GeoClock: Physics-Guided Causal Temporal Learning for GNSS Fault Detection and Classification Under Domain Shift
Geomatics · 01.11.2026 · 6 (6) · 130
DOI: 10.3390/geomatics6060130 ↗Kurz gefasst
Fachartikel in der Zeitschrift Geomatics, online erschienen am 01.11.2026. Verfasst von Jingling Li und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Youth Innovation Promotion Association CAS.
Abstract (Originalsprache)
This study evaluates GeoClock under a raw-hour-disjoint protocol designed to avoid reuse of nominal observation epochs across source training and validation. The model maps variable-cardinality GNSS observations to 80 physical statistical features and processes causal 60-epoch windows using a multi-task temporal convolutional network. BDS_2I, BDS_7I, BDS_6I, and GPS_1C provide source training, validation, and a source lockbox; all GPS_2W hourly files are held out. Across five paired masked-pretraining seeds with seed-specific source-selected thresholds, direct GPS_2W transfer has a mean AUROC of 0.999377 ± 0.001246 and recall of 0.999990 ± 0.000022, but a mean FPR of 0.537431 ± 0.337510. An independently acquired cross-site and cross-domain validation set from Site B (20 one-hour injected files spanning four signal domains and five fault realizations per domain; 14,180 windows and 81 events) yields a frozen direct-transfer AUROC of 0.999983 and an FPR of 0.1108. Under the stated 240 s clean-start assumption, the FPR falls to 0.000545 with recall 0.9721. This experiment evaluates geographically distinct acquisition conditions using the same frozen model and source-selected threshold; because the fault patterns remain injected, it does not establish field integrity or generalization to arbitrary sites. Five-seed GRU and TCN comparisons, residual-threshold diagnostics, feature-family ablations, and component ablations do not resolve threshold portability. A radial ECEF sensitivity analysis shows severe degradation at 3 and 10 m coordinate offsets. The results support controlled recovery of the stated injected observables and expose calibration and position-reference limitations; they do not establish field integrity.
Förderung
- Youth Innovation Promotion Association CAS
Zitieren
APA
Li, J., & Wu, H. (2026). GeoClock: Physics-Guided Causal Temporal Learning for GNSS Fault Detection and Classification Under Domain Shift. Geomatics, 6(6), 130. https://doi.org/10.3390/geomatics6060130
Vancouver
Li J, Wu H. GeoClock: Physics-Guided Causal Temporal Learning for GNSS Fault Detection and Classification Under Domain Shift. Geomatics. 2026;6(6):130. doi:10.3390/geomatics6060130
BibTeX
@article{Li2026,
author = {Li, Jingling and Wu, Huabing},
title = {GeoClock: Physics-Guided Causal Temporal Learning for GNSS Fault Detection and Classification Under Domain Shift},
journal = {Geomatics},
year = {2026},
volume = {6},
number = {6},
pages = {130},
doi = {10.3390/geomatics6060130}
}
EUVIMED