Forecasting Daily Ambient PM2.5 Concentrations in Qingdao City Using Deep Learning and Hybrid Interpretable Models and Analysis of Driving Factors Using SHAP
文献类型：期刊论文
| 作者 | He, Zhenfang1,2; Guo, Qingchun1,2,3; Zhang, Zuhan1; Feng, Genyue1; Qiao, Shuaisen1; Wang, Zhaosheng4 |
| 刊名 | TOXICS
 |
| 出版日期 | 2025-12-30 |
| 卷号 | 14期号:1页码:44 |
| 关键词 | deep learning ANN RNN CNN transformer BiLSTM SHAP PM2.5 |
| DOI | 10.3390/toxics14010044 |
| 产权排序 | 4 |
| 文献子类 | Article |
| 英文摘要 | With the acceleration of urbanization in China, air pollution is becoming increasingly serious, especially PM2.5 pollution, which poses a significant threat to public health. The study employed different deep learning models, including recurrent neural network (RNN), artificial neural network (ANN), convolutional Neural Network (CNN), bidirectional Long Short-Term Memory (BiLSTM), Transformer, and novel hybrid interpretable CNN-BiLSTM-Transformer architectures for forecasting daily PM2.5 concentrations on the integrated dataset. The dataset of meteorological factors and atmospheric pollutants in Qingdao City was used as input features for the model. Among the models tested, the hybrid CNN-BiLSTM-Transformer model achieved the highest prediction accuracy by extracting local features, capturing temporal dependencies in both directions, and enhancing global pattern and key information, with low root Mean Square Error (RMSE) (5.4236 mu g/m(3)), low mean absolute error (MAE) (4.0220 mu g/m(3)), low mean absolute percentage error (MAPE) (22.7791%) and high correlation coefficient (R) (0.9743) values. Shapley additive explanations (SHAP) analysis further revealed that PM10, CO, mean atmospheric temperature, O-3,O- and SO2 are the key influencing factors of PM2.5. This study provides a more comprehensive and multidimensional approach for predicting air pollution, and valuable insights for people's health and policy makers. |
| URL标识 | 查看原文 |
| WOS关键词 | POLLUTION |
| WOS研究方向 | Environmental Sciences & Ecology ; Toxicology |
| 语种 | 英语 |
| WOS记录号 | WOS:001672052100001 |
| 出版者 | MDPI |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/220934]  |
| 专题 | 生态系统网络观测与模拟院重点实验室_外文论文 |
| 通讯作者 | He, Zhenfang |
| 作者单位 | 1.Liaocheng Univ, Sch Geog & Environm, Liaocheng 252000, Peoples R China; 2.Liaocheng Univ, Inst Huanghe Studies, Liaocheng 252000, Peoples R China; 3.Chinese Acad Sci, Inst Earth Environm, State Key Lab Loess Sci, Xian 710061, Peoples R China; 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Natl Ecosyst Sci Data Ctr, Key Lab Ecosyst Network Observat & Modeling, Beijing 100101, Peoples R China |
| 推荐引用方式 GB/T 7714 | He, Zhenfang,Guo, Qingchun,Zhang, Zuhan,et al. Forecasting Daily Ambient PM2.5 Concentrations in Qingdao City Using Deep Learning and Hybrid Interpretable Models and Analysis of Driving Factors Using SHAP[J]. TOXICS,2025,14(1):44. |
| APA | He, Zhenfang,Guo, Qingchun,Zhang, Zuhan,Feng, Genyue,Qiao, Shuaisen,&Wang, Zhaosheng.(2025).Forecasting Daily Ambient PM2.5 Concentrations in Qingdao City Using Deep Learning and Hybrid Interpretable Models and Analysis of Driving Factors Using SHAP.TOXICS,14(1),44. |
| MLA | He, Zhenfang,et al."Forecasting Daily Ambient PM2.5 Concentrations in Qingdao City Using Deep Learning and Hybrid Interpretable Models and Analysis of Driving Factors Using SHAP".TOXICS 14.1(2025):44. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。