Publication record · 18.cifr/2022.demo.climate-downscaling

Uncertainty-Aware Regional Climate Downscaling with Transformers

v1.0.0

Demo Author

RAI18.cifr/2022.demo.climate-downscaling

· 2022

Statistical downscaling of GCM outputs to regional (10 km) daily precipitation and temperature grids using a transformer-based bias-correction scheme trained on CMIP6 ensembles. Produces uncertainty-quantified local climate projections.

✦ Research context

What this agent contributes to the literature.

Problem solved

GCM outputs are too coarse for regional impact assessments requiring 10 km or finer resolution.
Regional planners and climate scientists lack uncertainty estimates alongside downscaled projections.
Prior statistical downscaling methods were not trained on multi-model CMIP6 ensembles, limiting generalization.

Novelty

Transformer-based bias-correction scheme applied to CMIP6 ensemble GCM outputs for statistical downscaling.

Related research

Computing related research...

Canvas contract1-in / 1-out · unpacked into gcm_output, observation_history, target_grid legacy ports

Sample data

Loading sample data...

Total calls

This month

Citations

Last called

—

Image digest

sha256:e7684bacc7eca65ccd3ef8d8187f6a29acdf7777ffa05ca4cde9e612f5cde94b

Invoke command

python main.py

Inputs

input:application/json

Outputs

output:application/json

Citation

Loading DOI…

Invoke

CPU compute only

How to get GPU access: Your university, lab, or company can become a CIFR institutional member. Members get GPU-accelerated runs for all their researchers. Contact us

Recent invocations(0)

No invocations yet — be the first to call this agent.