Metraipolis › archive › dc_e1cb46e85386
Zero-shot time-series foundation models against the Khepri v1.5 baselines for 96-hour carbon-intensity forecasts in nine Nordic bidding zones: a preregistered comparison — arXiv:2611.02895
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02895
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:25:27.639Z
- SHA-256 of the archived text
24197a70acb1e830a058d89bb2f4ef9994bcaf32bebf522bdd4d77c7360ed3fc- Stable URL of this page
https://metraipolis.com/documento/dc_e1cb46e85386
How to cite
Zero-shot time-series foundation models against the Khepri v1.5 baselines for 96-hour carbon-intensity forecasts in nine Nordic bidding zones: a preregistered comparison — arXiv:2611.02895 — arXiv (en), https://arxiv.org/abs/2611.02895 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1cb46e85386 (Metraipolis archive dc_e1cb46e85386, sha256 24197a70acb1e830a058d89bb2f4ef9994bcaf32bebf522bdd4d77c7360ed3fc)
BibTeX
@misc{dce1cb46e85386,
title = {Zero-shot time-series foundation models against the Khepri v1.5 baselines for 96-hour carbon-intensity forecasts in nine Nordic bidding zones: a preregistered comparison — arXiv:2611.02895},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02895},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1cb46e85386; sha256 24197a70acb1e830a058d89bb2f4ef9994bcaf32bebf522bdd4d77c7360ed3fc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02895. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We compare three zero-shot time-series foundation models (Timestral-5M, Timestral-209M and Chronos-2, 8192-hour context, no covariates) with the Khepri v1.5 SARIMA and GBM baselines, with their code and hyperparameters unchanged, for 96-hour forecasts of hourly carbon intensity in the Nordic bidding zones NO1-NO5 and SE1-SE4. The design, the analysis code and a minimum detectable effect (MDE) were timestamped before any foundation-model forecast by an OpenTimestamps proof (Bitcoin-confirmed) and the GPG-signed tag prereg-v1; the proofs are archived in Zenodo (DOI https://doi.org/10.5281/zenodo.23881315 ). The preregistration was also submitted to OSF Registries 2026-11-02 07:49 UTC ( this http URL embargo requested, pending OSF approval). On the 2025 test (361 daily origins, contamination not ruled out) all three models have a lower zone-averaged MAPE than both baselines, by 0.952 to 1.347 percentage points (Diebold-Mariano with the Harvey-Leybourne-Newbold correction, all p < 0.0001), and each beats SARIMA in 9 of 9 zones. On a post-release holdout of 14 origins from 2026-10-16 the point estimates have the same sign (0.729 to 1.326 percentage points lower), but all lie within the preregistered MDE of 2.989 points and are reported as not determined. For calibration (RQ4) the preregistration locked a Diebold-Mariano-HLN test on CRPS; the MDE applies to MAPE only. Holdout CRPS point estimates (n = 14) are 1.1114 (Timestral-5M), 1.0733 (Timestral-209M) and 1.1198 (Chronos-2) against 1.4165 gCO2-eq/kWh for SARIMA (each p < 0.0001). The SARIMA quantiles are constructed from the fitted model's Gaussian predictive distribution (deviation D-03), not taken from a native v1.5 forecast, so the difference may partly reflect the SARIMA intervals. The contamination indicator does not exceed its preregistered threshold for any comparison; with 14 holdout origins it has low power (HAC standard errors 0.124 to 0.360 pp). Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Physics and Society (physics.soc-ph) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.02895 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T11:02:37.888Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).