A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.

This study introduces a high-resolution wind nowcasting model designed for aviation applications at Madeira International Airport, a location known for its complex wind patterns. By using data from a network of six meteorological stations and deep learning techniques, the produced model is capable o...

Full description

Saved in:
Bibliographic Details
Main Authors: Décio Alves, Fábio Mendonça, Sheikh Shanawaz Mostafa, Diogo Freitas, João Pestana, Dinarte Vieira, Marko Radeta, Fernando Morgado-Dias
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0316548
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850188694474981376
author Décio Alves
Fábio Mendonça
Sheikh Shanawaz Mostafa
Diogo Freitas
João Pestana
Dinarte Vieira
Marko Radeta
Fernando Morgado-Dias
author_facet Décio Alves
Fábio Mendonça
Sheikh Shanawaz Mostafa
Diogo Freitas
João Pestana
Dinarte Vieira
Marko Radeta
Fernando Morgado-Dias
author_sort Décio Alves
collection DOAJ
description This study introduces a high-resolution wind nowcasting model designed for aviation applications at Madeira International Airport, a location known for its complex wind patterns. By using data from a network of six meteorological stations and deep learning techniques, the produced model is capable of predicting wind speed and direction up to 30-minute ahead with 1-minute temporal resolution. The optimized architecture demonstrated robust predictive performance across all forecast horizons. For the most challenging task, the 30-minute ahead forecasts, the model achieved a wind speed Mean Absolute Error (MAE) of 0.78 m/s and a wind direction MAE of 33.06°. Furthermore, the use of Gaussian noise concatenation to both input and label training data yielded the most consistent results. A case study further validated the model's efficacy, with MAE values below 0.43 m/s for wind speed and between 33.93° and 35.03° for wind direction across different forecast horizons. This approach shows that combining strategically deployed sensor networks with machine learning techniques offers improvements in wind nowcasting for airports in complex environments, possibly enhancing operational efficiency and safety.
format Article
id doaj-art-0b32257fb6b0482f8b0df1b2aefd25cc
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-0b32257fb6b0482f8b0df1b2aefd25cc2025-08-20T02:15:50ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031654810.1371/journal.pone.0316548A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.Décio AlvesFábio MendonçaSheikh Shanawaz MostafaDiogo FreitasJoão PestanaDinarte VieiraMarko RadetaFernando Morgado-DiasThis study introduces a high-resolution wind nowcasting model designed for aviation applications at Madeira International Airport, a location known for its complex wind patterns. By using data from a network of six meteorological stations and deep learning techniques, the produced model is capable of predicting wind speed and direction up to 30-minute ahead with 1-minute temporal resolution. The optimized architecture demonstrated robust predictive performance across all forecast horizons. For the most challenging task, the 30-minute ahead forecasts, the model achieved a wind speed Mean Absolute Error (MAE) of 0.78 m/s and a wind direction MAE of 33.06°. Furthermore, the use of Gaussian noise concatenation to both input and label training data yielded the most consistent results. A case study further validated the model's efficacy, with MAE values below 0.43 m/s for wind speed and between 33.93° and 35.03° for wind direction across different forecast horizons. This approach shows that combining strategically deployed sensor networks with machine learning techniques offers improvements in wind nowcasting for airports in complex environments, possibly enhancing operational efficiency and safety.https://doi.org/10.1371/journal.pone.0316548
spellingShingle Décio Alves
Fábio Mendonça
Sheikh Shanawaz Mostafa
Diogo Freitas
João Pestana
Dinarte Vieira
Marko Radeta
Fernando Morgado-Dias
A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.
PLoS ONE
title A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.
title_full A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.
title_fullStr A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.
title_full_unstemmed A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.
title_short A networked station system for high-resolution wind nowcasting in air traffic operations: A data-augmented deep learning approach.
title_sort networked station system for high resolution wind nowcasting in air traffic operations a data augmented deep learning approach
url https://doi.org/10.1371/journal.pone.0316548
work_keys_str_mv AT decioalves anetworkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT fabiomendonca anetworkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT sheikhshanawazmostafa anetworkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT diogofreitas anetworkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT joaopestana anetworkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT dinartevieira anetworkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT markoradeta anetworkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT fernandomorgadodias anetworkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT decioalves networkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT fabiomendonca networkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT sheikhshanawazmostafa networkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT diogofreitas networkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT joaopestana networkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT dinartevieira networkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT markoradeta networkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach
AT fernandomorgadodias networkedstationsystemforhighresolutionwindnowcastinginairtrafficoperationsadataaugmenteddeeplearningapproach