首页|期刊导航|Computer Modeling in Engineering & Sciences|Frequency-Aware Spatiotemporal Graph Modeling of Multi-Pollutant Dynamics in Industrial Air Quality Systems

Frequency-Aware Spatiotemporal Graph Modeling of Multi-Pollutant Dynamics in Industrial Air Quality SystemsOA

中文摘要

Industrial air quality forecasting remains challenging due to nonlinear pollutant formation,localized emissions,meteorological variability,and nonstationary spatiotemporal dependencies among monitoring stations.This study proposes FFTGNet,a frequency-aware spatiotemporal graph neural network for multi-pollutant forecasting in industrial air quality systems.It integrates an FFT-guided dominant-period estimation and period-folding module with a temporal-to-spatial graph backbone composed of TemporalGLU and Chebyshev graph convolution.The frequency-guided module reorganizes input sequences into intra-period and inter-period representations,Temporal-GLU adaptively filters nonlinear temporal fluctuations and short-term spikes,and ChebGCN propagates information across inter-station spatial dependencies.Experiments were conducted using five years of hourly observations fromten Photochemical Assessment Monitoring Stations in Yunlin,Taiwan,covering O_(3),CO,PM10,meteorological variables,and PMF-derived VOC source features.Compared with conventional baselines and recent spatiotemporal models,includingMGCGRU-SANand AirNN-Adapted,the proposedmethod achieves themost consistent performance across pollutants and forecasting horizons.For 1 h forecasting,it obtains R^(2) values of 0.9509,0.8574,and 0.8556 forO_(3),CO,and PM10,respectively.For O_(3),it further maintains R^(2) values of 0.8116 and 0.6797 at the 3 and 6 h horizons,while showing smooth degradation rather than abrupt performance collapse up to 24 h.Ablation results confirm the complementary contributions of frequency-guided period folding,gated temporal modeling,and graph-based spatial propagation.Computational analysis further indicates that FFTGNet remains feasible for server-side near-real-time deployment,with an inference latency of 71.7ms per sample.These results demonstrate that coupling frequency-domain priors with spatiotemporal graph learning improves forecasting accuracy,stability,and applicability for industrial multi-pollutant air quality systems.

Chia-Hui Liu;Chen-Chuan Cheng

Department of Electronic Engineering,National Formosa University,Yunlin,TaiwanDepartment of Electronic Engineering,National Formosa University,Yunlin,Taiwan

资源环境

Frequency-aware learningspatiotemporal graphmodelsmulti-pollutantindustrial air quality systemsfast fourier transform

《Computer Modeling in Engineering & Sciences》 2026 (8)

P.1216-1241,26

10.32604/cmes.2026.083813

评论