Surface solar radiation drives the water cycle and energy exchange on the earth's surface, thus is an indispensable parameter for many numerical models to estimate soil moisture, evapotranspiration and plant photosynthesis. The diffuse radiation can increase the ecosystem productivity by enhancing canopy light use efficiency, thereby promote carbon uptake in ecosystems. The accurate knowledge of their spatial distribution is helpful for estimation of plant productivity, carbon dynamics of terrestrial ecosystems, research on regional climate change, and site selection of solar power plants. Therefore, we produce the high-resolution radiation datasets, including global solar radiation and the diffuse component in hourly, daily and monthly scales with spatial resolution of 5km over China in 2008 based on the observations of the China Meteorology Administration (CMA) and Multi-functional Transport Satellite (MTSAT) satellite data using deep learning techniques. The root mean square error (RMSE) between our products and in-situ measurements is about to 0.32 MJ/m2 (90 W/m2), 2.14 MJ/m2 and 1.30 MJ/m2 in hourly, daily and monthly scales, respectively. The dataset should be useful for the analysis of the regional differences and temporal cycles of solar radiation in fine scales, and the impact of diffuse radiation on plant growth etc.