Time-Series Embeddings from Language Models: A Tool for Wind Direction Nowcasting

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3APB445KMY" target="_blank" >RIV/00216208:11320/25:PB445KMY - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85193825688&doi=10.1007%2fs13351-024-3151-9&partnerID=40&md5=d96d1f1a654479091a19baca7df3a0eb" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85193825688&doi=10.1007%2fs13351-024-3151-9&partnerID=40&md5=d96d1f1a654479091a19baca7df3a0eb</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s13351-024-3151-9" target="_blank" >10.1007/s13351-024-3151-9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Time-Series Embeddings from Language Models: A Tool for Wind Direction Nowcasting

Popis výsledku v původním jazyce

Wind direction nowcasting is crucial in various sectors, particularly for ensuring aviation operations and safety. In this context, the TELMo (Time-series Embeddings from Language Models) model, a sophisticated deep learning architecture, has been introduced in this work for enhanced wind-direction nowcasting. Developed by using three years of data from multiple stations in the complex terrain of an international airport, TELMo incorporates the horizontal u (east–west) and v (north–south) wind components to significantly reduce forecasting errors. On a day with high wind direction variability, TELMo achieved mean absolute error values of 5.66 for 2-min, 10.59 for 10-min, and 14.79 for 20-min forecasts, processed within a swift 9-ms/step timeframe. Standard degree-based analysis, in comparison, yielded lower performance, emphasizing the effectiveness of the u and v components. In contrast, a Vanilla neural network, representing a shallow-learning approach, underperformed in all analyses, highlighting the superiority of deep learning methodologies in wind direction nowcasting. TELMo is an efficient model, capable of accurately forecasting wind direction for air traffic operations, with an error less than 20° in 97.49% of the predictions, aligning with recommended international thresholds. This model design enables its applicability across various geographical locations, making it a versatile tool in global aviation meteorology. © The Chinese Meteorological Society and Springer-Verlag Berlin Heidelberg 2024.

Název v anglickém jazyce

Time-Series Embeddings from Language Models: A Tool for Wind Direction Nowcasting

Popis výsledku anglicky

Wind direction nowcasting is crucial in various sectors, particularly for ensuring aviation operations and safety. In this context, the TELMo (Time-series Embeddings from Language Models) model, a sophisticated deep learning architecture, has been introduced in this work for enhanced wind-direction nowcasting. Developed by using three years of data from multiple stations in the complex terrain of an international airport, TELMo incorporates the horizontal u (east–west) and v (north–south) wind components to significantly reduce forecasting errors. On a day with high wind direction variability, TELMo achieved mean absolute error values of 5.66 for 2-min, 10.59 for 10-min, and 14.79 for 20-min forecasts, processed within a swift 9-ms/step timeframe. Standard degree-based analysis, in comparison, yielded lower performance, emphasizing the effectiveness of the u and v components. In contrast, a Vanilla neural network, representing a shallow-learning approach, underperformed in all analyses, highlighting the superiority of deep learning methodologies in wind direction nowcasting. TELMo is an efficient model, capable of accurately forecasting wind direction for air traffic operations, with an error less than 20° in 97.49% of the predictions, aligning with recommended international thresholds. This model design enables its applicability across various geographical locations, making it a versatile tool in global aviation meteorology. © The Chinese Meteorological Society and Springer-Verlag Berlin Heidelberg 2024.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of Meteorological Research

ISSN

2095-6037

e-ISSN

—

Svazek periodika

38

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

12

Strana od-do

558-569

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85193825688