Validating Machine Learning Retrievals of the Cloud-Top Droplet Effective Radius Over Oceans That Account for 3D Radiative Transfer Effects

Bispectral retrievals of the droplet effective radius (r_e) from instruments such as MODIS are widely utilized to study cloud microphysics in marine boundary layer clouds. These retrievals are known to have systematic errors due to cloud heterogeneity. Here, we develop a neural network regression to retrieve cloud-top r_e at a solar zenith angle of 30° and nadir viewing using MODIS. The neural network regression is trained on 3D radiative transfer simulations of quasi-adiabatic stochastically generated clouds and corrects relative errors in r_e with respect to cloud-top with an r² of 0.88. The neural network regression produces unbiased retrievals of cloud-top r_e against large eddy simulation cloud fields where the bispectral retrieval has biases reaching +100%. The neural network regression reduces retrieval biases against airborne observations of cumulus from CAMP²Ex from +100% to +40%, and marginally improves already good consistency against stratocumulus sampled during VOCALS. A cross-comparison technique for assessing statistical remote sensing retrievals is introduced. The neural network regression explains 63% and 91% of the variance in the differences between MODIS 1.6 and 2.1 μm retrievals for Overcast and partially cloudy pixels (PCL) and 42% and 76% for the 2.1 and 3.7 μm differences, respectively. Residual spectral inconsistency is partially attributed to precipitation-sized particles using radar observations. Regional averages of the operational MODIS r_e exceed the cloud-top r_e predicted by the neural network by +50% for Overcast pixels in the tropics and a consistent +70% for PCL pixels. Errors in bispectral retrievals due to heterogeneity are nonrandom at both the cloud and climate scale.