<ul><li>Full-complexity Earth system models (ESMs) are computationally expensive, limiting their use in exploring climate outcomes.</li><li>Efficient emulators that approximate ESMs are being used to map emissions onto climate outcomes.</li><li>A comparison between deep learning emulators and a linear regression-based emulator was conducted on ClimateBench, a popular benchmark for data-driven climate emulation.</li><li>The linear regression-based emulator outperformed the deep learning foundation model on 3 out of 4 regionally-resolved climate variables.</li></ul>

The impact of internal variability on benchmarking deep learning climate emulators

Discover more