CORDEX-ML-Bench: A benchmarking dataset for data-driven regional climate downscaling.

CORDEX-ML-Bench A Standardized Benchmarking Dataset for Data-Driven Regional Climate Downscaling 📋 Overview CORDEX-ML-Bench provides a standardized framework for evaluating machine learning models for regional climate downscaling. Participants will train models on Regional Climate Model (RCM) simulations and test their performance across different time periods and spatial domains. This Zenodo repository only provides the training data, other relevant information will be provided below. Key Features RCM simulations spanning three distinct geographic domains. Allowing for testing and evaluation of emulators in multiple domains. Currently, this repository is in a testing phase, and not all the data has been uploaded. Evaluation framework across historical and future periods. CORDEX-ML-Bench provides tools for training and evaluating ESD and RCM emulators. These can be found here📦 WCRP-CORDEX/ml-benchmark. 🌍 Geographic Domains Domain Resolution Target Variables Target Grid Size Predictor Variables Predictor Grid Size Static Fields New Zealand (NZ) 0.11° Tasmax, Pr 128 × 128 u, v, q, t, z at 850, 700, 500 hPa (15 variables) 16 x 16 (2°) Orography (128 x 128; 0.11°) Europe (ALPS) 0.11° Tasmax, Pr 128 × 128 u, v, q, t, z at 850, 700, 500 hPa 16 x 16 (2°) Orography South Africa (SA) 0.10° Tasmax, Pr 128 × 128 u, v, q, t, z at 850, 700, 500 hPa 16 x 16 (2°) Orography An illustration of the predictor (16 x 16) and target domains (128 x 128) are shown above. Noting that the predictor domains are slightly larger than the target domains. Predictor Variables (16 total, 16 x 16) Atmospheric variables at 850 hPa, 700 hPa, 500 hPa : u - zonal wind component v - meridional wind component q - specific humidity t - temperature z - geopotential height Static field: Orography (topography) 🔧 Getting Started Loading Data For code examples and tutorials on loading the training data, refer to the official repository: 📦 WCRP-CORDEX/ml-benchmark Data Preprocessing Region-specific preprocessing information: NZ Domain: nram812/CORDEXBench-nzdomain-preprocessing ALPS Domain: jgonzalezab/CORDEXBench-alpsdomain-preprocessing 🎯 Training Framework Perfect Framework Training The benchmark investigates training in the "perfect" framework: X (predictors): Coarsened RCM fields y (targets): High-resolution truth from RCM Evaluation is supported in both perfect (coarsened RCM) and imperfect (applied directly to the GCM) configurations. 🧪 Experimental Setups 1️⃣ ESD Pseudo-Reality (1961–1980) Training Period: 20 years (1961–1980)GCM Examples: ACCESS-CM2 (NZ), CNRM-CM5 (ALPS) This experiment mimics traditional Empirical Statistical Downscaling (ESD) training. Configurations: ✅ With orography ❌ Without orography 2️⃣ Emulator Historical + Future (1961–1980 + 2081–2100) Training Period: 40 years combinedPeriods: Historical (1961–1980) + Future (2081–2100)GCM Examples: ACCESS-CM2 (NZ), CNRM-CM5 (ALPS) This experiment evaluates model extrapolation skill and transferability across different GCMs. Configurations: ✅ With orography ❌ Without orography 📊 Evaluation Framework Test Periods Historical: 1981–2000 Mid-Century: 2041–2060 End-Century: 2081–2100 Evaluation Types PP Cross-Validation: Same GCM used in training and testing Imperfect Inference: Same GCM but different realizations or noise Transferability Testing: Different GCM than training set Change Signal Evaluation: Climate change response in future periods 📋 Evaluation