International Journal of Big Data Intelligent Technology, 2026, 7(2); doi: 10.38007/IJBDIT.2026.070214.
Yiding Zhao, Chunwei Zhang
School of Intelligent Construction and Hydraulic Engineering, Chuzhou University, Chuzhou, China
The mesoscale processes of typhoons in the deep sea are an important way for mesoscale kinetic energy to be dissipated into small-scale turbulence. The wind field of these typhoons is also the main initial field and real-time assimilation data source for current mesoscale meteorological models. Traditional ground-based and sea-based observation methods are difficult to provide complete information on the horizontal wind speed field of typhoons in the deep sea. This study proposes a method for reconstructing the horizontal wind speed field of typhoons in the deep sea based on ERA5 global reanalysis data, and establishes a temporal and spatial matching database for the horizontal wind speed field of typhoons in the Northwest Pacific deep sea. The study shows that this database can effectively reconstruct the gradient change characteristics of the horizontal wind speed along the radial direction of typhoons.
Deep-Sea Typhoon; Horizontal Wind Speed; Global Reanalysis Data
Yiding Zhao, Chunwei Zhang. A Study on the Reconstruction of the Horizontal Wind Speed Field of Deep-Sea Typhoons Based on Global Reanalysis Data. International Journal of Big Data Intelligent Technology (2026), Vol. 7, Issue 2: 140-145. https://doi.org/10.38007/IJBDIT.2026.070214.
[1] Aleskerova A, Kubryakov A, Stanichny S, et al. Characteristics of topographic submesoscale eddies off the Crimea coast from high-resolution satellite optical measurements[J]. Ocean Dynamics, 2021, 71(6): 655-677.
[2] Ren H, Ke S, Dudhia J, et al. Wind disaster assessment of landfalling typhoons in different regions of China over 2004-2020[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2022, 228: 105084.
[3] Zhuo J, Tan Z. Physics-augmented deep learning to improve tropical cyclone intensity and size estimation from satellite imagery[J]. Monthly Weather Review, 2021, 149(7): 2097-2113.
[4] Nezhad M M, Heydari A, Pirshayan E, et al. A novel forecasting model for wind speed assessment using sentinel family satellites images and machine learning method[J]. Renewable Energy, 2021, 179: 2198-2211.
[5] Campos R M, Gramcianinov C B, de Camargo R, et al. Assessment and calibration of ERA5 severe winds in the Atlantic Ocean using satellite data[J]. Remote Sensing, 2022, 14(19): 4918.
[6] Gao Y, Wang X. Analysis of the response relationship between PWV and meteorological parameters using combined GNSS and ERA5 data: A case study of typhoon Lekima[J]. Atmosphere, 2024, 15(10): 1249.
[7] Lv T, Yu H, Lin L, et al. Research on typhoon prediction by integrating numerical simulation and deep learning methods[J]. Atmosphere, 2025, 16(1): 111.
[8] Xiong J, Yu F, Fu C, et al. Evaluation and improvement of the ERA5 wind field in typhoon storm surge simulations[J]. Applied Ocean Research, 2022, 118: 103000.
[9] Tan J, Yang Q, Hu J, et al. Tropical cyclone intensity estimation using Himawari-8 satellite cloud products and deep learning[J]. Remote Sensing, 2022, 14(4): 812.
[10] Wang C, Li X. Deep learning in extracting tropical cyclone intensity and wind radius information from satellite infrared images—A review[J]. Atmospheric and Oceanic Science Letters, 2023, 16(4): 100373.