Dataset of Tropical Cyclone in a High-Resolution Global Nonhydrostatic Atmospheric Simulation

This dataset comprises a time series of tropical cyclones that were simulated using the high-resolution Nonhydrostatic Icosahedral Atmospheric Model (NICAM). By tracking tropical cyclones over a period of 30 years of climate simulation data, 2463 tracks that encompass the life stages of precursors (pre-TCs), tropical cyclones (TCs), and post-tropical cyclones (post-TCs) were extracted. Each data in the track contains information about the time, longitude, latitude, maximum wind speed at 10m, minimum central pressure, elapsed time since onset, and life-stage label of the tropical cyclone. The number of steps for pre-TCs, TCs, and post-TCs were 45288, 55206, and 37312, respectively. The dataset for each step also consists of atmospheric field data of various physical quantities, including outgoing longwave radiation (OLR) at the top-of-the-atmosphere, sea level pressure (SLP), sea surface temperature (SST), specific humidity at 600 hPa, and zonal and meridional winds at 850 and 200 hPa over a 1000 km square area that encompasses a tropical cyclone at its center. This dataset holds immense potential for developing machine learning models for detecting, predicting the intensity, and predicting the cyclogenesis of tropical cyclones.