A New Frontier in Wind Shear Intensity Forecasting: Stacked Temporal Convolutional Networks and Tree-Based Models Framework

Wind shear presents a considerable hazard to aviation safety, especially during the critical phases of takeoff and landing. Accurate forecasting of wind shear events is essential to mitigate these risks and improve both flight safety and operational efficiency. This paper introduces a hybrid Tempora...

Full description

Saved in:
Bibliographic Details
Main Authors: Afaq Khattak, Jianping Zhang, Pak-wai Chan, Feng Chen, Abdulrazak H. Almaliki
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/15/11/1369
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154433876983808
author Afaq Khattak
Jianping Zhang
Pak-wai Chan
Feng Chen
Abdulrazak H. Almaliki
author_facet Afaq Khattak
Jianping Zhang
Pak-wai Chan
Feng Chen
Abdulrazak H. Almaliki
author_sort Afaq Khattak
collection DOAJ
description Wind shear presents a considerable hazard to aviation safety, especially during the critical phases of takeoff and landing. Accurate forecasting of wind shear events is essential to mitigate these risks and improve both flight safety and operational efficiency. This paper introduces a hybrid Temporal Convolutional Networks and Tree-Based Models (TCNs-TBMs) framework specifically designed for time series modeling and the prediction of wind shear intensity. The framework utilizes the ability of TCNs to capture intricate temporal patterns and integrates it with the predictive strengths of TBMs, such as Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Categorical Boosting (CatBoost), resulting in robust forecast. To ensure optimal performance, hyperparameter tuning was performed using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), enhancing predictive accuracy. The effectiveness of the framework is validated through comparative analyses with standalone machine learning models such as XGBoost, RF, and CatBoost. The proposed TCN-XGBoost model outperformed these alternatives, achieving a lower Root Mean Squared Error (RMSE: 1.95 for training, 1.97 for testing), Mean Absolute Error (MAE: 1.41 for training, 1.39 for testing), and Mean Absolute Percentage Error (MAPE: 7.90% for training, 7.89% for testing). Furthermore, the uncertainty analysis demonstrated the model’s reliability, with a lower mean uncertainty (7.14 × 10<sup>−8</sup>) and standard deviation of uncertainty (6.48 × 10<sup>−8</sup>) compared to other models. These results highlight the potential of the TCNs-TBMs framework to significantly enhance the accuracy of wind shear intensity predictions, emphasizing the value of advanced time series modeling techniques for risk management and decision-making in the aviation industry. This study highlights the framework’s broader applicability to other meteorological forecasting tasks, contributing to aviation safety worldwide.
format Article
id doaj-art-ed96630454b74de59a45ab964bd5c6bf
institution Kabale University
issn 2073-4433
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-ed96630454b74de59a45ab964bd5c6bf2024-11-26T17:50:33ZengMDPI AGAtmosphere2073-44332024-11-011511136910.3390/atmos15111369A New Frontier in Wind Shear Intensity Forecasting: Stacked Temporal Convolutional Networks and Tree-Based Models FrameworkAfaq Khattak0Jianping Zhang1Pak-wai Chan2Feng Chen3Abdulrazak H. Almaliki4Department of Civil, Structural and Environmental Engineering, Trinity College Dublin, Dublin 2, D02 PN40 Dublin, IrelandSecond Research Institute of Civil Aviation Administration of China, Civil Unmanned Aircraft Traffic Management Key Laboratory of Sichuan Province, Chengdu 610041, ChinaHong Kong Observatory, 134A Nathan Road, Kowloon, Hong Kong 999077, ChinaKey Laboratory of Infrastructure Durability and Operation Safety in Airfield of CAAC, Tongji University, 4800 Cao’an Road, Jiading, Shanghai 201804, ChinaDepartment of Civil Engineering, College of Engineering, Taif University, P.O. Box 11099, Taif 21944, Saudi ArabiaWind shear presents a considerable hazard to aviation safety, especially during the critical phases of takeoff and landing. Accurate forecasting of wind shear events is essential to mitigate these risks and improve both flight safety and operational efficiency. This paper introduces a hybrid Temporal Convolutional Networks and Tree-Based Models (TCNs-TBMs) framework specifically designed for time series modeling and the prediction of wind shear intensity. The framework utilizes the ability of TCNs to capture intricate temporal patterns and integrates it with the predictive strengths of TBMs, such as Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Categorical Boosting (CatBoost), resulting in robust forecast. To ensure optimal performance, hyperparameter tuning was performed using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), enhancing predictive accuracy. The effectiveness of the framework is validated through comparative analyses with standalone machine learning models such as XGBoost, RF, and CatBoost. The proposed TCN-XGBoost model outperformed these alternatives, achieving a lower Root Mean Squared Error (RMSE: 1.95 for training, 1.97 for testing), Mean Absolute Error (MAE: 1.41 for training, 1.39 for testing), and Mean Absolute Percentage Error (MAPE: 7.90% for training, 7.89% for testing). Furthermore, the uncertainty analysis demonstrated the model’s reliability, with a lower mean uncertainty (7.14 × 10<sup>−8</sup>) and standard deviation of uncertainty (6.48 × 10<sup>−8</sup>) compared to other models. These results highlight the potential of the TCNs-TBMs framework to significantly enhance the accuracy of wind shear intensity predictions, emphasizing the value of advanced time series modeling techniques for risk management and decision-making in the aviation industry. This study highlights the framework’s broader applicability to other meteorological forecasting tasks, contributing to aviation safety worldwide.https://www.mdpi.com/2073-4433/15/11/1369wind sheartime series modelingtemporal convolutional networkstree-based models
spellingShingle Afaq Khattak
Jianping Zhang
Pak-wai Chan
Feng Chen
Abdulrazak H. Almaliki
A New Frontier in Wind Shear Intensity Forecasting: Stacked Temporal Convolutional Networks and Tree-Based Models Framework
Atmosphere
wind shear
time series modeling
temporal convolutional networks
tree-based models
title A New Frontier in Wind Shear Intensity Forecasting: Stacked Temporal Convolutional Networks and Tree-Based Models Framework
title_full A New Frontier in Wind Shear Intensity Forecasting: Stacked Temporal Convolutional Networks and Tree-Based Models Framework
title_fullStr A New Frontier in Wind Shear Intensity Forecasting: Stacked Temporal Convolutional Networks and Tree-Based Models Framework
title_full_unstemmed A New Frontier in Wind Shear Intensity Forecasting: Stacked Temporal Convolutional Networks and Tree-Based Models Framework
title_short A New Frontier in Wind Shear Intensity Forecasting: Stacked Temporal Convolutional Networks and Tree-Based Models Framework
title_sort new frontier in wind shear intensity forecasting stacked temporal convolutional networks and tree based models framework
topic wind shear
time series modeling
temporal convolutional networks
tree-based models
url https://www.mdpi.com/2073-4433/15/11/1369
work_keys_str_mv AT afaqkhattak anewfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT jianpingzhang anewfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT pakwaichan anewfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT fengchen anewfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT abdulrazakhalmaliki anewfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT afaqkhattak newfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT jianpingzhang newfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT pakwaichan newfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT fengchen newfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework
AT abdulrazakhalmaliki newfrontierinwindshearintensityforecastingstackedtemporalconvolutionalnetworksandtreebasedmodelsframework