Copula-based synthetic data augmentation for machine-learning emulators
University of Reading（雷丁大学）；Imperial College London（帝国理工学院）；Leiden University（莱顿大学）；European Centre for Medium-Range Weather Forecasts（欧洲中期天气预报中心）
英文摘要：
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$^{-2}$).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
