融合GNSS水汽、风速与大气污染物的河北省冬季PM2.5浓度预测研究

为提高PM_2.5浓度预测的时效和精度，本文综合大气污染物、GNSS水汽和风速等观测要素，利用FFT与LSTM神经网络方法构建PM_2.5浓度预测模型，开展未来24 h的PM_2.5浓度预测研究。首先对大气污染物、GNSS水汽和风速等观测要素进行快速傅里叶变换，提取各类要素的公共变化周期，获得最佳公共周期为216 h；然后选取最佳公共周期长度的各类要素作为模型输入，24 h序列的PM_2.5浓度作为模型输出，分别以PM_2.5单要素的RBF神经网络和融合大气污染物、风速、GNSS水汽的LSTM神经网络构建PM_2.5浓度预测模型；最后利用实测PM_2.5浓度序列分别对2种模型开展外部可靠性检验，将RMSE和IA作为评价指标进行模型精度评价。研究结果表明，基于FFT-LSTM的PM_2.5浓度预测模型的RMSE和IA分别为16.22 μg/m³和84.36%，模型预测精度较好，可有效预测未来24 h的PM_2.5浓度，该模型可为大气污染防治部门空气质量预测提供参考。

Study on the Prediction of PM2.5 Concentration of Hebei Province in Winter by Combining GNSS PWV,Wind Speed

In order to improve the timeliness and accuracy of PM_2.5 concentration prediction, this paper integrates observation factors such as atmospheric pollutants, GNSS PWV and wind speed, and uses the methods of FFT and LSTM neural network to build thePM_2.5 concentration prediction model to predictPM_2.5 concentration in the next 24 hours. Firstly, fast Fourier transform is applied to the observation elements such as air pollutants, GNSS PWV and wind speed, and the common change period of various elements is extracted to obtain the optimal common period of 216 hours. Then, various elements of the optimal common period length are selected as the model input, and thePM_2.5 concentration of 24-hour sequence are taken as the model output. The RBF neural network ofPM_2.5 single elements and the LSTM neural network integrating atmospheric pollutants, wind speed and GNSS PWV are respectively used to construct thePM_2.5 concentration prediction model. Finally, the measuredPM_2.5 concentration sequence is used to test the external reliability of the two models,RMSE and IA are used as evaluation indexes to evaluate the model accuracy. The results show that the RMSE and IA tested by thePM_2.5 concentration prediction model based on FFT-LSTM are 16.22 μg /m³ and 84.36%, respectively. The prediction accuracy of the model could effectively predict thePM_2.5 concentration in the next 24 hours. The model can be used as a reference of air quality prediction for air pollution prevention department.