Physics-Driven Machine Learning Algorithm Facilitates Multilayer Cloud Property Retrievals From Geostationary Passive Imager Measurements

A physics-driven machine learning (ML) algorithm that integrates radiative transfer model (RTM) simulation and ML techniques has been developed to facilitate multilayer cloud property retrievals from Advanced Himawari Imager (AHI) measurements based on the geostationary satellite Himawari-8. A theoretically sensitive study revealed that integrating RTM-simulated clear-sky radiances into the retrieval model holds substantial potential to enhance multilayer cloud property retrieval. Thus, a convolutional neural network (CNN) model called CNN_TL was designed for the simultaneous retrieval of ice and water properties in multilayer clouds based on the combined use of visible/near-infrared (VNIR) and thermal infrared (TIR) measurements and RTM-simulated clear-sky radiances as predictors. The CNN_TL model was initially trained using the simulated datasets generated by RTM to gain better model initiation and generalization and further tuned using the standard references from collocated active sensor products through the transfer learning (TL) method. Validation on independent dataset shows CNN_TL-retrieved cloud top heights agreeing well with active sensor products for both overlaying ice and underlying water (root mean square errors (RMSEs): 1.219 and 0.863 km), substantially outperforming AHI official products. In addition, due to separate retrieval of ice and water microphysical properties in multilayer clouds, CNN_TL retrieved overlying ice microphysical properties exhibited a substantial correlation with active sensor products, showing Pearson coefficients of above 0.78. Notably, the CNN_TL model outperformed the purely ML-based model, demonstrating the advantage of integrating physical RTM simulation and ML techniques through the TL method. Finally, a novel investigation into the spatial distribution of multilayer cloud properties across full disk is conducted, revealing distinct seasonal variations and notable latitudinal dependencies.