He Zhenfang, Guo Qingchun, Wang Zhaosheng, Li Xinzhou
School of Geography and Environment, Liaocheng University, Liaocheng 252000, China.
Institute of Huanghe Studies, Liaocheng University, Liaocheng 252000, China.
Toxics. 2025 Mar 28;13(4):254. doi: 10.3390/toxics13040254.
Surface air pollution affects ecosystems and people's health. However, traditional models have low prediction accuracy. Therefore, a hybrid model for accurately predicting daily surface PM concentrations was integrated with wavelet (W), convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), and bidirectional gated recurrent unit (BiGRU). The data for meteorological factors and air pollutants in Guangzhou City from 2014 to 2020 were utilized as inputs to the models. The W-CNN-BiGRU-BiLSTM hybrid model demonstrated strong performance during the predicting phase, achieving an R (correlation coefficient) of 0.9952, a root mean square error (RMSE) of 1.4935 μg/m, a mean absolute error (MAE) of 1.2091 μg/m, and a mean absolute percentage error (MAPE) of 7.3782%. Correspondingly, the accurate prediction of surface PM concentrations is beneficial for air pollution control and urban planning.
地面空气污染会影响生态系统和人们的健康。然而，传统模型的预测准确率较低。因此，一种用于精确预测每日地面PM浓度的混合模型被整合了小波（W）、卷积神经网络（CNN）、双向长短期记忆（BiLSTM）和双向门控循环单元（BiGRU）。2014年至2020年广州市的气象因素和空气污染物数据被用作模型的输入。W-CNN-BiGRU-BiLSTM混合模型在预测阶段表现出强大的性能，相关系数R为0.9952，均方根误差（RMSE）为1.4935μg/m，平均绝对误差（MAE）为1.2091μg/m，平均绝对百分比误差（MAPE）为7.3782%。相应地，精确预测地面PM浓度有利于空气污染控制和城市规划。
