Machine Learning-Based Estimation of Tropical Cyclone Intensity from Advanced Technology Microwave Sounder Using a U-Net Algorithm

• Published in: Remote sensing (Basel, Switzerland) Vol. 16; no. 1; p. 77
• Main Authors: Liang, Zichao, Lee, Yong-Keun, Grassotti, Christopher, Lin, Lin, Liu, Quanhua
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2024
• Subjects: Aircraft; Algorithms; Artificial intelligence; Artificial satellites in remote sensing; Atlantic Ocean; ATMS; Brightness temperature; climate; Comparative analysis; Cyclones; Deep learning; Environmental aspects; ERA5; Estimates; eyewall; Forecasts and trends; hurricanes; Identification and classification; Labels; Machine learning; Neural networks; Pacific Ocean; prediction; Pressure; Storm damage; surface pressure; Surface wind; surface wind speed; tropical cyclone; Tropical cyclones; Water temperature; Weather forecasting; Wind; Wind speed; United States; United States > US; Atlantic Ocean; Pacific Ocean
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs16010077

A U-Net algorithm was used to retrieve surface pressure and wind speed over the ocean within tropical cyclones (TCs) and their neighboring areas using NOAA-20 Advanced Technology Microwave Sounder (ATMS) reprocessed Sensor Data Record (SDR) brightness temperatures (TBs) and geolocation information. For TC locations, International Best Track Archive for Climate Stewardship (IBTrACS) data have been used over the North Atlantic Ocean and West Pacific Ocean between 2018 and 2021. The European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5) surface pressure and wind speed were employed as reference labels. Preliminary results demonstrated that the visualizations for wind speed and pressure matched the prediction and ERA5 location. The residual biases and standard deviations between the predicted and reference labels were about 0.15 m/s and 1.95 m/s, respectively, for wind speed and 0.48 hPa and 2.67 hPa, respectively, for surface pressure, after applying cloud screening for each ATMS pixel. This indicates that the U-Net model is effective for surface wind speed and surface pressure estimates over general ocean conditions.