Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation
This work addresses data efficiency in climate modeling, offering a method to enhance model performance without additional computational expense, though it appears incremental as it builds on existing transfer learning techniques.
The paper tackles the problem of wasting high-resolution data in training machine-learned climate models by proposing a transfer learning approach that leverages all available data without extra simulation cost, demonstrating improved generalization and forecasting skill across three chaotic systems.
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