Top-of-atmosphere (TOA) outgoing longwave radiation (OLR), a key component of the Earth’s energy budget, serves as a diagnostic of the Earth’s climate system response to incoming solar radiation. However, existing products are typically estimated using the traditional two-step method, which may bring extra uncertainties. This paper presents a direct machine learning method to estimate TOA OLR by directly linking Himawari-8/Advanced Himawari Imager (AHI) TOA radiances with TOA OLR determined by Clouds and the Earth’s Radiant Energy System (CERES) and other information, such as the viewing geometry. Models are built separately under clear- and cloudy-sky conditions using a gradient-boosting regression tree. Independent test results show that the root mean square errors (RMSEs) of the clear-sky and cloudy-sky models for estimating instantaneous values are 7.46 W/m² (3.0%) and 11.61 W/m² (5.8%), respectively. Daily results are obtained by averaging all the instantaneous results in one day. Intercomparisons of the daily results with CERES TOA OLR data show that the RMSE of the estimated AHI OLR is ~6 W/m² (3%). The developed high-resolution AHI TOA OLR dataset will be beneficial in analyzing the regional energy budget.

Five global monthly top-of-atmosphere (TOA) outgoing longwave radiation (OLR) products are evaluated in this study, including the products derived from the High-Resolution Infrared Radiation Sounder (HIRS), Clouds and the Earth’s Radiant Energy System (CERES), Advanced Very High Resolution Radiometer (AVHRR), the CM SAF cLoud, Albedo and surface RAdiation dataset from AVHRR data (CLARA), and the Global Energy and Water Cycle EXchanges (GEWEX) project. Results show that overall there is good consistency among these five products. Larger differences are found between GEWEX and CERES (HIRS) after (before) 2000 (RMSE ~ 5 W/m²), particularly in the tropical regions. In terms of global mean values, GEWEX shows large differences with the other products from the year 1992 to 2002, and CLARA shows large differences from the year 1979 to 1981, which are more obvious in the global ocean values. Large discrepancies among these products exist at low latitudinal bands, particularly before the year 2000. Australia and Asia (mid–low latitude part) are two typical regions in which larger differences are found.

The Tibetan Plateau (TP) plays a crucial role in the global climate system, yet long-term trends in its top-of-atmosphere (TOA) radiation budget remain poorly understood. Using 40-year (1981–2020) CLARA-A3 satellite data and reanalysis datasets, we quantify the spatiotemporal variations of TOA reflected shortwave radiation (RSF) and outgoing longwave radiation (OLR), and decompose the RSF into atmospheric and surface contributions. Additionally, we attribute observed trends to key drivers via multiple linear regression. The TP shows a significant decrease in RSF (−11.06 W/m²) and a significant increase in OLR (+4.88 W/m²). Spatially, OLR increases are widespread and statistically significant over the central and western plateau, while RSF trends are heterogeneous and mostly non-significant except for localized negative trends. The atmospheric contribution to RSF declines markedly (−0.329 W/(m²·year)), whereas the surface contribution increases (+0.061 W/(m²·year)). Attribution analysis identifies cloud fraction change (CFC) as the dominant drivers: it explains most of the RSF decline and the OLR increase. Cloud optical thickness and vertical structure play only minor roles. Our findings demonstrate that decreasing cloud cover is reshaping the TP’s TOA energy budget, providing essential geo-information for the spatial evaluation of climate models and the refinement of satellite-derived radiation products.