Reconstruction of Typhoon-Induced Ocean Thermal Structures Using Deep Learning and Multi-Source Satellite Data with News Impact Analysis

被引:0
|
作者
Zhao, Yang [1 ]
Gao, Ziming [2 ]
Fan, Ruimin [2 ]
Yu, Fangjie [2 ,3 ]
Zhang, Xinglong [3 ]
Tang, Junwu [3 ]
Chen, Ge [2 ,3 ]
机构
[1] Ocean Univ China, Coll Literature & Journalism, Qingdao 266100, Peoples R China
[2] Ocean Univ China, Coll Marine Technol, Fac Informat Sci & Engn, Qingdao 266100, Peoples R China
[3] Laoshan Lab, Qingdao 266061, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 21期
关键词
typhoon; three-dimensional thermal structure reconstruction; ocean dynamics; fully connected transformer network; cross-validation; sensitivity analysis; Argo data; content analysis; INTENSITY;
D O I
10.3390/app142110050
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Reconstructing the three-dimensional thermal structure of the ocean under typhoon conditions presents significant challenges due to the scarcity of observational data, particularly in subsurface regions, and the limitations of existing observation methods in terms of spatial and temporal resolution. Accurate reconstruction of these structures is crucial for understanding the energy exchange between the ocean and typhoons, as this exchange directly influences typhoon intensity and trajectory. To address these challenges, this study introduces a fully connected transformer network (FCT), which integrates fully connected layers with a transformer model. The FCT model leverages the attention mechanisms inherent in the transformer architecture to effectively extract and integrate multi-scale ocean dynamical features. Using data from Typhoon Lekima in 2019, this study reconstructs ocean thermal structures at various depths and achieves an RMSE of 1.03 degrees C and an MAE of 0.83 degrees C when validated against Argo data. Furthermore, the model's robustness was demonstrated through five-fold cross-validation, with the validation loss exhibiting minor fluctuations across folds but remaining stable overall, with an average validation loss of 0.986 degrees C, indicating the model's generalizability. Sensitivity analysis also revealed the model's resilience to variations in key input variables, showing minimal impact on output even with perturbations of up to 10% in input data. In addition, the study incorporates content analysis of typhoon-related news reports from 2011 to 2020, revealing a predominance of political topics, which underscores the central role of government in disaster response, with economic and ecological topics following. This integrated approach not only enhances our understanding of the interactions between ocean thermal structures and typhoon dynamics but also provides valuable insights into the societal impacts of typhoons, as reflected in media coverage, contributing to improved disaster management strategies.
引用
收藏
页数:13
相关论文
共 50 条
  • [41] Application of human-centric digital twins: Predicting outdoor thermal comfort distribution in Singapore using multi-source data and machine learning
    Liu, Xin
    Gou, Zhonghua
    Yuan, Chao
    URBAN CLIMATE, 2024, 58
  • [42] A comparative analysis of different pixel and object-based classification algorithms using multi-source high spatial resolution satellite data for LULC mapping
    Balha, Akanksha
    Mallick, Javed
    Pandey, Suneel
    Gupta, Sandeep
    Singh, Chander Kumar
    EARTH SCIENCE INFORMATICS, 2021, 14 (04) : 2231 - 2247
  • [43] Deep and machine learning prediction of forest above-ground biomass using multi-source remote sensing data in coniferous planted forests in Iran
    Ali, Hassan
    Mohammadi, Jahangir
    Jouibary, Shaban Shataee
    EUROPEAN JOURNAL OF FOREST RESEARCH, 2024, 143 (06) : 1731 - 1745
  • [44] A comparative analysis of different pixel and object-based classification algorithms using multi-source high spatial resolution satellite data for LULC mapping
    Akanksha Balha
    Javed Mallick
    Suneel Pandey
    Sandeep Gupta
    Chander Kumar Singh
    Earth Science Informatics, 2021, 14 : 2231 - 2247
  • [45] An accurate prediction of the physicochemical properties of traditional Chinese medicine granules using a multi-source data model fusion strategy based on deep ensemble learning algorithms
    Wan, Xinhao
    Luo, Xiaorong
    Yang, Ming
    Li, Yuanhui
    Zhong, Zhijian
    Tao, Qing
    Wu, Zhenfeng
    MICROCHEMICAL JOURNAL, 2025, 209
  • [46] Assessing the potential hydrological impact of the Gibe III Dam on Lake Turkana water level using multi-source satellite data. (vol 16, pg 3561, 2012)
    Velpuri, N. M.
    Senay, G. B.
    HYDROLOGY AND EARTH SYSTEM SCIENCES, 2012, 16 (10) : 3645 - 3645
  • [47] Evaluation of spatial patterns accuracy in identifying built-up areas within risk zones using deep learning, RGB aerial imagery, and multi-source GIS data
    Vitale, Alessandro
    Salvo, Carolina
    Lamonaca, Francesco
    ACTA IMEKO, 2023, 12 (04): : 11 - 11
  • [48] MHRA-MS-3D-ResNet-BiLSTM: A Multi-Head-Residual Attention-Based Multi-Stream Deep Learning Model for Soybean Yield Prediction in the US Using Multi-Source Remote Sensing Data
    Fathi, Mahdiyeh
    Shah-Hosseini, Reza
    Moghimi, Armin
    Arefi, Hossein
    REMOTE SENSING, 2025, 17 (01)
  • [49] Decision tree-based machine learning models for above-ground biomass estimation using multi-source remote sensing data and object-based image analysis
    Tamiminia, Haifa
    Salehi, Bahram
    Mahdianpari, Masoud
    Beier, Colin M.
    Johnson, Lucas
    Phoenix, Daniel B.
    Mahoney, Michael
    GEOCARTO INTERNATIONAL, 2022, 37 (26) : 12763 - 12791
  • [50] A Deep Learning-Based Method for the Semi-Automatic Identification of Built-Up Areas within Risk Zones Using Aerial Imagery and Multi-Source GIS Data: An Application for Landslide Risk
    Francini, Mauro
    Salvo, Carolina
    Viscomi, Antonio
    Vitale, Alessandro
    REMOTE SENSING, 2022, 14 (17)