IJSRP, Volume 10, Issue 10, October 2020 Edition [ISSN 2250-3153]
Arwini Arisandi, Aji Hamim Wigena, Agus Mohamad Soleh
Abstract:
Statistical downscaling (SDS) is a method to relate functionally global scale to local scale climate data. The global scale data are from the Global Climate Models (GCM) output while the local data are from a rainfall station. Generally, the GCM output data are available in the form of contiguous grids which commonly causes the multicollinearity problem. The problem can be overcome by a method such as principal component analysis (PCA), LASSO, forward selection. A SDS modeling can use the continuum regression with PCA.