Presentation1_A 35-year daily global solar radiation dataset reconstruction at the Great Wall Station, Antarctica: First results and comparison with ERA5, CRA40 reanalysis, and ICDR (AVHRR) satellite products.pdf

• Main Authors: Zhaoliang Zeng, Xin Wang, Zemin Wang, Wenqian Zhang, Dongqi Zhang, Kongju Zhu, Xiaoping Mai, Wei Cheng, Minghu Ding
• Format: Conference Object
• Language: unknown
• Published: 2022
• Subjects: Solid Earth Sciences; Climate Science; Atmospheric Sciences not elsewhere classified; Exploration Geochemistry; Inorganic Geochemistry; Isotope Geochemistry; Organic Geochemistry; Geochemistry not elsewhere classified; Igneous and Metamorphic Petrology; Ore Deposit Petrology; Palaeontology (incl. Palynology); Structural Geology; Tectonics; Volcanology; Geology not elsewhere classified; Seismology and Seismic Exploration; Glaciology; Hydrogeology; Natural Hazards; Quaternary Environments; Earth Sciences not elsewhere classified; Evolutionary Impacts of Climate Change; DGSR; empirical formula; machine learning; CRA40 reanalysis product; ICDR (AVHRR) satellite product; Antarc*; Antarctic; Antarctica; Ice Sheet; Sea ice
• Online Access: https://doi.org/10.3389/feart.2022.961799.s001; https://figshare.com/articles/presentation/Presentation1_A_35-year_daily_global_solar_radiation_dataset_reconstruction_at_the_Great_Wall_Station_Antarctica_First_results_and_comparison_with_ERA5_CRA40_reanalysis_and_ICDR_AVHRR_satellite_products_pdf/20762524

Solar radiation drives many geophysical and biological processes in Antarctica, such as sea ice melting, ice sheet mass balance, and photosynthetic processes of phytoplankton in the polar marine environment. Although reanalysis and satellite products can provide important insight into the global scale of solar radiation in a seamless way, the ground-based radiation in the polar region remains poorly understood due to the harsh Antarctic environment. The present study attempted to evaluate the estimation performance of empirical models and machine learning models, and use the optimal model to establish a 35-year daily global solar radiation (DGSR) dataset at the Great Wall Station, Antarctica using meteorological observation data during 1986–2020. In addition, it then compared against the DGSR derived from ERA5, CRA40 reanalysis, and ICDR (AVHRR) satellite products. For the DGSR historical estimation performance, the machine learning method outperforms the empirical formula method overall. Among them, the Mutli2 model (hindcast test R 2 , RMSE, and MAE are 0.911, 1.917 MJ/m 2 , and 1.237 MJ/m 2 , respectively) for the empirical formula model and XGBoost model (hindcast test R 2 , RMSE, and MAE are 0.938, 1.617 MJ/m 2 , and 1.030 MJ/m 2 , respectively) for the machine learning model were found with the highest accuracy. For the austral summer half-year, the estimated DGSR agrees very well with the observed DGSR, with a mean bias of only −0.47 MJ/m 2 . However, other monthly DGSR products differ significantly from observations, with mean bias of 1.05 MJ/m 2 , 3.27 MJ/m 2 , and 6.90 MJ/m 2 for ICDR (AVHRR) satellite, ERA5, and CRA40 reanalysis products, respectively. In addition, the DGSR of the Great Wall Station, Antarctica followed a statistically significant increasing trend at a rate of 0.14 MJ/m 2 /decade over the past 35 years. To our best knowledge, this study presents the first reconstruction of the Antarctica Great Wall Station DGSR spanning 1986–2020, which will contribute to the research of surface ...