A study published in the Journal of Remote Sensing on April 29, 2026, introduces a transfer learning method that allows China's Fengyun-4A (FY-4A) geostationary satellite to estimate surface solar radiation (SSR) and its global, direct, and diffuse components with improved accuracy. The research, conducted by scientists from the Aerospace Information Research Institute, Chinese Academy of Sciences; Sichuan University of Science and Engineering; and the Institute of Atmospheric Physics, Chinese Academy of Sciences, addresses the challenge of tracking solar radiation amid rapidly changing clouds, aerosols, and atmospheric conditions.
The new framework adapts knowledge from the Himawari-8-based Cloud, Atmospheric Radiation and Renewal Energy Application (CARE) product, reducing reliance on auxiliary meteorological datasets. According to the study, accurate sunlight data is essential for the clean-energy transition, as surface solar radiation controls Earth's energy balance, hydrological cycles, ecosystem processes, and the performance of solar photovoltaic (PV) and concentrating solar power systems. While ground-based radiometric networks offer reliable observations, their stations are sparse and unevenly distributed, particularly across oceans and developing regions. Reanalysis products provide broad coverage but may lose accuracy due to coarse resolution and simplified cloud–aerosol–radiation interactions.
The researchers developed a deep neural network (DNN) model using Himawari-8 Level 1 (L1) observations and the CARE radiation product, then fine-tuned it with FY-4A L1 data. The model uses top-of-atmosphere reflectance and solar–satellite geometry as dynamic inputs, with Bayesian optimization selecting key hyperparameters. Validation using 33 ground stations from the Baseline Surface Radiation Network (BSRN), Bureau of Meteorology (BOM), and Global Tropical Moored Buoy Array (GTMBA) during 2018–2020 showed strong performance. At representative BSRN sites, FY-4A achieved instantaneous root mean square errors (RMSEs) of 102.2, 117.5, and 83.1 W m⁻² for global, direct, and diffuse radiation, respectively. At the daily mean scale, RMSEs dropped to 28.5, 30.1, and 22.6 W m⁻².
The authors emphasized that the transfer learning strategy turns China's geostationary satellite observations into a more powerful resource for energy and climate applications. The new FY-4A radiation product could help improve PV site assessment, power forecasting, grid management, climate modeling, and land-surface simulations. Direct radiation is especially important for concentrating solar power, while diffuse radiation affects PV output under cloudy or aerosol-rich skies. By resolving these components separately, the framework offers more actionable information than global radiation alone.
The study demonstrates that transfer learning can help overcome sensor differences and limited ground training data. Looking ahead, the same strategy could be extended to other Chinese geostationary satellites, including Fengyun-4B (FY-4B), supporting more reliable solar-energy monitoring across East Asia and beyond. The research was supported by the National Natural Science Foundation of China (Nos. 42025504, 42405145, and 42430604), the Natural Science Foundation of Sichuan Province (No. 2024NSFSC0770), the Tianfu Yongxing Laboratory Organized Research Project Funding (No. 2024KIGG18), and the Opening Fund of Artificial Intelligence Key Laboratory of Sichuan Province (No. 2024RYY03). More details can be found in the original study at https://spj.science.org/doi/10.34133/remotesensing.1044.
