Enhanced Short-Term Prediction of Solar Radiation Using HRNet Model With Geostationary Satellite Data

Our study focuses on leveraging a deep neural network approach coupled with geostationary satellite data to enhance short-term 3-h-ahead predictions of solar radiation over Northeast Asia. A crucial aspect of our study was improving the smoothness of the predicted image patterns, especially in cases of long-term forecasts, based on the application of the HRNet model. The proposed method effectively depicted the 2-D images of the predicted maps for potential solar radiation because it maintains high-resolution representations throughout its layers. Our short-term prediction maps for potential solar radiation showed good agreement with reference images from the physical model, and complex cloud movements were well predicted using the HRNet model. Reliable accuracy was obtained between the ground pyranometer measurements and our predicted values for the potential 3-h-ahead predictions (RMSE =98.570 Wm-2, nRMSE =23.79%, MBE
$= -0.578$
Wm-2, and
$R^{2} =0.829$
). Furthermore, the HRNet model demonstrated a notably low average blurriness score of 0.00019 and high average peak signal-to-noise ratio (PSNR) of 7.646, demonstrating its improved ability to deliver sharper and less-noisy predictions than selected deep learning models.