• To encourage investment in renewable energy, there is a requirement to assess availability of renewable energy resources under projected changes in climate (Schaeffer, et al. 2012) [1].
  • Global Circulation Models (GCMs) provide coarse scale estimated climate features of climate along future response pathways.
  • Performing downscaling to a finer local scale is uncertain due to non-linear feedback of climate.
  • Statistical downscaling requires - feature selection, distribution assumptions multiple models per sites.

    • Is it possible to use a data driven learning method capable of representing such effects and perform well across multiple sites?

    [1]
    Schaeffer, R, Szklo, A S, Pereira de Lucena, A F, Moreira Cesar Borba, B S, Pupo Nogueira, L P, Fleming, F P, Troccoli, A, Harrison, M and Boulahya, M S (2012 ). Energy sector vulnerability to climate change: A review. Energy. 38 1–2

    Creative Commons License
    Downscaling Global Climate Models with Convolutional and Long-Short-Term Memory Networks for Solar Energy Applications by C.P. Davey is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.