Accurate prediction of PM_2.5 concentration is crucial for air quality management and public health protection. However, existing methods often struggle to capture and interpret the nonlinear relationships among multiple atmospheric variables. This study proposes GT-iFormer, a novel interpretable deep learning model that integrates graph convolutional networks (GCNs), Temporal Convolutional Networks (TCNs), and inverted Transformer (iTransformer) for PM_2.5 concentration prediction. The model features a GTCN-Block that encapsulates GCN and TCN with residual-style fusion, preserving feature-level dependencies alongside temporal patterns to prevent information degradation. The Pearson correlation coefficients and KNN algorithm are innovatively integrated to build a data-driven graph structure, which allows GCNs to flexibly model the nonlinear relationships between pollutants and meteorological factors based on observed data. TCNs obtain multi-scale temporal patterns via causal dilated convolutions. Subsequently, the concatenated representations of GTCN-Block are input into iTransformer to model global inter-variable interactions using attention mechanisms along the axis of the variable. We incorporated SHAP (SHapley Additive exPlanations) analysis to expose feature importance and nonlinear relationships with PM_2.5 predictions. Results on the hour-level data of Beijing (2020–2021) and Shenzhen (2021) show that our proposed GT-iFormer surpasses all baseline models, with an RMSE of 8.781 μg/m³ and R² of 0.978 for Beijing, and an RMSE of 3.871 μg/m³ and R² of 0.957 for Shenzhen on single-step prediction, equating to RMSE reductions of 15.75% and 17.92%, respectively, over the best baseline model. The SHAP analysis shows clearly distinct regional patterns, with combustion sources dominant in Beijing (represented by CO at 28.231%), and traffic emissions dominant in Shenzhen (represented by NO₂ at 25.908%). Crucial threshold effects are established for all variables, with significant cross-city differences that can serve as general forecasts and guidance for city-specific air quality management policies.

Accurately forecasting air pollutants concentration can reduce health risks and provide an important reference for environmental governance. This study proposes a new deep learning model, GLA-Net, which aims to achieve high-precision prediction of the air quality index (AQI) of monitoring stations. Specifically, GLSTM-Block is designed to use the GAT module to capture dynamic spatial interaction of AQI, generate spatial semantic features, and then use LSTM to capture the temporal correlation characteristics of these spatial characteristics. This paper uses an LSTM network outside of GLSTM-Block to capture the original temporal characteristics of the input data. Then, the temporal characteristics of the LSTM output are added to the dynamic spatiotemporal features of the GLSTM-Block to obtain the final spatiotemporal features as the input of the subsequent temporal attention layer. The temporal attention layer uses a multi-head self-attention mechanism to focus on the impact of the spatiotemporal characteristics of historical air quality data on each prediction time step, and performs AQI prediction through a fully connected layer. Analysis based on measured data from Beijing, Shanghai and Shenzhen shows that the GLA-Net model has significant advantages in predicting single-step and multi-step changes in AQI. The study found that although the model has a large absolute error in predicting concentrations in highly polluted areas, it can better grasp the trend of changes. This feature is particularly evident in Beijing (AQI mean 64.289), with root mean square error (RMSE) of 12.716 and index of agreement (IA) of 0.983.

Outdoor jogging is a significant component of daily physical activities that benefit public health and urban living environments. However, it is still challenging to untangle the intricate associations between environmental variables and jogging paces, due to nonlinear interactions, spatial heterogeneity, and inadequacy in model interpretability. To this end, an interpretable spatial machine learning framework based on the integration of the Geographically Weighted Random Forest (GW-RF) model and SHapley Additive exPlanations (SHAP) is proposed. Drawing on multi-source urban datasets and Beijing’s large-scale jogging trajectory data, this model allows for global and local interpretation of environmental effects on the built, natural, and visual dimensions. The findings are as follows: (1) Built environment variables demonstrate the greatest explanatory power, with street network configuration (GAC, GAI) and population density identified as the dominant predictors of jogging intensity; (2) All environmental variables exhibit nonlinear threshold effects, with SHAP analysis revealing sign-switching points and optimal ranges—moderate NDVI and sky openness promote jogging while extreme values suppress it; (3) Natural and visual variables operate within distinct comfort thresholds, where moderate annual mean temperature, green view index, and sky openness are consistently associated with higher jogging intensity; and (4) The GW-RF model achieves superior predictive performance (R² = 0.7939, RMSE = 8.54, MAE = 5.72) over five benchmark models, confirming the necessity of spatial weighting in nonlinear ensemble learning. By revealing nonlinear response patterns and effective environmental ranges, the study presents quantitative evidence for the understanding urban physical activities and providing methodological guidance for fostering healthier and more activity-supportive urban environments.

Accurate prediction of PM_2.5 concentrations is essential for public health protection and environmental management. However, existing forecasting models face critical challenges in capturing complex temporal dependencies and providing interpretability for decision-making. This study proposes a novel hybrid framework integrating one-dimensional convolutional neural networks (1D CNN), extended Long Short-Term Memory (xLSTM), and attention mechanism (CNN-xLSTM-AM), combined with SHapley Additive exPlanations (SHAP) for interpretable PM_2.5 forecasting. The 1D CNN unit captures local temporal relationships of multivariate sequences. The xLSTM design, based on sLSTM-mLSTM-sLSTM blocks, addresses limitations of traditional LSTM architectures through exponential gating and dual memory structures: sLSTM captures the state-tracking dynamics of scalar memory mixing, and mLSTM captures multivariate dependencies using matrix memory with larger capacity. The attention mechanism assigns dynamic weights to temporal features according to the importance of each time step. Extensive experiments on Beijing hourly data (2020–2021) show that CNN-xLSTM-AM achieves an RMSE of 9.845 μg/m³ and an R² of 0.977 for single-step prediction. Compared with CNN-xLSTM, it reduces RMSE by approximately 8.5% in single-step prediction and by 8.9% and 12.3% at the 2 h and 10 h forecasting horizons, respectively. The SHAP interpretability analysis identifies atmospheric pollutants as the highest contributors to predictive power (57.09%), with carbon monoxide as the top feature (32.791%). SHAP dependence analyses further suggest nonlinear associations between the input factors and model predictions, with potential turning points identified for selected variables, including carbon monoxide, relative humidity, wind speed, and wind direction. These model-derived patterns indicate potential changes in predictive relationships but should not be interpreted as definitive physical thresholds or universal regime shifts in PM2.5 behavior. These results demonstrate the potential of combining predictive modeling with post hoc interpretation to support environmental decision-making and may inform the development of targeted emission-control strategies and threshold-informed early-warning approaches.