The solar radiation forecasting model is estimated using a Generalized Additive Model (GAM) based on weekly weather forecast data from the Japan Meteorological Agency.

This approach is grounded in insights gained from our previous research, including the following studies.

1. Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques
   Takuji Matsumoto, Yuji Yamada
   Energies 14(21), 2021.

2. Construction of Forecast Model for Power Demand and PV Power Generation Using Tensor Product Spline Function
   Takuji Matsumoto, Yuji Yamada
   IOP Conference Series: Earth and Environmental Science 812(1), 012001, 2021.

3. Prediction method for solar power business based on forecasted general weather conditions and periodic trends by weather.
   Takuji Matsumoto, Yuji Yamada
   Transactions of the Operations Research Society of Japan 62, 1-22, 2019.