Application of an Artificial Neural Network Simulation for Top-of-Atmosphere Radiative Flux Estimation from CERES

摘要: Abstract The Clouds and the Earth's Radiant Energy System (CERES) provides top-of-atmosphere (TOA) radiative flux estimates from shortwave (SW) longwave (LW) radiance measurements by applying empirical angular distribution models (ADMs) for scene types defined coincident high-resolution imager-based cloud retrievals. In this study, CERES ADMs are simulated using a feed-forward error back-propagation (FFEB) artificial neural network (ANN) simulation to provide means of estimating TOA SW LW fluxes different in absence imager measurements. all cases, ANN-derived deviate less than 0.3 W m−2, on average, show smaller dependence viewing geometry derived Earth Radiation Budget Experiment (ERBE). significant improvement accuracy over ERBE-like when compared regionally.