Low-visibility phenomena strongly impact the environment,as well as transportation,aviation and other fields that are closely related to people's livelihoods;thus,they represent important ecological issues of soci...Low-visibility phenomena strongly impact the environment,as well as transportation,aviation and other fields that are closely related to people's livelihoods;thus,they represent important ecological issues of social concern.Based on observation data concerning low-visibility phenomena derived from 105 national meteorological stations in Xinjiang,China over the past 20 years,we systematically analyzed the differences between manual and instrument observations for six types of low-visibility phenomena,with a focus on exploring their spatiotemporal distribution characteristics using instrument data.The results revealed that low-visibility phenomena were dominated by fog-and haze-related events(mist,fog,and haze)in northern Xinjiang and dust-related events(dust storms,blowing sand,and floating dust)in southern Xinjiang,with transitional characteristics observed in eastern Xinjiang.Compared with manual observations,the instrument measurements significantly improved the fine-scale low-visibility phenomenon identification process.On the basis of the instrument observation data,spatial-dimension analysis results indicated that low-visibility phenomena in Xinjiang were significantly influenced by terrain factors.Constrained by the Tianshan Mountains,haze-like phenomena formed a core agglomeration area in northern Xinjiang,whereas dust-and sand-related phenomena radiated outward,with the Taklimakan Desert at the center.Moreover,the gripping effect of the terrain promoted dust transmission along low-altitude channels.Temporally,fog-and haze-related phenomena occurred mainly during autumn and winter,and the proportion of these events decreased from 76.7%to 55.1%.The fog-and haze-related phenomena demonstrated a U-shaped rebound trend,while the proportion of mist phenomena decreased by 34.2%.Dust storms occurred during spring,accounting for 23.3%to 44.9%of all storms.Instrument measurement technology has the advantages of high spatial and temporal resolutions and multiparameter coordination but provides a limited dust-haze mixed-pollution identification capacity.This study provides crucial reference data for enhancing the understanding of low-visibility events in Xinjiang and the potential responses while improving the accuracy of pollution source tracking and meteorological process diagnosis tasks.展开更多
Video imagery enables both qualitative characterization and quantitative retrieval of low-visibility conditions.These phenomena exhibit complex nonlinear dependencies on atmospheric processes,particularly during moist...Video imagery enables both qualitative characterization and quantitative retrieval of low-visibility conditions.These phenomena exhibit complex nonlinear dependencies on atmospheric processes,particularly during moisture-driven weather events such as fog,rain,and snow.To address this challenge,we propose a dual-branch neural architecture that synergistically processes optical imagery and multi-source meteorological data(temperature,humidity,and wind speed).The framework employs a convolutional neural network(CNN)branch to extract visibility-related visual features from video imagery sequences,while a parallel artificial neural network(ANN)branch decodes nonlinear relationships among the meteorological factors.Cross-modal feature fusion is achieved through an adaptive weighting layer.To validate the framework,multimodal Backpropagation-VGG(BP-VGG)and Backpropagation-ResNet(BP-ResNet)models are developed and trained/tested using historical imagery and meteorological observations from Nanjing Lukou International Airport.The results demonstrate that the multimodal networks reduce retrieval errors by approximately 8%–10%compared to unimodal networks relying solely on imagery.Among the multimodal models,BP-ResNet exhibits the best performance with a mean absolute percentage error(MAPE)of 8.5%.Analysis of typical case studies reveals that visibility fluctuates rapidly while meteorological factors change gradually,highlighting the crucial role of high-frequency imaging data in intelligent visibility retrieval models.The superior performance of BP-ResNet over BP-VGG is attributed to its use of residual blocks,which enables BP-ResNet to excel in multimodal processing by effectively leveraging data complementarity for synergistic improvements.This study presents an end-to-end intelligent visibility inversion framework that directly retrieves visibility values,enhancing its applicability across industries.However,while this approach boosts accuracy and applicability,its performance in critical low-visibility scenarios remains suboptimal,necessitating further research into more advanced retrieval techniques—particularly under extreme visibility conditions.展开更多
基金supported by the Central Government Guidance Funds for Local Science and Technology Development Program(grant no.ZYYD2025ZY21)the Science and Technology Plan Project of the Xinjiang Production and Construction Corps(2023AB036)+1 种基金the Xinjiang Meteorological Bureau High-Level Key Talent Programthe Natural Science Foundation of the Xinjiang Uygur Autonomous Region(2023D01A17 and 2025D01A109).
