Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation
Abstract
How can we learn from all available data when training machine-learnt climate models, without incurring any extra cost at simulation time? Typically, the training data comprises coarse-grained high-resolution data. But only keeping this coarse-grained data means the rest of the high-resolution data is thrown out. We use a transfer learning approach, which can be applied to a range of machine learning models, to leverage all the high-resolution data. We use three chaotic systems to show it stabilises training, gives improved generalisation performance and results in better forecasting skill. Our code is at https://github.com/raghul-parthipan/dont_waste_data
Cite
@article{arxiv.2210.04001,
title = {Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation},
author = {Raghul Parthipan and Damon J. Wischik},
journal= {arXiv preprint arXiv:2210.04001},
year = {2022}
}
Comments
8 pages. NeurIPS 2022 Workshop: Tackling Climate Change with Machine Learning. Spotlight talk