The visibility of the weather significantly affects the punctuality and safety of civil aviation flights. Suppose visibility can be precisely forecast in advance. In that case, it will be crucial to make accurate flight plans, and pre-flight preparation since sudden changes in weather visibility often cause flight go-around, holding, alternate, cancellation, and even dangerous occurrences. John F. Kennedy International Airport (JFK) sees quick visibility changes in the fall and winter due to complicated and variable meteorological conditions, making accurate flight planning and risky flights more of a challenge than usual. Given that several meteorological parameters influence weather visibility and that these factors are strongly correlated with time. Therefore, this study contrasts two deep learning-based methods for hourly visibility prediction: the Long Short-Term Memory (LSTM) approach and the Gated-Recurrent Unit (GRU) approach. To find visibility, the proposed model considers several different criteria. The proposed techniques are intended to forecast atmospheric visibility for safer flights.
Forecast Analysis of Visibility for Airport Operations with Deep Learning Techniques
2023-03-08
607997 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
NASA Tests Concepts for Low-Visibility Airport Operations
Online Contents | 1998
Engineering Index Backfile | 1956
|THE VISIBILITY OF AIRPORT RUNWAYS1
SAE Technical Papers | 1956
|