Site adaptation with machine learning for a Northern Europe gridded solar radiation product

TL;DR

This paper explores the use of machine learning techniques to improve the accuracy of high-latitude solar radiation data, specifically for Sweden, by adapting existing datasets with ground measurements.

Contribution

It introduces a machine learning-based site adaptation method for enhancing the quality of gridded solar radiation data in high-latitude regions, outperforming traditional statistical approaches.

Findings

Machine learning algorithms outperform statistical methods in site adaptation.

Model performance varies across locations, indicating the need for location-specific models.

No single model is universally best for all sites due to heterogeneity.

Abstract

Gridded global horizontal irradiance (GHI) databases are fundamental for analysing solar energy applications' technical and economic aspects, particularly photovoltaic applications. Today, there exist numerous gridded GHI databases whose quality has been thoroughly validated against ground-based irradiance measurements. Nonetheless, databases that generate data at latitudes above 65$^{\circ}$ are few, and those available gridded irradiance products, which are either reanalysis or based on polar orbiters, such as ERA5, COSMO-REA6, or CM SAF CLARA-A2, generally have lower quality or a coarser time resolution than those gridded irradiance products based on geostationary satellites. Among the high-latitude gridded GHI databases, the STR\r{A}NG model developed by the Swedish Meteorological and Hydrological Institute (SMHI) is likely the most accurate one, providing data across Sweden. To further enhance the product quality, the calibration technique called "site adaptation" is herein used to improve the STR\r{A}NG dataset, which seeks to adjust a long period of low-quality gridded irradiance estimates based on a short period of high-quality irradiance measurements. This study, differing from the conventional statistical approaches, adopts machine learning for site adaptation. Nine machine-learning algorithms have been analysed and compared with conventional statistical ones to identify Sweden's most favourable technique for site adaptation. Three weather stations of SMHI are used for training and validation. The results show that, due to the spatio-temporal heterogeneity in model performance, no universal model can be identified, which suggests that site adaptation is a location-dependent procedure.