospheric Techniques, Instruments, and Modeling)
►
Show Figures
Figure 1
