All-day cloud property and occurrence probability dataset based on satellite remote sensing data

The cloud property database and different type cloud occurrence probability datasets are helpful for meteorological research and application, as well as climate comprehension. Building on the foundation of CldNet with all-day cloud type recognition capability, CldNet Version 2.0 (CldNetV2) is proposed. This enhanced version leverages transfer learning and model parameter sharing techniques to not only classify cloud types but also predict additional cloud properties. Datasets with multiple cloud properties obtained by CldNetV2 make up for the lack of current Himawari cloud product at nighttime. Meanwhile, the dataset of different cloud type occurrence probabilities is statistically obtained on three time scales including annual, seasonal, and monthly, and more importantly, the dataset distinguishes between all day, daytime, and nighttime. In addition, the reliability of our cloud product is independently validated by the cloud properties from CALIPSO trajectories, ERA5 cloud cover fraction and the visualization of cloud property distribution and typhoon eye track during typhoons. Further more, the all-day cloud property and occurrence probability dataset for meteorological environment assessment has been publicly released.