摘要
建立空气质量预报模型,预测污染物浓度对人类健康和社会经济发展具有重要意义。然而,传统的空气质量模型CMAQ对污染物浓度的预报精度并不理想。对此,本文提出了一种基于卷积神经网络(CNN)和长短期记忆神经网络(LSTM)的空气质量预报修正模型,并使用哈里斯鹰算法(HHO)对模型的超参数进行优化;用CMAQ模型对上海市2022年12月六种大气污染物(SO_(2)、NO_(2)、PM_(10)、PM2.5、O_(3)、CO)浓度的预报数据以及监测站的气象数据和污染物浓度实测数据作为HHO-CNN-LSTM模型的输入,对CMAQ模型预报结果进行修正。使用均方根误差(RMSE)、平均绝对误差(MAE)和一致性指数(IOA)作为评价指标。结果显示,修正模型显著提高了六项污染物浓度的预测精度,RMSE减少了73.11%~91.31%,MAE减少了67.19%~89.25%,IOA提升了35.34%~108.29%。同时针对HHO算法陷入局部最优而导致修正模型对CO浓度预测效果不佳的问题,使用高斯随机游走策略对HHO算法进行改进,显著提高了CO浓度的预测精度。相比于改进之前,RMSE减少了39.55%,MAE减少了45.93%,IOA提高了32.43%。
[JP2]With rising levels of air-pollution,air-quality forecasting has become integral to the dissemination of human health advisories and the preparation of mitigation strategies.Traditional air quality models,such as the Community Multi-scale Air Quality(CMAQ)model,have unsatisfactory accuracy.Accordingly,a correction model,which combines convolutional neural network(CNN)and long-short-term memory neural network(LSTM)and optimized by harris hawks optimization algorithm(HHO)was established to enhance the accuracy of CMAQ model's prediction results for six air pollutants(SO_(2),NO_(2),PM_(10),PM 2.5,O_(3) and CO).The accuracy of HHO-CNN-LSTM was evaluated using root mean square error(RMSE),mean absolute error(MAE),and the index of agreement(IOA).The results demonstrated a significant improvement in the accuracy of prediction for the six pollutants using the correction model.RMSE decreased by 73.11%to 91.31%,MAE decreased by 67.19%to 89.25%,and IOA increased by 35.34%to 108.29%.To address the propensity of the HHO algorithm to converge on local optima,leading to poor CO correction performance,this study proposed a method for the HHO algorithm with a Gaussian random walk strategy to improve the CO concentration correction performance.
作者
郑鑫楠
林开颜
王孜竞
宋远博
师洋
路函悦
张亚雷
沈峥
ZHENG Xinnan;LIN Kaiyan;WANG Zijing;SONG Yuanbo;SHI Yang;LU Hanyue;ZHANG Yalei;SHEN Zheng(College of Electronics and Information Engineering,Tongji University,Shanghai 201804,China;Institute of New Rural Development,Tongji University,Shanghai 201804,China;College of Environmental Science and Engineering,Tongji University,Shanghai 200092,China)
出处
《能源环境保护》
2023年第6期101-110,共10页
Energy Environmental Protection
基金
国家重点研发计划政府间国际合作资助项目(2022YFE0120600)
国家自然科学基金面上资助项目(21978224)。
关键词
空气质量预报
CMAQ模型
卷积神经网络
长短期记忆神经网络
哈里斯鹰优化算法
Air quality prediction
CMAQ
Convolutional neural network(CNN)
Long-short-term memory neural network(LSTM)
Harris hawks optimization algorithm(HHO)