文摘Low-visibility phenomena strongly impact the environment,as well as transportation,aviation and other fields that are closely related to people's livelihoods;thus,they represent important ecological issues of social concern.Based on observation data concerning low-visibility phenomena derived from 105 national meteorological stations in Xinjiang,China over the past 20 years,we systematically analyzed the differences between manual and instrument observations for six types of low-visibility phenomena,with a focus on exploring their spatiotemporal distribution characteristics using instrument data.The results revealed that low-visibility phenomena were dominated by fog-and haze-related events(mist,fog,and haze)in northern Xinjiang and dust-related events(dust storms,blowing sand,and floating dust)in southern Xinjiang,with transitional characteristics observed in eastern Xinjiang.Compared with manual observations,the instrument measurements significantly improved the fine-scale low-visibility phenomenon identification process.On the basis of the instrument observation data,spatial-dimension analysis results indicated that low-visibility phenomena in Xinjiang were significantly influenced by terrain factors.Constrained by the Tianshan Mountains,haze-like phenomena formed a core agglomeration area in northern Xinjiang,whereas dust-and sand-related phenomena radiated outward,with the Taklimakan Desert at the center.Moreover,the gripping effect of the terrain promoted dust transmission along low-altitude channels.Temporally,fog-and haze-related phenomena occurred mainly during autumn and winter,and the proportion of these events decreased from 76.7%to 55.1%.The fog-and haze-related phenomena demonstrated a U-shaped rebound trend,while the proportion of mist phenomena decreased by 34.2%.Dust storms occurred during spring,accounting for 23.3%to 44.9%of all storms.Instrument measurement technology has the advantages of high spatial and temporal resolutions and multiparameter coordination but provides a limited dust-haze mixed-pollution identification capacity.This study provides crucial reference data for enhancing the understanding of low-visibility events in Xinjiang and the potential responses while improving the accuracy of pollution source tracking and meteorological process diagnosis tasks.
基金Foundation of Key Laboratory of Smart Earth(KF2023ZD03-02)China Meteorological Administration Innovation development project(CXFZ2025J116)+1 种基金National Natural Science Foundation of China(42205197)Basic Research Fund of CAMS(2022Y023,2022Y025)。
文摘Video imagery enables both qualitative characterization and quantitative retrieval of low-visibility conditions.These phenomena exhibit complex nonlinear dependencies on atmospheric processes,particularly during moisture-driven weather events such as fog,rain,and snow.To address this challenge,we propose a dual-branch neural architecture that synergistically processes optical imagery and multi-source meteorological data(temperature,humidity,and wind speed).The framework employs a convolutional neural network(CNN)branch to extract visibility-related visual features from video imagery sequences,while a parallel artificial neural network(ANN)branch decodes nonlinear relationships among the meteorological factors.Cross-modal feature fusion is achieved through an adaptive weighting layer.To validate the framework,multimodal Backpropagation-VGG(BP-VGG)and Backpropagation-ResNet(BP-ResNet)models are developed and trained/tested using historical imagery and meteorological observations from Nanjing Lukou International Airport.The results demonstrate that the multimodal networks reduce retrieval errors by approximately 8%–10%compared to unimodal networks relying solely on imagery.Among the multimodal models,BP-ResNet exhibits the best performance with a mean absolute percentage error(MAPE)of 8.5%.Analysis of typical case studies reveals that visibility fluctuates rapidly while meteorological factors change gradually,highlighting the crucial role of high-frequency imaging data in intelligent visibility retrieval models.The superior performance of BP-ResNet over BP-VGG is attributed to its use of residual blocks,which enables BP-ResNet to excel in multimodal processing by effectively leveraging data complementarity for synergistic improvements.This study presents an end-to-end intelligent visibility inversion framework that directly retrieves visibility values,enhancing its applicability across industries.However,while this approach boosts accuracy and applicability,its performance in critical low-visibility scenarios remains suboptimal,necessitating further research into more advanced retrieval techniques—particularly under extreme visibility conditions.
