SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA

TL;DR

SolarSeer is an AI-based model that provides ultrafast, highly accurate 24-hour solar irradiance forecasts across the US, outperforming traditional numerical weather prediction models in speed and accuracy.

Contribution

The paper introduces SolarSeer, a novel AI model that directly maps satellite data to forecasts, eliminating complex computations and significantly improving speed and accuracy over existing methods.

Findings

SolarSeer operates over 1,500 times faster than traditional NWP models.

It reduces root mean squared error of irradiance forecasts by over 27%.

It effectively captures irradiance fluctuations and improves forecast accuracy.

Abstract

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.