EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Horizon AQI Forecasting Through the Heterogeneous Fusion of a Temporal Convolutional Network and a Graph-Conditioned Causal Transformer

Bingyan Li, Joi San Tan, Hui-Fuang Ng, Seng Poh Lim, Xuekai Wei, Weizhi Xian, Jielu Yan

Applied Sciences · 10.11.2026 · 16 (22) · 11119

DOI: 10.3390/app162211119 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 10.11.2026. Verfasst von Bingyan Li und 6 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Research Program of Chongqing Municipal Education Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent station observations provide a useful basis for air quality index (AQI) forecasting, whereas regional measurements may supply additional context at longer forecast leads. In this study, the forecasts of an independently trained temporal convolutional network (TCN) and a graph-conditioned causal transformer (Graph-CT) are combined. Both use the same input window of 24 h to predict all the hourly leads from 1 to 24 h, and their corresponding outputs are averaged. Air-quality records from 26 stations in the Chengdu–Chongqing economic circle are reconstructed on a common hourly grid, with causal input filling and evaluation restricted to observed targets. Learning rates and training durations are selected on 2021 data, followed by retrospective evaluation on the previously inspected 2022 benchmark. Across five runs, equal fusion achieves a pooled root mean square error (RMSE) of 18.036 ± 0.103 AQI, compared with 19.491 ± 0.063 for TCN, 18.284 ± 0.140 for Graph-CT, 19.413 ± 0.174 for iTransformer, and 19.043 ± 0.455 for Graph WaveNet under the common task. The paired interval includes zero, leaving the advantage over a two-member Graph-CT ensemble unresolved. Validation calibration slightly decreases the RMSE but increases the mean absolute error (MAE), and removing the transformer branch improves the evaluated configuration. Forecast averaging is therefore useful on this benchmark, although the results favour neither equal coefficients as an optimum nor the full architecture over its simpler variants. The evaluation of untouched periods and regions remains necessary for assessing generalization.

Förderung

  • Science and Technology Research Program of Chongqing Municipal Education Commission

Zitieren

APA

Li, B., Tan, J. S., Ng, H., Lim, S. P., Wei, X., Xian, W., & Yan, J. (2026). Multi-Horizon AQI Forecasting Through the Heterogeneous Fusion of a Temporal Convolutional Network and a Graph-Conditioned Causal Transformer. Applied Sciences, 16(22), 11119. https://doi.org/10.3390/app162211119

Vancouver

Li B, Tan JS, Ng H, Lim SP, Wei X, Xian W, et al. Multi-Horizon AQI Forecasting Through the Heterogeneous Fusion of a Temporal Convolutional Network and a Graph-Conditioned Causal Transformer. Applied Sciences. 2026;16(22):11119. doi:10.3390/app162211119

BibTeX
@article{Li2026,
  author = {Li, Bingyan and Tan, Joi San and Ng, Hui-Fuang and Lim, Seng Poh and Wei, Xuekai and Xian, Weizhi and Yan, Jielu},
  title = {Multi-Horizon AQI Forecasting Through the Heterogeneous Fusion of a Temporal Convolutional Network and a Graph-Conditioned Causal Transformer},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {11119},
  doi = {10.3390/app162211119}
}
Kostenlos starten →