Deep Learning-Based Atmospheric Visibility Detection

Atmospheric visibility is a crucial meteorological element impacting urban air pollution monitoring, public transportation, and military security. Traditional visibility detection methods, primarily manual and instrumental, have been costly and imprecise. With advancements in data science and comput...

Full description

Saved in:
Bibliographic Details
Main Authors: Yawei Qu, Yuxin Fang, Shengxuan Ji, Cheng Yuan, Hao Wu, Shengbo Zhu, Haoran Qin, Fan Que
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/15/11/1394
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217149350543360
author Yawei Qu
Yuxin Fang
Shengxuan Ji
Cheng Yuan
Hao Wu
Shengbo Zhu
Haoran Qin
Fan Que
author_facet Yawei Qu
Yuxin Fang
Shengxuan Ji
Cheng Yuan
Hao Wu
Shengbo Zhu
Haoran Qin
Fan Que
author_sort Yawei Qu
collection DOAJ
description Atmospheric visibility is a crucial meteorological element impacting urban air pollution monitoring, public transportation, and military security. Traditional visibility detection methods, primarily manual and instrumental, have been costly and imprecise. With advancements in data science and computing, deep learning-based visibility detection technologies have rapidly emerged as a research hotspot in atmospheric science. This paper systematically reviews the applications of various deep learning models—Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and Transformer networks—in visibility estimation, prediction, and enhancement. Each model’s characteristics and application methods are discussed, highlighting the efficiency of CNNs in spatial feature extraction, RNNs in temporal tracking, GANs in image restoration, and Transformers in capturing long-range dependencies. Furthermore, the paper addresses critical challenges in the field, including dataset quality, algorithm optimization, and practical application barriers, proposing future research directions, such as the development of large-scale, accurately labeled datasets, innovative learning strategies, and enhanced model interpretability. These findings highlight the potential of deep learning in enhancing atmospheric visibility detection techniques, providing valuable insights into the literature and contributing to advances in the field of meteorological observation and public safety.
format Article
id doaj-art-86b9631175ee45b693bde8a90015419e
institution OA Journals
issn 2073-4433
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-86b9631175ee45b693bde8a90015419e2025-08-20T02:08:08ZengMDPI AGAtmosphere2073-44332024-11-011511139410.3390/atmos15111394Deep Learning-Based Atmospheric Visibility DetectionYawei Qu0Yuxin Fang1Shengxuan Ji2Cheng Yuan3Hao Wu4Shengbo Zhu5Haoran Qin6Fan Que7College of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing 211169, ChinaCollege of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing 211169, ChinaYunce Technologies (Beijing) Co., Ltd., Beijing 100085, ChinaSchool of Emergency Management, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaKey Laboratory of Transportation Meteorology of China Meteorological Administration, Nanjing Joint Institute for Atmospheric Sciences, Nanjing 210041, ChinaCollege of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing 211169, ChinaCollege of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing 211169, ChinaCollege of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing 211169, ChinaAtmospheric visibility is a crucial meteorological element impacting urban air pollution monitoring, public transportation, and military security. Traditional visibility detection methods, primarily manual and instrumental, have been costly and imprecise. With advancements in data science and computing, deep learning-based visibility detection technologies have rapidly emerged as a research hotspot in atmospheric science. This paper systematically reviews the applications of various deep learning models—Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and Transformer networks—in visibility estimation, prediction, and enhancement. Each model’s characteristics and application methods are discussed, highlighting the efficiency of CNNs in spatial feature extraction, RNNs in temporal tracking, GANs in image restoration, and Transformers in capturing long-range dependencies. Furthermore, the paper addresses critical challenges in the field, including dataset quality, algorithm optimization, and practical application barriers, proposing future research directions, such as the development of large-scale, accurately labeled datasets, innovative learning strategies, and enhanced model interpretability. These findings highlight the potential of deep learning in enhancing atmospheric visibility detection techniques, providing valuable insights into the literature and contributing to advances in the field of meteorological observation and public safety.https://www.mdpi.com/2073-4433/15/11/1394visibilitydeep learningCNNRNNGANTransformer
spellingShingle Yawei Qu
Yuxin Fang
Shengxuan Ji
Cheng Yuan
Hao Wu
Shengbo Zhu
Haoran Qin
Fan Que
Deep Learning-Based Atmospheric Visibility Detection
Atmosphere
visibility
deep learning
CNN
RNN
GAN
Transformer
title Deep Learning-Based Atmospheric Visibility Detection
title_full Deep Learning-Based Atmospheric Visibility Detection
title_fullStr Deep Learning-Based Atmospheric Visibility Detection
title_full_unstemmed Deep Learning-Based Atmospheric Visibility Detection
title_short Deep Learning-Based Atmospheric Visibility Detection
title_sort deep learning based atmospheric visibility detection
topic visibility
deep learning
CNN
RNN
GAN
Transformer
url https://www.mdpi.com/2073-4433/15/11/1394
work_keys_str_mv AT yaweiqu deeplearningbasedatmosphericvisibilitydetection
AT yuxinfang deeplearningbasedatmosphericvisibilitydetection
AT shengxuanji deeplearningbasedatmosphericvisibilitydetection
AT chengyuan deeplearningbasedatmosphericvisibilitydetection
AT haowu deeplearningbasedatmosphericvisibilitydetection
AT shengbozhu deeplearningbasedatmosphericvisibilitydetection
AT haoranqin deeplearningbasedatmosphericvisibilitydetection
AT fanque deeplearningbasedatmosphericvisibilitydetection