Abstract. Surface solar radiation (SSR) is an essential factor in the flow of surface energy, enabling accurate capturing of long-term climate change and understanding the energy balance of Earth's atmosphere system. However, the long-term trend estimation of SSR is subjected to significant uncertainties due to the temporal inhomogeneity and the uneven spatial distribution of the in-situ observations. This paper develops an observational integrated and homogenized global-terrestrial (except for Antarctica)) stational SSR dataset (SSRIH_station) by integrating all available SSR observations, including the existing homogenized SSR results. The series are then interpolated in order to obtain a 5°×5° resolution gridded dataset (SSRIH_grid). On this basis, we further reconstruct a long-term (1955–2018) global land (except for Antarctica) SSR anomalies dataset with a 5°×2.5° resolution (SSRIH_20CR) by training improved partial convolutional neural network deep learning methods based on the reanalysis 20CRv3. Based on this, we analysed the global land (except for Antarctica) /regional scale SSR trends and spatiotemporal variations: the reconstruction results reflect the distribution of SSR anomalies and have high reliability in filling and reconstructing the missing values. At the global land (except for Antarctica) scale, the decreasing trend of the SSRIH_20CR (-1.276±0.205 W/m² per decade) is slightly smaller than the trend of the SSRIH_grid (-1.776±0.230 W/m² per decade) from 1955 to 1991. The trend of SSRIH_20CR (0.697±0.359 W/m² per decade) from 1991 to 2018 is also marginally lower than that of the SSRIH_grid (0.851±0.410 W/m² per decade). At the regional scale, the difference between the SSRIH_20CR and SSRIH_grid is more significant in years and areas with insufficient coverage. Asia, Africa, Europe and North America cause the global dimming of the SSRIH_20CR, while Europe and North America drive the global brightening of the SSRIH_20CR. Spatial sampling inadequacies have largely contributed to a bias in the long-term variation of global/regional SSR. This paper's homogenized gridded dataset and the Artificial Intelligence reconstruction gridded dataset (Jiao and Li, 2023) are all available at https://doi.org/10.6084/m9.figshare.21625079.v1.

中文翻译：

---

基于人工智能方法的集成均质化全球地表太阳辐射数据集及其重建

摘要。地表太阳辐射 (SSR) 是地表能量流动的重要因素，能够准确捕捉长期气候变化并了解地球大气系统的能量平衡。然而，由于现场观测的时间不均匀性和空间分布的不均匀性，SSR的长期趋势估计存在很大的不确定性。本文通过整合所有可用的 SSR 观测，包括现有的均质化 SSR 结果，开发了一个观测综合和均质化的全球-陆地（南极洲除外））站点 SSR 数据集（SSRIH_站）。然后对系列进行插值以获得 5°×5° 分辨率的网格化数据集（SSRIH_网格). 在此基础上，我们进一步重建了一个长期（1955-2018）全球陆地（南极洲除外）SSR异常数据集，分辨率为5°×2.5°（SSRIH 20CR），训练改进的部分卷积神经网络深度学习_方法基于再分析 20CRv3。在此基础上，我们分析了全球陆地（南极洲除外）/区域尺度的SSR趋势和时空变化：重建结果反映了SSR异常的分布，对填补和重建缺失值具有较高的可靠性。在全球陆地（南极洲除外）尺度上，SSRIH _20CR的下降趋势（-1.276±0.205 W/m ²每十年）略小于SSRIH_网格的趋势（-1.776±0.230 W/m² per decade) 1955-1991 SSRIH _20CR 1991-2018 趋势(0.697±0.359 W/m ² per decade) 也略低于SSRIH grid ₍ 0.851±0.410 W/m ² per decade) . _{在区域尺度上，SSRIH 20CR}和 SSRIH_网格在覆盖不足的年份和地区差异更为显着。亚洲、非洲、欧洲和北美导致SSRIH _20CR全球变暗，欧洲和北美推动SSRIH _{20CR全球变亮}. 空间采样不足在很大程度上导致了全球/区域 SSR 长期变化的偏差。本文的均质化网格数据集和人工智能重建网格数据集（Jiao 和 Li，2023）均可在 https://doi.org/10.6084/m9.figshare.21625079.v1 获取。