EUVIMEDEUVIMED entdecken
Crossref

MIST-Net: A heterogeneous spatiotemporal network for regional ozone forecasting robust to sparse data

Muzhe Wu, Zhizhang Shen

Environmental Research · 2026

DOI: 10.1016/j.envres.2026.125839 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Research, 2026. Verfasst von Muzhe Wu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Environment and Ecology, Jiangnan University, 1800 Lihu Ave, Wuxi, Jiangsu, 214122, China. Electronic address: 1103230120@stu.jiangnan.edu.…. Hauptthemen laut MEDLINE: Ozone, Air Pollutants, Environmental Monitoring, Air Pollution. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Ministry of Science and Technology of the People's Republic of China, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate regional ozone (O3) forecasting remains challenging due to complex multi-pollutant chemical interactions and the inherent sparsity of real-world monitoring data. Existing spatiotemporal models often fail to explicitly decouple heterogeneous variables and rely on error-prone imputation methods to handle missing inputs. To address these issues, we propose a Multi-pollutant Interaction Spatiotemporal Network (MIST-Net), which treats individual environmental factors as independent heterogeneous nodes and employs a dual-graph architecture: an Intra-Station Graph to capture cross-variable dependencies, and an Inter-Station Graph for spatial dependencies. Additionally, an integrated dual-channel missingness indicator mechanism enables the model to learn robustly and directly from incomplete data including missing records and unstructured data. Extensive evaluations on two diverse datasets (Los Angeles and Madrid) demonstrate that MIST-Net achieves highly competitive performance. For 1-h forecasting, MIST-Net reduced Root Mean Square Error (RMSE) by 25.08% over SARIMA and 18.43% over DCRNN on the LA dataset. Under an extreme 40% random data missing rate, MIST-Net exhibited robustness, limiting the increase in RMSE to within 13.0% for 12-h forecasting. Furthermore, attention-based analyses provide an exploratory perspective on empirical inter-variable lag correlations and learned spatial correlation topologies. Ultimately, MIST-Net offers a robust deep learning paradigm for resilient air quality monitoring under sensor-failure scenarios and at newly deployed, unmonitored sites.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OzoneAir PollutantsEnvironmental MonitoringAir PollutionForecastingSpainNeural Networks, ComputerPrediction Algorithms

Stichwörter der Autor:innen

Data sparsityHeterogeneous graphRegional ozone forecastingResilient air quality monitoringSpatiotemporal graph neural network

Substanzen

OzoneAir Pollutants

Autor:innen und Institutionen

  • School of Environment and Ecology, Jiangnan University, 1800 Lihu Ave, Wuxi, Jiangsu, 214122, China. Electronic address: 1103230120@stu.jiangnan.edu.cn.
  • School of Environment and Ecology, Jiangnan University, 1800 Lihu Ave, Wuxi, Jiangsu, 214122, China. Electronic address: zshen@jiangnan.edu.cn.

Förderung

  • Ministry of Science and Technology of the People's Republic of China
  • National Key Research and Development Program of China

Zitieren

APA

Wu, M., & Shen, Z. (2026). MIST-Net: A heterogeneous spatiotemporal network for regional ozone forecasting robust to sparse data. Environmental Research. https://doi.org/10.1016/j.envres.2026.125839

Vancouver

Wu M, Shen Z. MIST-Net: A heterogeneous spatiotemporal network for regional ozone forecasting robust to sparse data. Environmental Research. 2026. doi:10.1016/j.envres.2026.125839

BibTeX
@article{Wu2026,
  author = {Wu, Muzhe and Shen, Zhizhang},
  title = {MIST-Net: A heterogeneous spatiotemporal network for regional ozone forecasting robust to sparse data},
  journal = {Environmental Research},
  year = {2026},
  doi = {10.1016/j.envres.2026.125839}
}
Kostenlos starten →