A Spatial–Temporal Causal Convolution Network Framework for Accurate and Fine-Grained PM2.5 Concentration Prediction

Abstract

Accurate and fine-grained prediction of PM2.5 concentration is of great significance for air quality control and human physical and mental health. Traditional approaches, such as time series, recurrent neural networks (RNNs) or graph convolutional networks (GCNs), cannot effectively integrate spatial–temporal and meteorological factors and manage dynamic edge relationships among scattered monitoring stations. In this paper, a spatial–temporal causal convolution network framework, ST-CCN-PM2.5, is proposed. Both the spatial effects of multi-source air pollutants and meteorological factors are considered via spatial attention mechanism. Time-dependent features in causal convolution networks are extracted by stacked dilated convolution and time attention. All the hyper-parameters in ST-CCN-PM2.5 are tuned by Bayesian optimization. Haikou air monitoring station data are employed with a series of baselines (AR, MA, ARMA, ANN, SVR, GRU, LSTM and ST-GCN). Final results include the following points: (1) For a single station, the RMSE, MAE and R2 values of ST-CCN-PM2.5 decreased by 27.05%, 10.38% and 3.56% on average, respectively. (2) For all stations, ST-CCN-PM2.5 achieve the best performance in win–tie–loss experiments. The numbers of winning stations are 68, 63, and 64 out of 95 stations in RMSE (MSE), MAE, and R2, respectively. In addition, the mean MSE, RMSE and MAE of ST-CCN-PM2.5 are 4.94, 2.17 and 1.31, respectively, and the R2 value is 0.92. (3) Shapley analysis shows wind speed is the most influencing factor in fine-grained PM2.5 concentration prediction. The effects of CO and temperature on PM2.5 prediction are moderately significant. Friedman test under different resampling further confirms the advantage of ST-CCN-PM2.5. The ST-CCN-PM2.5 provides a promising direction for fine-grained PM2.5 prediction.

TimesNet-PM2.5: Interpretable TimesNet for Disentangling Intraperiod and Interperiod Variations in PM2.5 Prediction

“…Our method performed the best in eight models. Moreover, when comparing TimesNet-PM2.5 to other models on predicting PM2.5 concentration for the next 1 h from the literature [7], it was evident that our model was superior in terms of MSE, RMSE, and MAE (in Table 4). For instance, TimesNet-PM2.5 exhibited an MSE of 4.98, which was better than other models expect ST-CCN-PM 2.5 .…”

“…In this study, a modified version of TimesNet, termed TimesNet-PM2.5, is proposed, tailored specifically for the task of PM2.5 forecasting. Through extensive experiments, it becomes evident that TimesNet-PM2.5 outperforms not only the original state-of-the-art TimesNet model, but also other benchmark models such as ARIMA [6] and ST-CCN-PM 2.5 [7], in PM2.5 prediction scenarios across varied prediction lengths, ranging from 1 to 24 h. This consistent enhanced performance underscores the efficacy of the modifications introduced to TimesNet-PM2.5, rendering it a potent solution for PM2.5 forecasting. The salient contributions and innovations are summarized as follows:…”

Prediction of daily fine particulate matter (PM2.5) concentration in Aksaray, Turkey: Temporal variation, meteorological dependence, and employing artificial neural network

“…Table 4 presents a comprehensive comparison of findings between the studies published in the literature and the technique utilized in this study 14,54,55,60–66 . It highlights key aspects such as the region, the specific neural network technique, and evaluation metrics.…”

Optimized deep learning models for effluent prediction in wastewater treatment processes

“…24 BO is able to tune the hyperparameters of the spatiotemporal causal convolution network structure to perform well in PM 2.5 concentration prediction. 25 In summary, BO is a global optimization technique grounded in probabilistic models, striving to identify the optimal solution to the objective function with minimal iterations. It boasts high sampling efficiency, effectively leveraging limited data samples to enhance the precision of model predictions.…”