Deep Learning in Climate Forecasting and Downscaling

  • CNN-LSTM - forecast global solar radiation (auto-regressive setting) over multiple time resolutions (Ghimire, et al. 2019). [1]
  • ConvLSTM - precipitation forecasting in Hong Kong versus optical flow modelling from radar images (Shi, et al. 2015). [2]
  • Super-resolution Convolutional Neural Network (SRCNN) - progressive downscaling of precipitation over US via reanalysis products (Vandal et al. 2018). [3]
  • Not specifically applied to global solar radiation downscaling studies although Aerosol Optical Depth has been studied (Li, et al. 2020). [4]

    • [1]
    Ghimire, S, Deo, R C, Raj, N and Mi, J (2019 ). Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms. Applied Energy. 253 1–1

    [2]
    Shi, X, Chen, Z, Wang, H, Yeung, D-Y, Wong, W and Woo, W Convolutional LSTM network: A machine learning approach for precipitation nowcasting. MIT Press, Cambridge, MA, USA. 802–10

    [3]
    Vandal, T, Kodra, E, Ganguly, S, Michaelis, A, Nemani, R and Ganguly, A R DeepSD: Generating high resolution climate change projections through single image super-resolution: An abridged version. AAAI Press. 5389–93

    [4]
    Li, L, Franklin, M, Girguis, M, Lurmann, F, Wu, J, Pavlovic, N, Breton, C, Gilliland, F and Habre, R (2020 ). Spatiotemporal imputation of MAIAC AOD using deep learning with downscaling. Remote Sensing of Environment. 237

    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.