Pith Number

pith:AE7JQX7P

pith:2026:AE7JQX7PUXHK3YOLJESY2ZQS77

not attested not anchored not stored refs resolved

Reduced-Order Surrogates for Forced Flexible Mesh Coastal-Ocean Models

Allan P. Engsig-Karup, Freja H{\o}gholm Petersen, Jesper Sandvig Mariegaard, Rocco Palmitessa

Koopman autoencoders with forcings deliver accurate year-long reduced-order surrogates for coastal-ocean models.

arxiv:2602.05416 v2 · 2026-02-05 · cs.CE · cs.AI · cs.LG · physics.ao-ph · physics.flu-dyn

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{AE7JQX7PUXHK3YOLJESY2ZQS77}

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

Across all cases, the reduced order surrogates with temporal unrolling achieve high accuracy with relative root-mean-squared-errors of 0.0068-0.14 and R²-values of 0.61-0.995... In two of the three cases, the Koopman Autoencoder have higher accuracy than the POD-based surrogates. Comparing to in-situ observations, the surrogate yields -0.64% to 12% increase in water surface elevation prediction error when compared to prediction errors of the physics-based model.

C2weakest assumption

That the learned linear temporal operator in latent space, regularized for eigenvalue stability, continues to produce bounded long-term trajectories when driven by real meteorological forcings outside the three tested regimes.

C3one line summary

Koopman autoencoders with forcings and temporal unrolling deliver accurate year-long predictions for coastal-ocean models at 300-1400x speedup, outperforming POD in two of three cases.

References

38 extracted · 38 resolved · 6 Pith anchors

[1] doi:10.48550/arXiv.2003.02236 2003 · doi:10.48550/arxiv.2003.02236

[2] Brunton, S.L., Brunton, B.W., Proctor, J.L., Kutz, J.N · doi:10.1029/2024gl112835

[3] and Brunton, Bingni W · doi:10.1371/journal.pone.0150171

[4] On the Properties of Neural Machine Translation: Encoder-Decoder Approaches · arXiv:1409.1259

[5] URL:https://comune 2025

Receipt and verification

First computed	2026-06-19T16:12:18.439363Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

013e985fefa5ceade1cb49258d6612fff885412f839049b10b521eef09799c39

Aliases

arxiv: 2602.05416 · arxiv_version: 2602.05416v2 · doi: 10.48550/arxiv.2602.05416 · pith_short_12: AE7JQX7PUXHK · pith_short_16: AE7JQX7PUXHK3YOL · pith_short_8: AE7JQX7P

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/AE7JQX7PUXHK3YOLJESY2ZQS77 \
  | 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: 013e985fefa5ceade1cb49258d6612fff885412f839049b10b521eef09799c39

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "99bfdefa7e46724443be77255529bff02982fc4961bee2a260639cdd81a67ccc",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG",
      "physics.ao-ph",
      "physics.flu-dyn"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CE",
    "submitted_at": "2026-02-05T07:59:58Z",
    "title_canon_sha256": "7506acd9d8ad360236091291992e7f2c32ed310f6022220cabf822e9f9746402"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.05416",
    "kind": "arxiv",
    "version": 2
  }
}