Fig 1.
Overview of the STGATN model architecture.
The model input consists of pollutant concentration, location, and timestamp data. The GTCN models temporal causal relationships at monitoring stations in a non-recursive manner. The ST-Block employs temporal attention to capture nonlinear correlations across time steps and integrates graph attention to model dynamic spatial dependencies. A fusion gate integrates temporal causal correlations with dynamic spatiotemporal features. A transformer attention layer between the encoder and decoder generates future representations.
Table 1.
Data distribution.
Table 2.
Model hyperparameters.
Table 3.
The effectiveness of different pollutants for long-term PM2.5 concentration prediction.
Table 4.
The effectiveness of different meteorological factors for long-term PM2.5 concentration prediction.
Table 5.
Comparison of the STGATN model and baseline model proposed in this article for long-term pollutant concentration prediction tasks.
Table 6.
The performance of long-term PM2.5 concentration prediction.
Table 7.
Computing cost of the proposed method on the Beijing dataset.
Fig 2.
The prediction result of STGATN (prediction of the first time step).
In the legend, the orange dashed line represents the predicted PM2.5 value, and the blue solid line represents the actual observed value. Randomly select 200 consecutive test samples from the test set.
Fig 3.
Prediction Results of STGATN (Third Time Step Prediction).
Fig 4.
Prediction results of STGATN (6th time step prediction).
Table 8.
The performance of the proposed STGATN on distinct concentration levels.
Table 9.
The performance of the proposed STGATN on distinct temporal patterns.