Tables Table 1: ESD "Pseudo-Reality" Evaluation (T1) Training Setup Inference Set Evaluation Type Notes Metrics Required ESD 1961–1980<br>Static: Yes/No Historical<br>(1981–2000) PP cross-validation Same GCM, perfectly Error, Clim ✅ Historical<br>(1981–2000) Imperfect cross-validation Same GCM, imperfectly Error, Clim ✅ 2041–2060<br>2081–2100 Extrapolation Same GCM, perfectly Change signal ✅ 2041–2060<br>2081–2100 Extrapolation Same GCM, imperfectly Change signal ✅ Table 2: Emulator Evaluation (T2) Training Setup Inference Set Evaluation Type Notes Metrics Required Emulator<br>1961–1980 +<br>2081–2100<br>Static: Yes/No Historical<br>(1981–2000) PP cross-validation Same GCM, perfectly Error, Clim ✅ Historical<br>(1981–2000) Imperfect cross-validation Same GCM, imperfectly Error, Clim ✅ Historical<br>(1981–2000) Different GCM, perfectly Error, Clim ✅ Historical<br>(1981–2000) Different GCM, imperfectly Error, Clim ✅ 2041–2060<br>2081–2100 Extrapolation Same GCM, perfectly Change signal ✅ 2041–2060<br>2081–2100 Extrapolation Same GCM, imperfectly Change signal ✅ 2041–2060<br>2081–2100 Hard Transferability Different GCM, perfectly Change signal ✅ 2041–2060<br>2081–2100 Hard Transferability Different GCM, imperfectly Change signal ✅ 📁 Data Structure New Zealand Domain NZ_Domain/ ├── train/ │ ├── ESD_pseudo-reality/ │ │ ├── predictors/ │ │ │ ├── ACCESS-CM2_1961-1980.nc │ │ │ └── static.nc │ │ └── target/ │ │ └── pr_tasmax_ACCESS-CM2_1961-1980.nc │ │ │ └── Emulator_hist_future/ │ ├── predictors/ │ │ ├── ACCESS-CM2_1961-1980_2080-2099.nc │ │ └── static.nc │ └── target/ │ └── pr_tasmax_ACCESS-CM2_1961-1980_2080-2099.nc │ └── test/ ├── historical/ │ ├── predictors/ │ │ ├── perfect/ │ │ │ ├── ACCESS-CM2_1981-2000.nc │ │ │ └── EC-Earth3_1981-2000.nc │ │ └── imperfect/ │ │ ├── ACCESS-CM2_1981-2000.nc │ │ └── EC-Earth3_1981-2000.nc │ └── target/ │ ├── pr_tasmax_ACCESS-CM2_1981-2000.nc │ └── pr_tasmax_EC-Earth3_1981-2000.nc │ ├── mid_century/ │ ├── predictors/ │ │ ├── perfect/ │ │ └── imperfect/ │ └── target/ │ └── end_century/ ├── predictors/ │ ├── perfect/ │ └── imperfect/ └── target/ ALPS Domain ALPS_Domain/ ├── train/ │ ├── ESD_pseudo-reality/ │ │ ├── predictors/ │ │ │ ├── CNRM-CM5_1961-1980.nc │ │ │ └── static.nc │ │ └── target/ │ │ └── pr_tasmax_CNRM-CM5_1961-1980.nc │ │ │ └── Emulator_hist_future/ │ ├── predictors/ │ │ ├── CNRM-CM5_1961-1980_2080-2099.nc │ │ └── static.nc │ └── target/ │ └── pr_tasmax_CNRM-CM5_1961-1980_2080-2099.nc │ └── test/ ├── historical/ │ ├── predictors/ │ │ ├── perfect/ │ │ │ ├── CNRM-CM5_1981-2000.nc │ │ │ └── MPI-ESM-LR_1981-2000.nc │ │ └── imperfect/ │ │ ├── CNRM-CM5_1981-2000.nc │ │ └── MPI-ESM-LR_1981-2000.nc │ └── target/ │ ├── pr_tasmax_CNRM-CM5_1981-2000.nc │ └── pr_tasmax_MPI-ESM-LR_1981-2000.nc │ ├── mid_century/ │ ├── predictors/ │ │ ├── perfect/ │ │ └── imperfect/ │ └── target/ │ └── end_century/ ├── predictors/ │ ├── perfect/ │ └── imperfect/ └── target/ 🎓 Key Terminology Perfect Inference: Using the same GCM realization that was used in training Imperfect Inference: Using different realizations or added noise from the same GCM PP Cross-Validation: Perfect-Prognosis evaluation with the same GCM Hard Transferability: Testing on a completely different GCM than used in training Change Signal: The difference between future and historical climate periods 📚 Resources Main Repository: WCRP-CORDEX/ml-benchmark NZ Preprocessing: CORDEXBench-nzdomain-preprocessing ALPS Preprocessing: CORDEXBench-alpsdomain-preprocessing Last Updated: November 2025