Publications

Xu, JL; Liang, SL; Jiang, B (2022). 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, 14(5), 2315-2341.

Abstract
The surface radiation budget, also known as all-wave net radiation (R-n), is a key parameter for various land surface processes including hydrological, ecological, agricultural, and biogeochemical processes. Satellite data can be effectively used to estimate R-n, 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 R-n using a residual convolutional neural network (RCNN) integrating spatially adjacent information to improve the accuracy of retrievals. A global high-resolution (0.05 degrees), long-term (1981-2019), and daily mean R-n 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 R-2, 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 R-n products, i.e., the 5 km Global Land Surface Satellite (GLASS); the 1 degrees Clouds and the Earth's Radiant Energy System (CERES); and the 0.5 degrees x 0.625 degrees Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2), illustrate that our AVHRR R-n 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 R-n datasets indicate that the AVHRR R-n product reasonably replicates the spatial pattern and temporal evolution trends of R-n observations. The long-term record (1981-2019) of the AVHRR R-n product shows its value in climate change studies.

DOI:
10.5194/essd-14-2315-2022

ISSN:
1866-3516