A Neural Network Parametrization of Volumetric Cloud Fraction Profiles Using Satellite Observations and MERRA‐2 Reanalysis Meteorological Data

Abstract Clouds play a crucial role in regulating the hydrologic cycle and Earth's radiative energy budget, yet they are often poorly represented in global climate models (GCMs). This study applies deep machine learning (DML) to develop a physical parameterization of volumetric cloud fraction (VCF), the fraction of a 3‐D grid volume occupied by clouds using satellite lidar‐radar measurements. The DML learns the complex relationships between observed VCF profiles and collocated meteorological variables from MERRA‐2 reanalysis data. Our results show that the neural network (NN), particularly a sequence‐to‐sequence long short‐term memory (LSTM) network with a customized loss function, effectively captures underlying cloud physical processes. The DML prediction outperforms MERRA‐2 reanalysis in representing low‐level clouds in tropical and subtropical regions and low‐ and middle‐level clouds over midlatitude storm‐track and improves VCF histograms. These improvements are reflected in vertical distributions of zonally, meridionally, and globally averaged VCFs, geographic distributions of low‐, middle‐, and high‐level clouds, and seasonal variations in monthly mean VCF. Furthermore, the DML predictions effectively capture El Niño‐Southern Oscillation (ENSO) and other interannual variations. The NN parameterization is further evaluated through sensitivity analysis, where a single predictor is perturbed at a time. This reveals that relative humidity (RH) is the dominant factor influencing variations in globally averaged VCF at low and middle altitudes, followed by temperature. At higher altitudes, temperature becomes the primary driver of VCF through its effect on RH. Increases in pressure vertical velocity ( ω ) are associated with decreases in VCF, though their effect is minor compared to RH and temperature.