融合GNSS、ERA5、大气污染物的PM_(2.5)浓度预测研究

Study on PM_(2.5)concentration prediction by integrating GNSS,ERA5 PWV,and atmospheric pollutants

冬春季节的空气质量预测有助于公众合理安排出行和政府相关部门的交通治理.细颗粒物(PM_(2.5))的浓度主要影响因素有大气污染物、水汽等.为提高PM_(2.5)浓度预测的精度,以京津冀地区为例,利用快速傅里叶变换(fast Fourier transform,FFT)与长短期记忆(long short term memory,LSTM)神经网络方法相结合,考虑GNSS、ERA5水汽、大气污染物等观测要素,构建PM_(2.5)的浓度预测模型,预测研究未来24 h的PM_(2.5)的浓度.利用GNSS水汽校正区域ERA5水汽,并进行精度评定.利用FFT取大气污染物、第五代大气再分析产品(ECMWF atmospheric reanalysis 5,ERA5)水汽等观测要素的公共变化周期,获得最佳公共周期为78 h;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.通过均方根误差(root mean square error,RMSE)评价指标进行模型精度评价.研究结果表明:基于GNSS的ERA5水汽校正模型在秋冬季节ERA5水汽精度优于2 mm.FFT-LSTM模型预测精度在平原地区、山地地区和高原地区为10.22μg/m^(3)、8.56μg/m^(3)和9.02μg/m^(3),预测时效达到24 h.可有效预测未来24 h的PM_(2.5)浓度.该模型可为相关部门大气污染治理提供参考.

The prediction of air quality during the winter and spring seasons can be used for the public to make reasonable arrangements for travel and traffic management by relevant government departments.The main influencing factors of PM_(2.5)concentration include atmospheric pollutants,precipitable water vapor(PWV),etc.To improve the accuracy of PM_(2.5)concentration prediction,taking Beijing-Tianjin-Hebei region as an example,it was combined fast Fourier transform(FFT)and LSTM neural network methods,considered observation elements such as GNSS,ERA5 PWV,and atmospheric pollutants,and constructed the PM_(2.5)concentration prediction model to predict the concentration of PM_(2.5)in the next 24 hours.It was used GNSS PWV to correct the ERA5 PWV in the region and evaluated the accuracy.The public change period of air pollutants,ERA5 PWV and other observation elements are extracted by FFT,and the optimal public period is 78 hours;Select various factors with the best common cycle length as the model input,and the PM_(2.5)concentration of the 24 hour sequence as the model output.Evaluate model accuracy through RMSE evaluation indicators.The research results are indicated that the accuracy of ERA5 PWV correction model based on GNSS is better than 2 mm in autumn and winter seasons.The prediction accuracy of the FFT-LSTM model is 10.22μg/m^(3)in plain,8.56μg/m^(3)in mountainous,and 9.02μg/m^(3)in plateau regions,while the predicted time limit of 24 hours.It can effectively predict the PM_(2.5)concentration in the next 24 hours.This model can provide reference for relevant departments in air pollution control.