Assessment of Medicane Helios meteo-marine parameters using a machine learning approach

被引:1
|
作者
Scardino, Giovanni [1 ]
Kushabaha, Alok [1 ,2 ]
Sabato, Gaetano [1 ]
Tarascio, Sebastiano [3 ]
Scicchitano, Giovanni [1 ]
机构
[1] Univ Bari Aldo Moro, Dept Earth & Geoenvironm Sci, I-70125 Bari, Italy
[2] IUSS Sch Adv Studies, Pavia, Italy
[3] Univ Catania, Dept Biol Geol & Environm Sci, I-95129 Catania, Italy
关键词
Neural Network; storm surge; flooding; tide phases; wave height; SEA; HURRICANE; CYCLONES;
D O I
10.1109/MetroSea58055.2023.10317554
中图分类号
P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
Medicanes represent a unique weather phenomenon in the Mediterranean Sea, combining features of both tropical and extra-tropical cyclones. The recent Medicane Helios induced a severe windstorm that caused storm surges and flooding impacting coastal regions of southeastern Sicily. To assess the hydrodynamic parameters, such as tide phase, storm surge and wave flow induced by Medicane "Helios", an innovative machine learning system called LEUCOTEA was used. This system takes into account a combined approach of Geomorphological surveys, Convolution Neural Network, and Optical Flow techniques with real-time video records. The system provides the values of tide phases, storm surge and wave flow that could be useful for policymakers and environmental managers as a valuable tool to assess the potential coastal risks and to develop appropriate mitigation and adaptation strategies.
引用
收藏
页码:508 / 512
页数:5
相关论文
共 50 条
  • [41] THE EXPLORATION OF A MACHINE LEARNING APPROACH FOR THE ASSESSMENT OF LEARNING STYLES CHANGES
    Wei, Yueer
    Yang, Qingxia
    Chen, Jiangping
    Hu, Jie
    MECHATRONIC SYSTEMS AND CONTROL, 2018, 46 (03): : 121 - 126
  • [42] Using Machine Learning to Predict Consolidation Parameters
    Thurmond, Patrick A.
    Worley, H. Clay
    GEO-CONGRESS 2024: GEOTECHNICAL DATA ANALYSIS AND COMPUTATION, 2024, 352 : 445 - 453
  • [43] Global Marine Isochore Estimates Using Machine Learning
    Lee, Taylor R.
    Phrampus, Benjamin J.
    Obelcz, Jeffrey
    Wood, Warren T.
    Skarke, Adam
    GEOPHYSICAL RESEARCH LETTERS, 2020, 47 (18)
  • [44] Automatic void content assessment of composite laminates using a machine-learning approach
    Machado, Joao M.
    Trvares, Joao Manuel R. S. M.
    Camanho, Pedro P.
    Correia, Nuno
    COMPOSITE STRUCTURES, 2022, 288
  • [45] Assessment of crop insect damage using unmanned aerial systems: A machine learning approach
    Puig, E.
    Gonzalez, F.
    Hamilton, G.
    Grundy, P.
    21ST INTERNATIONAL CONGRESS ON MODELLING AND SIMULATION (MODSIM2015), 2015, : 1420 - 1426
  • [46] Probabilistic failure assessment of oil and gas gathering pipelines using machine learning approach
    Li, Xinhong
    Liu, Yabei
    Zhang, Renren
    Zhang, Nan
    RELIABILITY ENGINEERING & SYSTEM SAFETY, 2025, 256
  • [47] PhageLeads: Rapid Assessment of Phage Therapeutic Suitability Using an Ensemble Machine Learning Approach
    Yukgehnaish, Kumarasan
    Rajandas, Heera
    Parimannan, Sivachandran
    Manickam, Ravichandran
    Marimuthu, Kasi
    Petersen, Bent
    Clokie, Martha R. J.
    Millard, Andrew
    Sicheritz-Ponten, Thomas
    VIRUSES-BASEL, 2022, 14 (02):
  • [48] A Machine Learning Approach and Methodology for Solar Radiation Assessment Using Multispectral Satellite Images
    Verma P.
    Patil S.
    Annals of Data Science, 2023, 10 (04) : 907 - 932
  • [49] Sustainable development scale of housing estates: An economic assessment using machine learning approach
    Tang, Bo-sin
    Ho, Winky K. O.
    Wong, Siu Wai
    SUSTAINABLE DEVELOPMENT, 2021, 29 (04) : 708 - 718
  • [50] Cardiovascular Risk Assessment: An Interpretable Machine Learning Approach
    Paredes, S.
    Rocha, T.
    de Carvalho, P.
    Roseiro, I.
    Henriques, J.
    Sousa, J.
    INTERNATIONAL CONFERENCE ON BIOMEDICAL AND HEALTH INFORMATICS 2022, ICBHI 2022, 2024, 108 : 95 - 103