当前位置: X-MOL 学术Earth Syst. Sci. Data › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A global long-term (1981–2019) daily land surface radiation budget product from AVHRR satellite data using a residual convolutional neural network
Earth System Science Data ( IF 11.4 ) Pub Date : 2022-05-13 , DOI: 10.5194/essd-14-2315-2022
Jianglei Xu, Shunlin Liang, Bo Jiang

The surface radiation budget, also known as all-wave net radiation (Rn), is a key parameter for various land surface processes including hydrological, ecological, agricultural, and biogeochemical processes. Satellite data can be effectively used to estimate Rn, but existing satellite products have coarse spatial resolutions and limited temporal coverage. In this study, a point-surface matching estimation (PSME) method is proposed to estimate surface Rn using a residual convolutional neural network (RCNN) integrating spatially adjacent information to improve the accuracy of retrievals. A global high-resolution (0.05), long-term (1981–2019), and daily mean Rn product was subsequently generated from Advanced Very High Resolution Radiometer (AVHRR) data. Specifically, the RCNN was employed to establish a nonlinear relationship between globally distributed ground measurements from 522 sites and AVHRR top-of-atmosphere (TOA) observations. Extended triplet collocation (ETC) technology was applied to address the spatial-scale mismatch issue resulting from the low spatial support of ground measurements within the AVHRR footprint by selecting reliable sites for model training. The overall independent validation results show that the generated AVHRR Rn product is highly accurate, with R2, root-mean-square error (RMSE), and bias of 0.84, 26.77 W m−2 (31.54 %), and 1.16 W m−2 (1.37 %), respectively. Inter-comparisons with three other Rn products, i.e., the 5 km Global Land Surface Satellite (GLASS); the 1 Clouds and the Earth's Radiant Energy System (CERES); and the 0.5× 0.625 Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2), illustrate that our AVHRR Rn retrievals have the best accuracy under most of the considered surface and atmospheric conditions, especially thick-cloud or hazy conditions. However, the performance of the model needs to be further improved for the snow/ice cover surface. The spatiotemporal analyses of these four Rn datasets indicate that the AVHRR Rn product reasonably replicates the spatial pattern and temporal evolution trends of Rn observations. The long-term record (1981–2019) of the AVHRR Rn product shows its value in climate change studies. This dataset is freely available at https://doi.org/10.5281/zenodo.5546316 for 1981–2019 (Xu et al., 2021).

中文翻译:

使用残差卷积神经网络从 AVHRR 卫星数据中获得的全球长期(1981-2019 年)每日地表辐射收支产品

地表辐射收支,也称为全波净辐射 ( Rn ),是各种地表过程(包括水文、生态、农业和生物地球化学过程)的关键参数卫星数据可以有效地用于估计 Rn ,但现有卫星产品的空间分辨率较粗,时间覆盖范围有限。在这项研究中,提出了一种点-表面匹配估计(PSME)方法,使用残差卷积神经网络(RCNN)整合空间相邻信息来估计表面Rn 以提高检索的准确性。全球高分辨率 (0.05 )、长期 (1981–2019) 和每日平均R n产品随后由高级甚高分辨率辐射计 (AVHRR) 数据生成。具体来说,RCNN 用于建立来自 522 个站点的全球分布地面测量值与 AVHRR 大气层顶 (TOA) 观测值之间的非线性关系。通过选择可靠的模型训练站点,应用扩展的三元组搭配 (ETC) 技术来解决由于 AVHRR 足迹内地面测量的空间支持低而导致的空间尺度不匹配问题。整体独立验证结果表明,生成的 AVHRR R n产品非常准确,R 2、均方根误差 (RMSE) 和偏差分别为 0.84、26.77 W m -2 (31.54 %) 和 1.16 W m -2(1.37%),分别。与其他三个R n产品的相互比较,即 5 公里全球地表卫星(GLASS);1 云和地球辐射能系统 (CERES);以及 0.5 ×  0.625 研究和应用的现代时代回顾分析,第 2 版 (MERRA-2),说明我们的 AVHRR R n 反演在大多数考虑的表面和大气条件下具有最佳精度,尤其是厚云或朦胧的条件。但是,对于冰雪覆盖面,模型的性能需要进一步提高。这四个R n的时空分析数据集表明,AVHRR R n产品合理地复制了R n观测的空间格局和时间演变趋势。AVHRR R n产品的长期记录(1981-2019 年)显示了其在气候变化研究中的价值。该数据集可在 https://doi.org/10.5281/zenodo.5546316 免费获得 1981-2019 年(Xu 等人,2021 年)。
更新日期:2022-05-13
down
wechat
bug