Task-Aligned Transformer Imputation for Long-Horizon Air Quality Forecasting
Mathematics · 03.04.2026 · 14 (7) · 1196
DOI: 10.3390/math14071196 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 03.04.2026. Verfasst von Grega Vrbančič und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Slovenian Research and Innovation Agency.
Abstract (Originalsprache)
Accurate long-horizon air-quality forecasting becomes difficult when historical observations are missing or irregularly sampled because reconstruction errors can propagate into downstream predictions. In this work, we propose the TILSTM method, a task-aligned hybrid architecture that integrates a Transformer-based imputation module with an LSTM forecaster designed to jointly enforce a causal horizon boundary that restricts imputation strictly to the historical look-back window, an observed-preserving merge that leaves measured values unchanged, and a time-aware decay gate applied selectively to imputed positions. The model is trained end-to-end using a combined forecasting loss and a self-supervised imputation loss computed on artificially masked observed entries. We evaluate TILSTM on hourly PM10 forecasting from 21 monitoring stations in Slovenia across three forecasting horizons and three missingness regimes. Among the compared methods, TILSTM shows the clearest and most consistent gains at the 24 h horizon, while at medium horizons, the relative ranking becomes more dependent on the missingness regime. In pooled error summaries, TILSTM achieves the lowest MAE and RMSE at the 168 h horizon under the real and near_origin missingness regimes, while the overall results indicate that no single method is uniformly best across all long-horizon settings.
Förderung
- The Slovenian Research and Innovation Agency
Zitieren
APA
Vrbančič, G., Podgorelec, V., & Brezočnik, L. (2026). Task-Aligned Transformer Imputation for Long-Horizon Air Quality Forecasting. Mathematics, 14(7), 1196. https://doi.org/10.3390/math14071196
Vancouver
Vrbančič G, Podgorelec V, Brezočnik L. Task-Aligned Transformer Imputation for Long-Horizon Air Quality Forecasting. Mathematics. 2026;14(7):1196. doi:10.3390/math14071196
BibTeX
@article{Vrbani2026,
author = {Vrbančič, Grega and Podgorelec, Vili and Brezočnik, Lucija},
title = {Task-Aligned Transformer Imputation for Long-Horizon Air Quality Forecasting},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {7},
pages = {1196},
doi = {10.3390/math14071196}
}
EUVIMED