| 用GRU循环神经网络优化CMAQ预测结果 |
| Optimizing the Prediction Results of the CMAQ Model Using GRU Recurrent Neural Network |
| 投稿时间：2023-04-10 修订日期：2024-07-26 |
| DOI：10.19316/j.issn.1002-6002.2024.06.08 |
| 中文关键词: 环境空气 预测预报 多尺度空气质量模型(CMAQ) WRF-CMAQ-GRU模型 循环神经网络 |
| 英文关键词:ambient air forecast CMAQ model WRF-CMAQ-GRU model recurrent neural network |
| 基金项目: |
|
| 通讯作者:范敬勇* 河北省邢台生态环境监测中心, 河北 邢台 054000 |
| 摘要点击次数: 273 |
| 全文下载次数: 101 |
| 中文摘要: |
| 提高空气质量预报的准确度对于区域大气污染精准防控具有重要意义。针对邢台市空气质量预报情况,使用WRF气象模型输出数据和CMAQ空气质量模型输出数据结合GRU循环神经网络,建立了WRF-CMAQ-GRU模型,对2022年7月邢台市PM2.5、PM10、SO2、NO2、O3、CO等6种污染物的预测结果进行优化。实验发现:该模型对PM2.5及O3的优化效果最明显,PM2.5数据优化后的相关系数由0.28提高到0.85,O3数据优化后的相关系数由0.29提高到0.70。初步验证了GRU循环神经网络对WRF-CMAQ模型预报结果的显著优化作用,使空气质量预报准确度得到较大提升。 |
| 英文摘要: |
| Improving the accuracy of air quality forecast is of great significance for precise prevention and control of regional air pollution. In this study,aiming at the air quality forecast in Xingtai area,the WRF-CMAQ-GRU model was established using the WRF meteorological model output and the CMAQ air quality model output combined with GRU recurrent neural network. Correction experiment were conducted to optimize the prediction of six pollutant in Xingtai City in July 2022,including PM2.5, PM 10,SO2,NO2,O3,and CO. It was found that the optimization effect of the model on PM2.5 and O3 was the most obvious,and the overall correlation coefficient of PM2.5 increased from 0. 28 to 0. 85,the correlation coefficient of O3 increased from 0. 29 to 0. 70. It's preliminary verified that the GRU recurrent neural network can significantly optimize the prediction results of the WRF-CMAQ model,which greatly improves the accuracy of air quality prediction. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
