A Modified RNN-Based Deep Learning Method for Prediction of Atmospheric Visibility

被引:15
|
作者
Zang, Zengliang [1 ]
Bao, Xulun [2 ]
Li, Yi [1 ]
Qu, Youming [3 ]
Niu, Dan [4 ]
Liu, Ning [1 ]
Chen, Xisong [4 ]
机构
[1] Natl Univ Def Technol, Coll Meteorol & Oceanog, Changsha 410073, Peoples R China
[2] Southeast Univ, Sch Software, Suzhou 215123, Peoples R China
[3] Hunan Meteorol Informat Ctr, Changsha 410000, Peoples R China
[4] Southeast Univ, Sch Automat, Nanjing 210096, Peoples R China
基金
中国国家自然科学基金;
关键词
atmospheric visibility prediction; spatiotemporal sequence prediction; RNN; improve accuracy; feature fusion; CONTINENTAL RADAR IMAGES; SCALE-DEPENDENCE; PART I; PRECIPITATION; IMPACT; PREDICTABILITY; ALGORITHM; AEROSOLS; QUALITY;
D O I
10.3390/rs15030553
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Accurate atmospheric visibility prediction is of great significance to public transport safety. However, since it is affected by multiple factors, there still remains difficulties in predicting its heterogenous spatial distribution and rapid temporal variation. In this paper, a recursive neural network (RNN) prediction model modified with the frame-hopping transmission gate (FHTG), feature fusion module (FFM) and reverse scheduled sampling (RSS), named SwiftRNN, is developed. The new FHTG is used to accelerate training, the FFM is used for extraction and fusion of global and local features, and the RSS is employed to learn spatial details and improve prediction accuracy. Based on the ground-based monitoring data of atmospheric visibility from the China Meteorological Information Center during 1 January 2018 to 31 December 2020, the SwiftRNN model and two traditional ConvLSTM and PredRNN models are performed to predict hourly atmospheric visibility in central and eastern China at a lead of 12 h. The results show that the SwiftRNN model has better performance in the skill scores of visibility prediction than those of the ConvLSTM and PredRNN model. The averaged structural similarity (SSIM) of predictions at a lead up to 12 h is 0.444, 0.425 and 0.399 for the SwiftRNN, PredRNN and ConvLSTM model, respectively, and the averaged image perception similarity (LPIPS) is 0.289, 0.315 and 0.328, respectively. The averaged critical success index (CSI) of predictions over 1000 m fog area is 0.221, 0.205 and 0.194, respectively. Moreover, the training speed of the SwiftRNN model is 14.3% faster than the PredRNN model. It is also found that the prediction effect of the SwiftRNN model over 1000 m medium grade fog area is significantly improved along with lead times compared with the ConvLSTM and PredRNN model. All above results demonstrate the SwiftRNN model is a powerful tool in predicting atmospheric visibility.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Visual Analytics for RNN-Based Deep Reinforcement Learning
    Wang, Junpeng
    Zhang, Wei
    Yang, Hao
    Yeh, Chin-Chia Michael
    Wang, Liang
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2022, 28 (12) : 4141 - 4155
  • [2] RNN-Based Path Prediction of Obstacle Vehicles With Deep Ensemble
    Min, Kyushik
    Kim, Dongchan
    Park, Jongwon
    Huh, Kunsoo
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2019, 68 (10) : 10252 - 10256
  • [3] Software Fault Prediction Using an RNN-Based Deep Learning Approach and Ensemble Machine Learning Techniques
    Borandag, Emin
    APPLIED SCIENCES-BASEL, 2023, 13 (03):
  • [4] CNN and RNN-based Deep Learning Methods for Digital Signal Demodulation
    Wu, Tian
    PROCEEDINGS OF 2019 INTERNATIONAL CONFERENCE ON IMAGE, VIDEO AND SIGNAL PROCESSING (IVSP 2019), 2019, : 122 - 127
  • [5] DeepCPU: Serving RNN-based Deep Learning Models lOx Faster
    Zhang, Minjia
    Rajbhandari, Samyam
    Wang, Wenhan
    He, Yuxiong
    PROCEEDINGS OF THE 2018 USENIX ANNUAL TECHNICAL CONFERENCE, 2018, : 951 - 965
  • [6] RNN-based Derivation Structure Prediction for SMT
    Zhai, Feifei
    Zhang, Jiajun
    Zhou, Yu
    Zong, Chengqing
    PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2, 2014, : 779 - 784
  • [7] Learning on the Fly: An RNN-Based Online Throughput Prediction Framework for UAV Communications
    Jiang, Yuxuan
    Nihei, Koichi
    Li, Junnan
    Yoshida, Hiroshi
    Kanetomo, Dai
    2020 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC WORKSHOPS), 2020,
  • [8] RNN-Based Subway Passenger Flow Rolling Prediction
    Sha, Shouwei
    Li, Jing
    Zhang, Ke
    Yang, Zifan
    Wei, Zijian
    Li, Xueyan
    Zhu, Xin
    IEEE ACCESS, 2020, 8 : 15232 - 15240
  • [9] Prediction of Water Level in Lakes by RNN-Based Deep Learning Algorithms to Preserve Sustainability in Changing Climate and Relationship to Microcystin
    Ozdemir, Serkan
    Yildirim, Sevgi Ozkan
    SUSTAINABILITY, 2023, 15 (22)
  • [10] RNN-based Method for Fault Diagnosis of Grinding System
    Qu Xing-yu
    Zeng Peng
    Xu Chengcheng
    Fu Dong-dong
    2017 IEEE 7TH ANNUAL INTERNATIONAL CONFERENCE ON CYBER TECHNOLOGY IN AUTOMATION, CONTROL, AND INTELLIGENT SYSTEMS (CYBER), 2017, : 673 - 678