Meta-modeling strategy for data-driven forecasting
This work addresses the need for efficient and interpretable data-driven forecasting methods in climate science, though it appears incremental by building on existing meta-modeling approaches.
The paper tackled the problem of accurate and interpretable weather forecasting by using historical climate data and machine learning to predict temperature fields, achieving computational efficiency through adaptive training strategies that avoid expensive high-fidelity evaluations.
Accurately forecasting the weather is a key requirement for climate change mitigation. Data-driven methods offer the ability to make more accurate forecasts, but lack interpretability and can be expensive to train and deploy if models are not carefully developed. Here, we make use of two historical climate data sets and tools from machine learning, to accurately predict temperature fields. Furthermore, we are able to use low fidelity models that are cheap to train and evaluate, to selectively avoid expensive high fidelity function evaluations, as well as uncover seasonal variations in predictive power. This allows for an adaptive training strategy for computationally efficient geophysical emulation.