ArchesClimate-SSP

Deep-learning climate emulator (Swin-Transformer-based, autoregressive) trained to reproduce IPSL-CM6A-LR and CanESM5 monthly climate states conditioned on external forcings (GHGs, aerosols, ozone, solar irradiance). Generates unseen SSP scenario trajectories cheaply, without rerunning the full Earth System Model.

Code: https://github.com/grahamclyne/ArchesClimate-SSP (see INFERENCE.md there for the full inference recipe).

What's in this repo

Only what's needed to instantiate and load the network — weights + the Hydra config each checkpoint was trained with:

<run_name>/
  model.ckpt    # model weights (raw + EMA)
  config.yaml   # exact training-time Hydra config

Required companion data

This repo does not include initial conditions, forcing (boundary condition) trajectories, static fields, or normalization stats — those live in the paired dataset repo: gclyne/ArchesClimate-data.

See INFERENCE.md in the code repo for exactly which files from that dataset repo are needed for a given checkpoint, and how to run a rollout.

Runs currently published here

Run	Grid	Notes
archesclimate-ssp-deterministic	IPSL-CM6A-LR	Single free-running deterministic prediction per step
archesclimate-ssp-energy-score	IPSL-CM6A-LR	Energy-score-trained, supports a stochastic ensemble
archesclimate-ssp-canesm5-energy-score	CanESM5 (native grid)	Energy-score-trained, native CanESM5 64x128 grid