Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2508.03590 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909765253201920 |
|---|---|
| author | Bai, Mingliang Fang, Zuliang Tao, Shengyu Xiang, Siqi Bian, Jiang Xiang, Yanfei Zhao, Pengcheng Jin, Weixin Weyn, Jonathan A. Dong, Haiyu Zhang, Bin Sun, Hongyu Thambiratnam, Kit Zhang, Qi Sun, Hongbin Zhang, Xuan Wu, Qiuwei |
| author_facet | Bai, Mingliang Fang, Zuliang Tao, Shengyu Xiang, Siqi Bian, Jiang Xiang, Yanfei Zhao, Pengcheng Jin, Weixin Weyn, Jonathan A. Dong, Haiyu Zhang, Bin Sun, Hongyu Thambiratnam, Kit Zhang, Qi Sun, Hongbin Zhang, Xuan Wu, Qiuwei |
| contents | Accurate 24-hour solar irradiance forecasting is essential for the safe and economic operation of solar photovoltaic systems. Traditional numerical weather prediction (NWP) models represent the state-of-the-art in forecasting performance but rely on computationally costly data assimilation and solving complicated partial differential equations (PDEs) that simulate atmospheric physics. Here, we introduce SolarSeer, an end-to-end large artificial intelligence (AI) model for solar irradiance forecasting across the Contiguous United States (CONUS). SolarSeer is designed to directly map the historical satellite observations to future forecasts, eliminating the computational overhead of data assimilation and PDEs solving. This efficiency allows SolarSeer to operate over 1,500 times faster than traditional NWP, generating 24-hour cloud cover and solar irradiance forecasts for the CONUS at 5-kilometer resolution in under 3 seconds. Compared with the state-of-the-art NWP in the CONUS, i.e., High-Resolution Rapid Refresh (HRRR), SolarSeer significantly reduces the root mean squared error of solar irradiance forecasting by 27.28% in reanalysis data and 15.35% across 1,800 stations. SolarSeer also effectively captures solar irradiance fluctuations and significantly enhances the first-order irradiance difference forecasting accuracy. SolarSeer's ultrafast, accurate 24-hour solar irradiance forecasts provide strong support for the transition to sustainable, net-zero energy systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03590 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA Bai, Mingliang Fang, Zuliang Tao, Shengyu Xiang, Siqi Bian, Jiang Xiang, Yanfei Zhao, Pengcheng Jin, Weixin Weyn, Jonathan A. Dong, Haiyu Zhang, Bin Sun, Hongyu Thambiratnam, Kit Zhang, Qi Sun, Hongbin Zhang, Xuan Wu, Qiuwei Machine Learning Computational Engineering, Finance, and Science Accurate 24-hour solar irradiance forecasting is essential for the safe and economic operation of solar photovoltaic systems. Traditional numerical weather prediction (NWP) models represent the state-of-the-art in forecasting performance but rely on computationally costly data assimilation and solving complicated partial differential equations (PDEs) that simulate atmospheric physics. Here, we introduce SolarSeer, an end-to-end large artificial intelligence (AI) model for solar irradiance forecasting across the Contiguous United States (CONUS). SolarSeer is designed to directly map the historical satellite observations to future forecasts, eliminating the computational overhead of data assimilation and PDEs solving. This efficiency allows SolarSeer to operate over 1,500 times faster than traditional NWP, generating 24-hour cloud cover and solar irradiance forecasts for the CONUS at 5-kilometer resolution in under 3 seconds. Compared with the state-of-the-art NWP in the CONUS, i.e., High-Resolution Rapid Refresh (HRRR), SolarSeer significantly reduces the root mean squared error of solar irradiance forecasting by 27.28% in reanalysis data and 15.35% across 1,800 stations. SolarSeer also effectively captures solar irradiance fluctuations and significantly enhances the first-order irradiance difference forecasting accuracy. SolarSeer's ultrafast, accurate 24-hour solar irradiance forecasts provide strong support for the transition to sustainable, net-zero energy systems. |
| title | SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA |
| topic | Machine Learning Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2508.03590 |