Mapping Prediction of Surface Solar Radiation with Linear Regression Models: Case Study over Reunion Island

Abstract

This paper presents a novel mapping prediction method for surface solar radiation with linear regression models. The dataset for surface solar radiation prediction is the daily surface incoming shortwave radiation (SIS) product from CM SAF SARAH-E. The spatial resolution is 0.05° × 0.05° and the temporal coverage is from 2007 to 2016. The first five years (2007–2011) are used as training data, and the remaining five years (2012–2016) are used as test data in the prediction model. Datasets were detrended, de-seasonalized, and normalized before being applied to multiple linear regression (MLR), principal component regression (PCR), stepwise regression (SR), and partial least squares regression (PLSR), which are used to perform prediction mapping. The statistical analysis using MAE, MSE, and RMSE shows that the PCR model had the smallest MAE, MSE, and RMSE as compared to the other three models. The PCR model seems better for SSR mapping prediction over Reunion Island. Although the PCR model provides better prediction results, its MAE, MSE, and RMSE are quite large.

Keywords

• surface solar radiation
• linear regression model
• principal component analysis
• mapping prediction