20.500.12556/DKUM-97889 Task-aligned transformer imputation for long-horizon air quality forecasting 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. time-series forecasting imputation transformers LSTM air quality long-horizon prediction napovedovanje časovnih vrst kvaliteta zraka true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/mathematics © 2026 by the authors Članek v reviji 2026-04-22 16:23:00 2026-04-22 16:23:00 2026-04-23 03:11:23 0000-00-00 00:00:00 2026 0 0 22 str. no. 7, [article no.] 1196 Vol. 14 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2026-02-28 2026-04-01 2026-04-03 004.8 274155523 10.3390/math14071196 2227-7390 mathematics-14-01196.pdf mathematics-14-01196.pdf 1 A89B1EE442553291AC6FEE0166E92336 5a71c2c7b69c984aa5a4305134c8cc0716a2270ee7e7d6d24256ed28857556e5 0e9ac309-3e57-11f1-bc9c-00155d0001a1 https://dk.um.si/Dokument.php?lang=slv&id=205546 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0