Pith Number

pith:CGSKRP57

pith:2025:CGSKRP57ERNJIABLVER34J6BGY

not attested not anchored not stored refs pending

Beyond the Training Data: Confidence-Guided Mixing of Parameterizations in a Hybrid AI-Climate Model

Helge Heuer, Julien Savre, Manuel Schlund, Mierk Schwabe, Tom Beucler, Veronika Eyring

A neural network for convection predicts its own error to mix with a physics scheme, enabling stable hybrid climate simulations.

arxiv:2510.08107 v5 · 2025-10-09 · physics.ao-ph

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{CGSKRP57ERNJIABLVER34J6BGY}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

The NN parameterization predicts its own error, enabling mixing with a conventional convection scheme when confidence is low, thus making the hybrid AI-physics model tunable with respect to observations and reanalysis through mixing parameters. This improves process understanding by constraining convective tendencies across column water vapor, lower-tropospheric stability, and geographical conditions... In AMIP-style setups, several hybrid configurations outperform the default convection scheme (e.g., improved precipitation statistics). With additive input noise during training, both hybrid and pure-ML schemes lead to stable simulations and remain physically consistent for at least 20 years.

C2weakest assumption

The neural network trained on adjusted ClimSim data with subtracted radiative tendencies can be transferred to ICON-A despite distribution shifts, and its self-predicted confidence score reliably indicates actual inference errors in the new model to enable effective mixing.

C3one line summary

A ClimSim-trained physics-informed NN convection parameterization is transferred to ICON-A with confidence-guided mixing to a conventional scheme, yielding stable 20-year AMIP simulations that outperform the default convection scheme in precipitation statistics.

Cited by

2 papers in Pith

No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation

climt-paraformer: Stable Emulation of Convective Parameterization using a Temporal Memory-aware Transformer

Receipt and verification

First computed	2026-05-20T00:00:25.778611Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

11a4a8bfbf245a94002ba923be27c136353ebeef343a921c81cf16947c73f010

Aliases

arxiv: 2510.08107 · arxiv_version: 2510.08107v5 · doi: 10.48550/arxiv.2510.08107 · pith_short_12: CGSKRP57ERNJ · pith_short_16: CGSKRP57ERNJIABL · pith_short_8: CGSKRP57

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/CGSKRP57ERNJIABLVER34J6BGY \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 11a4a8bfbf245a94002ba923be27c136353ebeef343a921c81cf16947c73f010

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "20feba5992b58025b3cefd5a75d4fea4bb01c9a0ef88c8957c50d02178c032cf",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "physics.ao-ph",
    "submitted_at": "2025-10-09T11:44:47Z",
    "title_canon_sha256": "84b91c30c857359da6c4ca1cba0eb59dda812210af31bac9cf46f586f78f179a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2510.08107",
    "kind": "arxiv",
    "version": 5
  }
}