Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection

Windshear is a microscale meteorological phenomenon that can be dangerous to aircraft during the take-off and landing phases. Accurate windshear detection plays a significant role in air traffic control. In this paper, we aim to investigate a machine learning method for windshear detection based on...

Full description

Saved in:
Bibliographic Details
Main Authors: Jie Zhang, Pak-Wai Chan, Michael Kwok-Po Ng
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/23/4423
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060350791090176
author Jie Zhang
Pak-Wai Chan
Michael Kwok-Po Ng
author_facet Jie Zhang
Pak-Wai Chan
Michael Kwok-Po Ng
author_sort Jie Zhang
collection DOAJ
description Windshear is a microscale meteorological phenomenon that can be dangerous to aircraft during the take-off and landing phases. Accurate windshear detection plays a significant role in air traffic control. In this paper, we aim to investigate a machine learning method for windshear detection based on previously collected wind velocity data and windshear records. Generally, the occurrence of windshear events are reported by pilots. However, due to the discontinuity of flight schedules, there are presumably many unreported windshear events when there is no flight, making it difficult to ensure that all the unreported events are all non-windshear events. Hence, one of the key issues for machine-learning-based windshear detection is determining how to correctly distinguish windshear cases from the unreported events. To address this issue, we propose to use a positive and unlabeled learning method in this paper to identify windshear events from unreported cases based on wind velocity data collected by Doppler light detection and ranging (LiDAR) plan position indicator (PPI) scans. An optimal-transport-based optimization model is proposed to distinguish whether a windshear event appears in a sample constructed by several LiDAR PPI scans. Then, a binary classifier is trained to determine whether a sample represents windshear. Numerical experiments based on the observational wind velocity data collected at the Hong Kong International Airport show that the proposed scheme can properly recognize potential windshear cases (windshear cases without pilot reports) and greatly improve windshear detection and prediction accuracy.
format Article
id doaj-art-d52dd164ab614637b6f77fccd66903df
institution DOAJ
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d52dd164ab614637b6f77fccd66903df2025-08-20T02:50:36ZengMDPI AGRemote Sensing2072-42922024-11-011623442310.3390/rs16234423Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear DetectionJie Zhang0Pak-Wai Chan1Michael Kwok-Po Ng2Department of Mathematics, The University of Hong Kong, Pokfulam, Hong KongAviation Weather Services, Hong Kong Observatory, Kowloon, Hong KongDepartment of Mathematics, Hong Kong Baptist University, Kowloon Tong, Hong KongWindshear is a microscale meteorological phenomenon that can be dangerous to aircraft during the take-off and landing phases. Accurate windshear detection plays a significant role in air traffic control. In this paper, we aim to investigate a machine learning method for windshear detection based on previously collected wind velocity data and windshear records. Generally, the occurrence of windshear events are reported by pilots. However, due to the discontinuity of flight schedules, there are presumably many unreported windshear events when there is no flight, making it difficult to ensure that all the unreported events are all non-windshear events. Hence, one of the key issues for machine-learning-based windshear detection is determining how to correctly distinguish windshear cases from the unreported events. To address this issue, we propose to use a positive and unlabeled learning method in this paper to identify windshear events from unreported cases based on wind velocity data collected by Doppler light detection and ranging (LiDAR) plan position indicator (PPI) scans. An optimal-transport-based optimization model is proposed to distinguish whether a windshear event appears in a sample constructed by several LiDAR PPI scans. Then, a binary classifier is trained to determine whether a sample represents windshear. Numerical experiments based on the observational wind velocity data collected at the Hong Kong International Airport show that the proposed scheme can properly recognize potential windshear cases (windshear cases without pilot reports) and greatly improve windshear detection and prediction accuracy.https://www.mdpi.com/2072-4292/16/23/4423light detection and rangingwindshear detectionpositive and unlabeled learningoptimal transportmultiple instance learning
spellingShingle Jie Zhang
Pak-Wai Chan
Michael Kwok-Po Ng
Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection
Remote Sensing
light detection and ranging
windshear detection
positive and unlabeled learning
optimal transport
multiple instance learning
title Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection
title_full Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection
title_fullStr Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection
title_full_unstemmed Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection
title_short Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection
title_sort optimal transport based positive and unlabeled learning method for windshear detection
topic light detection and ranging
windshear detection
positive and unlabeled learning
optimal transport
multiple instance learning
url https://www.mdpi.com/2072-4292/16/23/4423
work_keys_str_mv AT jiezhang optimaltransportbasedpositiveandunlabeledlearningmethodforwindsheardetection
AT pakwaichan optimaltransportbasedpositiveandunlabeledlearningmethodforwindsheardetection
AT michaelkwokpong optimaltransportbasedpositiveandunlabeledlearningmethodforwindsheardetection