Development and Evaluation of a New Correlated K-Distribution Scheme for BCC_RAD Radiative Transfer Model

With the significant increase in the abundance of greenhouse gases in the atmosphere over recent decades, more of the weak gaseous absorption bands are required to be incorporated in the gas optics model to improve the computational accuracy of radiation, and thus the warming effect of gases. Based on the latest HITRAN2020 spectroscopic data, a new 36-band correlated k-distribution (CKD) scheme is developed with high spectral band resolution for radiative transfer model. By considering errors of both radiative fluxes and atmospheric heating rates, optimizations are made to select the overlapping method and the number of k-distribution quadrature points in each band. The new CKD model exhibits a remarkable improvement in heating rates and radiative fluxes relative to the previous 17-band model when performing the identical radiative transfer calculations under 50 atmospheric profiles. The heating rate root-mean-square errors (RMSEs) of the 36-band model are 0.101 and 0.075 K d-1 below 4 hPa for longwave and shortwave, respectively, when validated against the line-by-line benchmarks. The longwave irradiance RMSE is 0.47 W m-2 at the top of atmosphere, and the shortwave RMSE is 2.15 W m-2 at the surface. Furthermore, the cases simulating radiative forcing induced by varying gas concentrations demonstrate the ability of the 36-band model to study the warming effect of greenhouse gases.