Deep Feature Selection of Meteorological Variables for LSTM-Based PV Power Forecasting in High-Dimensional Time-Series Data

Accurate photovoltaic (PV) power forecasting is essential for grid integration, particularly in maritime climates with dynamic weather patterns. This study addresses high-dimensional meteorological data challenges by systematically evaluating 32 variables across four categories (solar irradiance, temperature, atmospheric, hydrometeorological) for day-ahead PV forecasting using long short-term memory (LSTM) networks. Using six years of data from a 350 kWp solar farm in Scotland, we compare satellite-derived data and local weather station measurements. Surprisingly, downward thermal infrared flux—capturing persistent atmospheric moisture and cloud properties in maritime climates—emerged as the most influential predictor despite low correlation (1.93%). When paired with precipitation data, this two-variable combination achieved 99.81% R2, outperforming complex multi-variable models. Satellite data consistently surpassed ground measurements, with 9 of the top 10 predictors being satellite derived. Our approach reduces model complexity while improving forecasting accuracy, providing practical solutions for energy systems. Keywords: deep learning; forecasting; long short-term memory; mean absolute; meteorological variables

Department

Computer Science

Publisher

MDPI

Sponsor

Effat University

Copyright

CC0 1.0 Universal

cb