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

作　　者：Decio ALVES Fabio MENDONCA Sheikh Shanawaz MOSTAFA Fernando MORGADO-DIAS 

机构地区：[1]University of Madeira,Campus Universitário da Penteada,9020-105,Funchal,Portugal [2]Interactive Technologies Institute/Laboratory for Robotics and Engineering Systems and Agência Regional para o Desenvolvimento da Investigação,Tecnologia e Inovação,Edif.Madeira Tecnopolo,Caminho da Penteada piso-2,9020-105,Funchal,Portugal

出　　处：《Journal of Meteorological Research》2024年第3期558-569,共12页气象学报（英文版）

基　　金：Supported by Interactive Technologies Institute/Larsys/Fundaçao para a Ciência e a Tecnologia(10.54499/LA/P/0083/2020,10.54499/UIDP/50009/2020,and 10.54499/UIDB/50009/2020);Agência Regional para o Desenvolvimento da Investigação,Tecnologia e Inovação,and Portuguese Technical Engineering Order(OET).

摘　　要：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.

关 键 词：wind nowcasting wind components wind direction time series prediction deep learning 

分 类 号：P457.5[天文地球—大气科学及气象学]