Contrastive Learning for Climate Model Bias Correction and Super-Resolution
This work addresses the need for more accurate local climate risk models, particularly in regions lacking rich observational data, though it is incremental as it builds on existing GAN and super-resolution techniques.
The paper tackled the problem of climate model bias correction and spatial resolution enhancement by proposing a method combining image super-resolution and contrastive learning GANs, achieving double the spatial resolution of NASA's NEX-GDDP product with comparable or improved bias correction for daily precipitation and temperature.
Climate models often require post-processing in order to make accurate estimates of local climate risk. The most common post-processing applied is bias-correction and spatial resolution enhancement. However, the statistical methods typically used for this not only are incapable of capturing multivariate spatial correlation information but are also reliant on rich observational data often not available outside of developed countries, limiting their potential. Here we propose an alternative approach to this challenge based on a combination of image super resolution (SR) and contrastive learning generative adversarial networks (GANs). We benchmark performance against NASA's flagship post-processed CMIP6 climate model product, NEX-GDDP. We find that our model successfully reaches a spatial resolution double that of NASA's product while also achieving comparable or improved levels of bias correction in both daily precipitation and temperature. The resulting higher fidelity simulations of present and forward-looking climate can enable more local, accurate models of hazards like flooding, drought, and heatwaves.