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

 

Introduction to CORDEX-ML-Bench: A Benchmarking Dataset for Data-driven Regional Climate Downscaling

CORDEXBench is a standardized benchmarking dataset designed to evaluate empirical-statistical downscaling (ESD) and deep learning-based regional climate emulators. It supports rigorous model evaluation across multiple climate zones and experimental setups. This dataset spans three distinct geographic domains:

• New Zealand (NZ) - 0.11° resolution

• Europe (ALPS) - 0.11° resolution

• South Africa - 0.10° resolution

Each region includes carefully structured training and testing data derived from dynamically downscaled Global Climate Models (GCMs), enabling systematic analysis of emulator performance in both historical and future climates.

The dataset provides two core training experiments:

1. ESD Pseudo-Reality (1961–1980)
   A 20-year historical training period using a single GCM (e.g., ACCESS-CM2 for NZ), designed to mimic ESD training. 

2. Emulator Hist+Future (1961–1980 + 2081–2100)
   A more comprehensive 40-year training period combining historical and future climates. This experiment supports evaluation of extrapolative skill, including transferability across GCMs.

Both setups will be tested with and without topography as a predictor. 

For each training setup, the dataset enables evaluation across multiple test periods and inference conditions:

• Historical (1981–2000): For both perfect and imperfect inference.

• Mid-century (2041–2060) and End-century (2081–2100): To assess extrapolation to future climates, including hard transferability scenarios using unseen GCMs.

Evaluation Types

The dataset supports several benchmarking configurations:

• PP cross-validation: Same GCM used in training and testing.

• Imperfect inference: Same GCM but different realizations or noise.

• Transferability testing: Inference using a different GCM than the training set.

• Change signal evaluation: Assessment of climate change response in future periods.

Data Structure Example: New Zealand Domain

Each domain follows a consistent file structure, with subdirectories for training and testing data, and further divisions by period, GCM, and evaluation type. Predictors include both dynamic variables (e.g., temperature, precipitation) and optional static fields (e.g., topography).

NZ_Domain/
├── train/
│   ├── ESD_pseudo-reality/
│   │   ├── predictors/
│   │   └── target/
│   ├── Emulator_hist_future/
│   │   ├── predictors/
│   │   └── target/
├── test/
│   ├── historical/
│   ├── mid_century/
│   └── end_century/

A More Detailied Overview of the Experiments

📘 Table 1: Evaluation using ESD “pseudo-reality” (T1)

Training Setup	Inference Set	Evaluation Type	Notes	Eval	Required
ESD “pseudo-reality” Period: 1961–1980 Static fields: Yes/No	historical (1981–2000)	PP cross-validation	Same GCM used in training, perfectly	Error, Clim	X
	historical 1981–2000	Imperfect cross validation	Same GCM, but imperfectly	Error, Clim
	2041-2060 + 2081-2100	Extrapolation	Same GCM, but perfectly	change signal	X
	2041-2060 + 2081-2100	Extrapolation	Same GCM but imperfectly	change signal

 

📗 Table 2: Evaluation using Emulator (T2)

Training Setup	Inference Set	Evaluation Type	Notes	Eval	Required
Emulator hist + future   period: 1961-1980 + 2081-2100   Static fields: Yes/No	historical (1981–2000)	PP cross-validation	Same GCM used in training, perfectly	Error, Clim	X
	historical 1981–2000	Imperfect cross validation	Same GCM, but imperfectly	Error, Clim	X
	2041-2060 + 2081-2100	Extrapolation	Same GCM, but perfectly	change signal	X
	2041-2060 + 2081-2100	Extrapolation / Hard Transferibility	Different GCM, but perfectly	change signal	X
	2041-2060 + 2081-2100	Extrapolation / Hard Transferibility	Different GCM, but imperfectly	change signal	X

# 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/
│   │   │   │   ├── ACCESS-CM2_2040-2059.nc
│   │   │   │   └── ...
│   │   │   └── imperfect/
│   │   │       ├── ACCESS-CM2_2040-2059.nc
│   │   │       └── ...
│   │   └── target/
│   │       ├── pr_tasmax_ACCESS-CM2_2040-2059.nc
│   │       └── ...
│
│   └── end_century/
│       ├── predictors/
│       │   ├── perfect/
│       │   │   ├── ACCESS-CM2_2080-2099.nc
│       │   │   └── ...
│       │   └── imperfect/
│       │       ├── ACCESS-CM2_2080-2099.nc
│       │       └── ...
│       └── target/
│           ├── pr_tasmax_ACCESS-CM2_2080-2099.nc
│           └── ...

# 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/
│   │   │   │   ├── CNRM-CM5_2040-2059.nc
│   │   │   │   └── MPI-ESM-LR_2040-2059.nc
│   │   │   └── imperfect/
│   │   │       ├── CNRM-CM5_2040-2059.nc
│   │   │       └── MPI-ESM-LR_2040-2059.nc
│   │   └── target/
│   │       ├── pr_tasmax_CNRM-CM5_2040-2059.nc
│   │       └── pr_tasmax_MPI-ESM-LR_2040-2059.nc
│
│   └── end_century/
│       ├── predictors/
│       │   ├── perfect/
│       │   │   ├── CNRM-CM5_2080-2099.nc
│       │   │   └── MPI-ESM-LR_2080-2099.nc
│       │   └── imperfect/
│       │       ├── CNRM-CM5_2080-2099.nc
│       │       └── MPI-ESM-LR_2080-2099.nc
│       └── target/
│           ├── pr_tasmax_CNRM-CM5_2080-2099.nc
│           └── pr_tasmax_MPI-ESM-LR_2080-2099.nc

Data Preprocessing

For information (roughly) on how the data was preprocessed, please see the following repositories for the different regions: 

• NZ: github.com
• ALPS: github.com