Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50

To address the issue of LiDAR’s low turbulence recognition rate at airports in low-altitude areas, a clear air turbulence recognition method based on an improved Squeeze-and-Excitation Residual Network with 50 layers (SE-ResNet50) is proposed. By introducing the squeeze-and-excitation module and imp...

Full description

Saved in:
Bibliographic Details
Main Authors: Zibo ZHUANG, Jun CHEN, Peilin HE, Hongying ZHANG, Guohua JIN, Xiong LUO
Format: Article
Language:English
Published: China Science Publishing & Media Ltd. (CSPM) 2025-06-01
Series:Leida xuebao
Subjects:
Online Access:https://radars.ac.cn/cn/article/doi/10.12000/JR25042
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849685803070914560
author Zibo ZHUANG
Jun CHEN
Peilin HE
Hongying ZHANG
Guohua JIN
Xiong LUO
author_facet Zibo ZHUANG
Jun CHEN
Peilin HE
Hongying ZHANG
Guohua JIN
Xiong LUO
author_sort Zibo ZHUANG
collection DOAJ
description To address the issue of LiDAR’s low turbulence recognition rate at airports in low-altitude areas, a clear air turbulence recognition method based on an improved Squeeze-and-Excitation Residual Network with 50 layers (SE-ResNet50) is proposed. By introducing the squeeze-and-excitation module and improving the network structure, the model’s excessive sensitivity to feature location is reduced, thereby enabling the network to selectively highlight useful information features during the learning process. A sample dataset was established using measured data from Lanzhou Zhongchuan International Airport; for model training, a balanced dataset was created by extracting an equal amount of weak, moderate, and strong turbulence data based on the turbulence classification level. Under the same experimental conditions, the recognition accuracy of the improved SE-ResNet50 was increased by 7.44%, 6.52%, and 4.11% compared with the convolutional neural network, MobileNetV2, and ShuffleNetV1 networks, respectively. A comparison of the confusion matrices generated by each model showed that the accuracy of the proposed method reached 95%, verifying the feasibility of the proposed method.
format Article
id doaj-art-0a480b25d4904d4dbcada04204994568
institution DOAJ
issn 2095-283X
language English
publishDate 2025-06-01
publisher China Science Publishing & Media Ltd. (CSPM)
record_format Article
series Leida xuebao
spelling doaj-art-0a480b25d4904d4dbcada042049945682025-08-20T03:22:58ZengChina Science Publishing & Media Ltd. (CSPM)Leida xuebao2095-283X2025-06-0114362964010.12000/JR25042R25042Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50Zibo ZHUANG0Jun CHEN1Peilin HE2Hongying ZHANG3Guohua JIN4Xiong LUO5Institute of Aviation Meteorology, Civil Aviation University of China, Tianjin 300300, ChinaCollege of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, ChinaCollege of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, ChinaCollege of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, ChinaSouthwest Institute of Technical Physics, Chengdu 610041, ChinaSouthwest Institute of Technical Physics, Chengdu 610041, ChinaTo address the issue of LiDAR’s low turbulence recognition rate at airports in low-altitude areas, a clear air turbulence recognition method based on an improved Squeeze-and-Excitation Residual Network with 50 layers (SE-ResNet50) is proposed. By introducing the squeeze-and-excitation module and improving the network structure, the model’s excessive sensitivity to feature location is reduced, thereby enabling the network to selectively highlight useful information features during the learning process. A sample dataset was established using measured data from Lanzhou Zhongchuan International Airport; for model training, a balanced dataset was created by extracting an equal amount of weak, moderate, and strong turbulence data based on the turbulence classification level. Under the same experimental conditions, the recognition accuracy of the improved SE-ResNet50 was increased by 7.44%, 6.52%, and 4.11% compared with the convolutional neural network, MobileNetV2, and ShuffleNetV1 networks, respectively. A comparison of the confusion matrices generated by each model showed that the accuracy of the proposed method reached 95%, verifying the feasibility of the proposed method.https://radars.ac.cn/cn/article/doi/10.12000/JR25042light detection and ranging (lidar)eddy dissipation rate (edr)clear air turbulenceresidual network (resnet)deep learning
spellingShingle Zibo ZHUANG
Jun CHEN
Peilin HE
Hongying ZHANG
Guohua JIN
Xiong LUO
Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50
Leida xuebao
light detection and ranging (lidar)
eddy dissipation rate (edr)
clear air turbulence
residual network (resnet)
deep learning
title Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50
title_full Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50
title_fullStr Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50
title_full_unstemmed Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50
title_short Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50
title_sort research on lidar clear air turbulence recognition based on improved se resnet50
topic light detection and ranging (lidar)
eddy dissipation rate (edr)
clear air turbulence
residual network (resnet)
deep learning
url https://radars.ac.cn/cn/article/doi/10.12000/JR25042
work_keys_str_mv AT zibozhuang researchonlidarclearairturbulencerecognitionbasedonimprovedseresnet50
AT junchen researchonlidarclearairturbulencerecognitionbasedonimprovedseresnet50
AT peilinhe researchonlidarclearairturbulencerecognitionbasedonimprovedseresnet50
AT hongyingzhang researchonlidarclearairturbulencerecognitionbasedonimprovedseresnet50
AT guohuajin researchonlidarclearairturbulencerecognitionbasedonimprovedseresnet50
AT xiongluo researchonlidarclearairturbulencerecognitionbasedonimprovedseresnet50