CORDEX-ML-Bench: A Benchmark for Data-Driven Regional Climate Downscaling—Experiment Design and Overview

<p><strong>Citation</strong>:</p><p>Rampal, N., González-Abad, J., Addison, H., Baño-Medina, J., Bettolli, M. L., Blasone, V., Booth, B., Coppola, E., Di Gioia, S., Oldham-Dorrington, J., Doury, A., Engelbrecht, F., Fuentes-Franco, R., Gibson, P. B., Glawion, L., Hardy, C., Ivanov, M., Lee, H. K., Legasa, M. N., Olmo, M., Orr, A., Polz, J., Rogers, M. S. J., Schillinger, M., Sharma, S., Soares, P. M. M., Sobolowski, S., Steinkopf, J., Tang, W., Tian, J.-B., Tomé, R., Wang, K.-C., Wang, Y.-C., Watson, P. A. G., Wetherell, T., Widmann, M., &amp; Gutiérrez, J. M. (2026). <em>CORDEX-ML-Bench: A Benchmark for Data-Driven Regional Climate Downscaling—Experiment Design and Overview</em>. WCRP-CORDEX Machine Learning Task Team.</p><p><strong>Key Takeaways:</strong></p><ul><li><strong>Establishing a Standardized Global Benchmark</strong>: The paper introduces CORDEX-ML-Bench, the first coordinated multi-domain, multi-architecture benchmarking framework explicitly designed to standardize machine learning (ML) models for regional climate downscaling. The framework enables researchers to evaluate and compare models consistently using open-source datasets and metrics, focusing on a 20× spatial resolution increase (from ~200 km down to ~10 km grids) for daily precipitation and maximum temperature. The initial benchmark targets three highly diverse geographical regions: the European Alps, New Zealand, and Southern Africa.</li><li><strong>The Critical Extrapolation Gap of Historical Training</strong>: A foundational finding of the benchmark is that ML models trained strictly on historical climate data systematically underestimate future climate change signals, including extreme warming and intensive precipitation. This reveals a major vulnerability in traditional historical-only statistical downscaling methods and proves that incorporating future climate projections into training datasets (the emulator approach) is vital for producing physically credible long-term projections.</li><li><strong>Generative AI Outperforms for Precipitation Extremes</strong>: In an evaluation of 40 independently developed ML configurations, generative approaches (such as diffusion models, flow matching, and Generative Adversarial Networks) consistently outperform deterministic regression models at downscaling precipitation. They excel at capturing highly localized spatial variability and heavy-tailed extreme events, whereas deterministic models suffer from spatial &quot;oversmoothing&quot;. Ho