EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Simulator-Grounded Benchmarking and a Corpus-Distilled Physics-Informed Forecaster for Fire Hazard-State and Damage Forecasting

Dohun Kim, Seonghee Lee, In-Hwan Lee

Forecasting · 11.08.2026 · 8 (4) · 71

DOI: 10.3390/forecast8040071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forecasting, online erschienen am 11.08.2026. Verfasst von Dohun Kim und 2 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Land, Infrastructure and Transport, Ministry of Culture, Sports and Tourism.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forecasting research repeatedly finds that simple methods can match or beat complex ones out of sample. We test this in a safety-critical domain, near-real-time prediction of fire hazard state and structural damage, using a simulator-grounded benchmark: high-fidelity computational fluid dynamics (Fire Dynamics Simulator, FDS) provides reference data, an FDS-calibrated zone model (CFAST) generates a large corpus cheaply, and the temperature trajectories drive a finite-element model (OpenSees) and a HAZUS/Eurocode-informed damage rule. Under one protocol we compare simple, deep (PatchTST, TimesNet), and physics-informed (PINN, PIKAN) forecasters. Complex models do not dominate: a small corpus lets parsimonious models approach best accuracy, and physics helps mainly when data are scarce (crossover near twenty scenarios). We propose CD-PINN, which identifies a data-optimal reduced-order physics residual from the corpus by physics-guided regression over a candidate library and uses it as the physics constraint. This lifts a per-event physics model to the accuracy of corpus-trained forecasters while staying interpretable. On 26 laboratory-fire experiments, however, in-distribution rankings do not transfer: the large accuracy spread collapses to near-parity, so a leaderboard poorly predicts laboratory-fire accuracy. For downstream damage, we further show that the label definition, not the model class, sets the achievable ceiling.

Förderung

  • Ministry of Land, Infrastructure and Transport
  • Ministry of Culture, Sports and Tourism

Zitieren

APA

Kim, D., Lee, S., & Lee, I. (2026). Simulator-Grounded Benchmarking and a Corpus-Distilled Physics-Informed Forecaster for Fire Hazard-State and Damage Forecasting. Forecasting, 8(4), 71. https://doi.org/10.3390/forecast8040071

Vancouver

Kim D, Lee S, Lee I. Simulator-Grounded Benchmarking and a Corpus-Distilled Physics-Informed Forecaster for Fire Hazard-State and Damage Forecasting. Forecasting. 2026;8(4):71. doi:10.3390/forecast8040071

BibTeX
@article{Kim2026,
  author = {Kim, Dohun and Lee, Seonghee and Lee, In-Hwan},
  title = {Simulator-Grounded Benchmarking and a Corpus-Distilled Physics-Informed Forecaster for Fire Hazard-State and Damage Forecasting},
  journal = {Forecasting},
  year = {2026},
  volume = {8},
  number = {4},
  pages = {71},
  doi = {10.3390/forecast8040071}
}
Kostenlos starten →