Cross-Variable Coupling and Period-Adaptive Learning for Interpretable Atmospheric Pollution Forecasting in Sustainable Environmental Management

Gas-sensor-based air quality forecasting is important for short-term pollutant concentration prediction and environmental monitoring support. However, practical monitoring records are affected by complex interactions among gaseous pollutants, metal oxide sensor responses, and available meteorological variables, while missing observations, abnormal fluctuations, and observation-quality variations may reduce forecasting reliability. Focusing on the UCI Air Quality Dataset, this study proposes an Interpretable Environmental Multi-scale Temporal Network (IEMTN) for multivariate gaseous pollutant forecasting. The proposed model uses historical pollutant concentrations, metal oxide sensor responses, and meteorological variables to support one-step, multi-step, and multi-target prediction of CO(GT), NO x (GT), NO 2 (GT), and C 6 H 6 (GT), which are the reference concentration targets provided in the dataset. Specifically, IEMTN constructs a dynamic environmental variable graph to characterize time-varying coupling relationships among pollutant variables, sensor response signals, and meteorological factors. It further introduces an observation-quality-aware temporal representation module to incorporate missing-value masks, missing-duration information, and temporal-deviation indicators, thereby reducing the influence of incomplete or unreliable observations. In addition, an adaptive multi-period temporal modeling module is designed to capture short-term fluctuations, diurnal variations, accumulation effects, and longer-range temporal patterns. Gradient-based attribution and perturbation-based analysis are also incorporated to improve prediction transparency. Experimental results show that IEMTN achieves the best one-step forecasting performance among the compared models, with average MAE, RMSE, MAPE ϵ , and R 2 values of 8.040, 12.721, 8.99%, and 0.956, respectively. For 24-step forecasting, IEMTN obtains MAE and RMSE values of 13.680 and 23.100, respectively, and maintains strong performance in multi-pollutant joint prediction. Ablation and interpretability analyses further confirm the contribution of the proposed modules. Overall, IEMTN provides a robust and interpretable modeling framework for pollutant concentration forecasting within the current gas-sensor-based monitoring dataset, while broader validation on multi-station datasets, additional pollutant types, and richer meteorological variables is still required.