Can we improve machine-learning (ML) emulators with synthetic data? If data are scarce or expensive to source and a physical model is available, statistically generated data may be useful for augmenting training sets cheaply. Here we explore the use of copula-based models for generating synthetically augmented datasets in weather and climate by testing the method on a toy physical model of downwelling longwave radiation and corresponding neural network emulator. Results show that for copula-augmented datasets, predictions are improved by up to 62 % for the mean absolute error (from 1.17 to 0.44 W m−2).
@article{arxiv.2012.09037,
title = {Copula-based synthetic data augmentation for machine-learning emulators},
author = {David Meyer and Thomas Nagler and Robin J. Hogan},
journal= {arXiv preprint arXiv:2012.09037},
year = {2021}
}