PM2.5 concentration prediction using a whale optimization algorithm based hybrid deep learning model in Beijing, China

被引:0
作者
Wei, Qing [1 ,2 ]
Zhang, Huijin [1 ,2 ]
Yang, Ju [3 ]
Niu, Bin [4 ]
Xu, Zuxin [1 ,2 ]
机构
[1] Tongji Univ, Coll Environm Sci & Engn, Shanghai 200092, Peoples R China
[2] Tongji Univ, Key Lab Urban Water Supply, State Key Lab Pollut Control & Resource Reuse,Mini, Water Saving & Water Environm Governance Yangtze R, Shanghai 200092, Peoples R China
[3] Guangdong Inst Water Resources & Hydropower Res, Guangzhou 510000, Peoples R China
[4] PowerChina East China Survey Design & Res Inst Co, Hangzhou 310000, Peoples R China
基金
中国国家自然科学基金;
关键词
PM; 2.5; prediction; Whale optimization algorithm; Convolutional neural network; Long short-term memory; Shapley additive explanation; POLLUTION; IMPACT;
D O I
10.1016/j.envpol.2025.125953
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
PM2.5 is a significant global atmospheric pollutant impacting visibility, climate, and public health. Accurate prediction of PM2.5 concentrations is critical for assessing air pollution risks and providing early warnings for effective management. This study proposes a novel hybrid machine learning model that combines the whale optimization algorithm (WOA) with a convolutional neural network (CNN), long short-term memory (LSTM), and an attention mechanism (AM) to predict daily PM2.5 concentrations. Tested with meteorological and air pollution daily data from 2014 to 2018, the WOA-CNN-LSTM-AM model demonstrates substantial improvements. It achieves MAE, RMSE, MBE, and R2 values of 14.29, 21.96, -0.23, and 0.93, respectively, showing a reduction in prediction errors by 39% compared to CNN and 34% compared to LSTM models. In the medium-term forecast, the accuracy of the hybrid model is 30%-54% over WOA-CNN-LSTM and 26%-39% over CNN-LSTM-AM. The R2 value decreases by 2.5% from the 1-day to 5-day forecast, maintaining high accuracy. SHAP analysis reveals that NO2 and CO are the primary drivers for PM2.5 predictions. This study provides a reliable tool for short and medium-term PM2.5 prediction and air pollution control.
引用
收藏
页数:11
相关论文
共 36 条
[1]   Severe haze in northern China: A synergy of anthropogenic emissions and atmospheric processes [J].
An, Zhisheng ;
Huang, Ru-Jin ;
Zhang, Renyi ;
Tie, Xuexi ;
Li, Guohui ;
Cao, Junji ;
Zhou, Weijian ;
Shi, Zhengguo ;
Han, Yongming ;
Gu, Zhaolin ;
Ji, Yuemeng .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2019, 116 (18) :8657-8666
[2]   Recursive neural network model for analysis and forecast of PM10 and PM2.5 [J].
Biancofiore, Fabio ;
Busilacchio, Marcella ;
Verdecchia, Marco ;
Tomassetti, Barbara ;
Aruffo, Eleonora ;
Bianco, Sebastiano ;
Di Tommaso, Sinibaldo ;
Colangeli, Carlo ;
Rosatelli, Gianluigi ;
Di Carlo, Piero .
ATMOSPHERIC POLLUTION RESEARCH, 2017, 8 (04) :652-659
[3]   Algorithms to estimate Shapley value feature attributions [J].
Chen, Hugh ;
Covert, Ian C. ;
Lundberg, Scott M. ;
Lee, Su-In .
NATURE MACHINE INTELLIGENCE, 2023, 5 (06) :590-601
[4]   Identifying the socioeconomic determinants of population exposure to particulate matter (PM2.5) in China using geographically weighted regression modeling [J].
Chen, Jing ;
Zhou, Chunshan ;
Wang, Shaojian ;
Hu, Jincan .
ENVIRONMENTAL POLLUTION, 2018, 241 :494-503
[5]   Using the geographical detector technique to explore the impact of socioeconomic factors on PM2.5 concentrations in China [J].
Ding, Yueting ;
Zhang, Ming ;
Qian, Xiangyan ;
Li, Chengren ;
Chen, Sai ;
Wang, Wenwen .
JOURNAL OF CLEANER PRODUCTION, 2019, 211 :1480-1490
[6]   Analysis of Atmospheric Pollutants and Meteorological Factors on PM2.5 Concentration and Temporal Variations in Harbin [J].
Gao, Xiuyan ;
Ruan, Zhaohui ;
Liu, Jiemei ;
Chen, Qixiang ;
Yuan, Yuan .
ATMOSPHERE, 2022, 13 (09)
[7]   A review of the CAMx, CMAQ, WRF-Chem and NAQPMS models: Application, evaluation and uncertainty factors [J].
Gao, Zhaoqi ;
Zhou, Xuehua .
ENVIRONMENTAL POLLUTION, 2024, 343
[8]   Drivers of PM2.5 air pollution deaths in China 2002-2017 [J].
Geng, Guannan ;
Zheng, Yixuan ;
Zhang, Qiang ;
Xue, Tao ;
Zhao, Hongyan ;
Tong, Dan ;
Zheng, Bo ;
Li, Meng ;
Liu, Fei ;
Hong, Chaopeng ;
He, Kebin ;
Davis, Steven J. .
NATURE GEOSCIENCE, 2021, 14 (09) :645-+
[9]   A comprehensive survey: Whale Optimization Algorithm and its applications [J].
Gharehchopogh, Farhad Soleimanian ;
Gholizadeh, Hojjat .
SWARM AND EVOLUTIONARY COMPUTATION, 2019, 48 :1-24
[10]   How harmful is air pollution to economic development? New evidence from PM2.5 concentrations of Chinese cities [J].
Hao, Yu ;
Peng, Hui ;
Temulun, T. ;
Liu, Li-Qun ;
Mao, Jie ;
Lu, Zhi-Nan ;
Chen, Hao .
JOURNAL OF CLEANER PRODUCTION, 2018, 172 :743-757