Metraipolis › archive › dc_cf42e447f584
More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting — arXiv:2609.31325
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31325
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:13:12.858Z
- SHA-256 of the archived text
58fcbd9791c26840f78f8fe285ae5211137baccdc985097b5703ff0490899c01- Stable URL of this page
https://metraipolis.com/documento/dc_cf42e447f584
How to cite
More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting — arXiv:2609.31325 — arXiv (en), https://arxiv.org/abs/2609.31325 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf42e447f584 (Metraipolis archive dc_cf42e447f584, sha256 58fcbd9791c26840f78f8fe285ae5211137baccdc985097b5703ff0490899c01)
BibTeX
@misc{dccf42e447f584,
title = {More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting — arXiv:2609.31325},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31325},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf42e447f584; sha256 58fcbd9791c26840f78f8fe285ae5211137baccdc985097b5703ff0490899c01},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31325. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Continual spatio-temporal forecasting supports traffic management and environmental monitoring under evolving dynamics and expanding sensor networks. However, conventional graph-based continual learning methods tie forecasting representations to the current sensor layout, so sensor expansion can alter the representation of learned spatial relationships. Our key insight is that sensor expansion changes the evidence available about a process without necessarily changing the dynamics to be learned. We propose STFO (Spatio-Temporal Field Operator), which parameterizes forecasting knowledge as a shared field-evolution operator and handles changing sensor layouts through observation and query interfaces. Normalized coordinate-based aggregation lifts irregular sensor histories onto a fixed latent grid, enabling reuse of learned spatial maps across observation sets without sensor-specific parameters. To accommodate process drift, a spectral descriptor summarizes variation across spatial scales and conditions Fourier propagation and attention to adapt operator responses to the current spatial regime. Coordinate-based decoding queries the evolved field at sensor locations and combines spatial corrections with local-history predictions. Experiments on PEMS-Stream, CA-Stream, and AIR-Stream demonstrate state-of-the-art average forecasting performance. STFO-Large reduces average MAE over DOL by 8.4% on PEMS-Stream and 4.7% on CA-Stream. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.31325 — 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 2026-10-08T01:43:06.744Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).