Reconstructing High Resolution ESM Data Through a Novel Fast Super Resolution Convolutional Neural Network (FSRCNN)
In this work, we present the first application of a fast super resolution convolutional neural network (FSRCNN) based approach for downscaling earth system model (ESM) simulations. Unlike other SR approaches, FSRCNN uses the same input feature dimensions as the low resolution input. This allows it to have smaller convolution layers, avoiding over-smoothing, and reducing computational costs. We adapt the FSRCNN to improve reconstruction on ESM data, we term the FSRCNN-ESM. We use high-resolution (~0.25°) monthly averaged model output of five surface variables over North America from the US Department of Energy's Energy Exascale Earth System Model's control simulation. These high-resolution and corresponding coarsened low-resolution (~1°) pairs of images are used to train the FSRCNN-ESM and evaluate its use as a downscaling approach. We find that FSRCNN-ESM outperforms FSRCNN and other super-resolution methods in reconstructing high resolution images producing finer spatial scale features with better accuracy for surface temperature, surface radiative fluxes, and precipitation.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- Grant/Contract Number:
- AC02-05CH11231; AC05-00OR22725
- OSTI ID:
- 1864450
- Journal Information:
- Geophysical Research Letters, Journal Name: Geophysical Research Letters Journal Issue: 4 Vol. 49; ISSN 0094-8276
- Publisher:
- American Geophysical UnionCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Oblique reconstructions in tomosynthesis. II. Super-resolution
Complementing Dynamical Downscaling With Super‐Resolution Convolutional Neural Networks