A Physics-Informed Machine Learning Approach utilizing Multiband Satellite Data for Solar Irradiance Estimation

2024/07/05 by Junichi Sasaki, Sasaki, Jun, Okada, Maki +4
Computer Science · Physics and Astronomy · #Atmospheric and Oceanic Physics (physics.ao-ph) #FOS: Physical sciences #Solar Radiation and Photovoltaics #Solar and Space Plasma Dynamics

paper · pdf · doi:10.48550/arxiv.2407.04283

openalex publication_date 2024/07/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Solar irradiance is fundamental data crucial for analyses related to weather and climate. High-precision estimation models are necessary to create areal data for solar irradiance. In this study, we developed a novel estimation model by utilizing machine learning and multiband data from meteorological satellite observations. Particularly under clear-sky and thin clouds, satellite observations can be influenced by surface reflections, which may lead to overfitting to ground observations. To make the model applicable at any location, we constructed the model incorporating prior information such as radiative transfer models and clear-sky probability, based on physical and meteorological knowledge. As a result, the estimation accuracy significantly improved at validation sites.

Related

• Machine learning model to predict solar radiation, based on the integration of meteorological data and data obtained from satellite images
• Surface solar radiation: AI satellite retrieval can outperform Heliosat and generalizes well to other climate zones
• Data fusion of complementary data sources using Machine Learning enables higher accuracy Solar Resource Maps
• Data-driven Surface Solar Irradiance Estimation using Neural Operators at Global Scale
• Model-Agnostic Hybrid Numerical Weather Prediction and Machine Learning Paradigm for Solar Forecasting in the Tropics