Spatiotemporal change of PM2.5 concentration in Beijing-Tianjin-Hebei and its prediction based on machine learning
文献类型：期刊论文
| 作者 | Liu, Nanjian1,3; Hao, Zhixin1,3; Zhao, Peng1,2 |
| 刊名 | URBAN CLIMATE
 |
| 出版日期 | 2024-11-01 |
| 卷号 | 58页码:102167 |
| 关键词 | Machine learning SHAP Driving factors Topographical regulation |
| DOI | 10.1016/j.uclim.2024.102167 |
| 产权排序 | 1 |
| 英文摘要 | For decades, PM2.5 (a type of fine particulate matter) in large urban areas has had a profound negative impact on human health. In this study, spatiotemporal analysis and four machine learning methods (XGBoost, ANN, CNN and MLR) were used to assess the changes and drivers of PM2.5 concentrations in the Beijing-Tianjin-Hebei (BTH) from 2016 to 2019 based on 68 stations. The results indicated a significant decrease in PM2.5 concentrations in BTH region (average decrease of 7.69 mu g/m3/yr), especially in the southwest region where pollution is the most serious, and the overall annual average still exceeded the national standard. In spatiotemporal modeling, XGBoost effectively captured the spatial characteristics of PM2.5 pollution and achieved the most robust prediction in general (RMSE = 22.11 mu g/m3, MAE = 15.18 mu g/m3, R2 = 0.64). The SHapley Additive exPlanations (SHAP)-based global and local driving analyses revealed that CO had the greatest relative impact on PM2.5 (52.46 %), while NO2 and SO2 were also important driving factors, with variable importance values of 10.68 % and 6.01 %, respectively. Moreover, temperature and surface humidity are key meteorological drivers of the formation and development of PM2.5 pollution. It is also worth noting that topography is an important geographic background for the formation of haze in the BTH region, which may induces air pollution under unfavorable meteorological conditions and hindering the improvement of air quality under favorable meteorological conditions. The results of this study deepen our understanding of air pollution and its driving factors in important urban agglomerations in China. |
| WOS关键词 | AIR-POLLUTION ; REGION ; CHINA |
| WOS研究方向 | Environmental Sciences & Ecology ; Meteorology & Atmospheric Sciences |
| WOS记录号 | WOS:001336684400001 |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/208197]  |
| 专题 | 陆地表层格局与模拟院重点实验室_外文论文 |
| 通讯作者 | Hao, Zhixin |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Mt Hazards & Environm, State Key Lab Mt Hazards & Engn Safety, Chengdu 610299, Peoples R China 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Nanjian,Hao, Zhixin,Zhao, Peng. Spatiotemporal change of PM2.5 concentration in Beijing-Tianjin-Hebei and its prediction based on machine learning[J]. URBAN CLIMATE,2024,58:102167. |
| APA | Liu, Nanjian,Hao, Zhixin,&Zhao, Peng.(2024).Spatiotemporal change of PM2.5 concentration in Beijing-Tianjin-Hebei and its prediction based on machine learning.URBAN CLIMATE,58,102167. |
| MLA | Liu, Nanjian,et al."Spatiotemporal change of PM2.5 concentration in Beijing-Tianjin-Hebei and its prediction based on machine learning".URBAN CLIMATE 58(2024):102167. |
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。