基于XGBoost-CMIP6耦合的哈尔滨市臭氧时空演变与未来情景预测
Spatiotemporal Evolution and Future Scenario Projections of Ozone in Harbin Based on XGBoost-CMIP6 Coupling
DOI: 10.12677/ojns.2026.145076, PDF,   
作者: 李思烨, 李善洁, 韦忞灏, 王忠良*：哈尔滨师范大学地理科学学院，黑龙江 哈尔滨；孟庆丰：哈尔滨理工大学计算机科学与技术学院，黑龙江 哈尔滨
关键词: 哈尔滨市；臭氧(O3)；时空变化；人口暴露风险；Harbin； O3； Spatiotemporal Variation； Population Exposure Risk
摘要: 为应对气候变化与人口老龄化背景下哈尔滨市臭氧(O3)污染的健康威胁，需科学预测未来多情景下的健康风险演变趋势。基于2018~2023年哈尔滨市监测数据与人口格网数据，耦合XGBoost机器学习算法与CMIP6气候模式。主要得出了以下结论：① 历史上，哈尔滨市臭氧浓度呈“西高东低”分布，主城区人口暴露强度高。② 模型验证显示XGBoost + CMIP6模拟性能良好(R2 = 0.81)。预测表明，在SSP5-8.5高排放情景下，2070年臭氧浓度将升至89 ± 4 µg∙m−3。③ 在SSP2-4.5中等排放情景下，风险增幅显著放缓。综上若不采取严格管控，未来气候变化将显著加剧哈尔滨市臭氧相关健康问题，亟须制定差异化的减排策略。
Abstract: To address the health threats posed by ozone (O3) pollution in Harbin under climate change and population aging, it is necessary to project future health risks under multiple scenarios. Based on air quality monitoring data and gridded population data for Harbin from 2018 to 2023, we coupled the XGBoost machine-learning algorithm with CMIP6 climate models. The main findings are as follows: (1) Historically, ozone concentrations in Harbin showed a west-high and east-low spatial pattern, with high population exposure intensity in the main urban area. (2) Model validation indicated that the coupled XGBoost-CMIP6 framework had good predictive performance (R2 = 0.81). Under the SSP5-8.5 high-emission scenario, ozone concentrations are projected to increase to 89 ± 4 μg/m3 by 2070. (3) Under the SSP2-4.5 moderate-emission scenario, the projected increase in risk slows markedly. Without stringent controls, future climate change will substantially exacerbate ozone-related health risks in Harbin, highlighting the urgent need for differentiated emission-reduction strategies.
文章引用：李思烨, 孟庆丰, 李善洁, 韦忞灏, 王忠良. 基于XGBoost-CMIP6耦合的哈尔滨市臭氧时空演变与未来情景预测[J]. 自然科学, 2026, 14(5): 723-734. https://doi.org/10.12677/ojns.2026.145076

参考文献

[1] 郑镇森, 窦建平, 张国涛, 等. 华北工业城市夏季大气臭氧生成机制及减排策略[J]. 环境科学, 2023, 44(4): 1821-1829.
[2] 董继元, 刘兴荣, 张本忠, 等. 我国臭氧短期暴露与人群死亡风险的Meta分析[J]. 环境科学学报, 2016, 36(4): 1477-1485.
[3] 杜楠, 陈磊, 廖宏, 等. 夏季对流层臭氧辐射强迫对华北地区天气和空气质量的影响[J]. 环境科学, 2023, 44(7): 3705-3714.
[4] 中共中央 国务院关于深入打好污染防治攻坚战的意见[EB/OL].
https://www.gov.cn/zhengce/2021-11/07/content_5649656.htm, 2024-06-30.
[5] 哈尔滨市人民政府关于印发哈尔滨市空气质量持续改善行动计划实施方案（2024—2025年）的通知[EB/OL].
https://www.harbin.gov.cn/haerbin/c104535/202407/c01_997632.shtml, 2024-06-30.
[6] Orellano, P., Reynoso, J., Quaranta, N., Bardach, A. and Ciapponi, A. (2020) Short-Term Exposure to Particulate Matter (PM10 and PM2.5), Nitrogen Dioxide (NO2), and Ozone (O3) and All-Cause and Cause-Specific Mortality: Systematic Review and Meta-Analysis. Environment International, 142, Article 105876.
https://doi.org/10.1016/j.envint.2020.105876
[7] Chen, R.J., Yin, P., Wang, L.J., et al. (2023) Short-Term Exposure to Ozone and Cause-Specific Mortality Risks and Thresholds in China: Evidence from Nationally Representative Data, 2013-2018. Environment International, 171, Article 107666.
https://doi.org/10.1016/j.envint.2022.107666
[8] 张欢, 梅煜臻, 吴瑛祖, 等. 中国近地表臭氧浓度的时空变化及其城市群分布特征——兼论“十三五”以来我国臭氧污染防治成效[J]. 长江流域资源与环境, 2023, 32(12): 2649-2660.
[9] Li, S., Zhang, H., Chen, Q., Chen, Y., An, Q., Wang, Z., et al. (2026) Historical and Future Changes of Surface Ozone over China from CMIP6 Models, Including an Assessment of Present-Day Uncertainties in Model Prediction. Atmospheric Chemistry and Physics, 26, 3669-3695.
https://doi.org/10.5194/acp-26-3669-2026
[10] Jiang, Y.Q., Sun, Y.S., Li, S.Y., Yin, D.J., et al. (2025) Grand Challenges of Mitigating O3-Related Mortality in China by 2060. Science Bulletin, 70, 1429-1431.
https://doi.org/10.1016/j.scib.2025.01.054
[11] Chen, T. and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, 13-17 August 2016, 785-794.
https://doi.org/10.1145/2939672.2939785
[12] Xu, C., Mao, Y. and Liao, H. (2024) Future Ozone Changes and Their Impacts on Vegetation and Human Health in China under the Shared Socio-Economic Pathways. Journal of Geophysical Research: Atmospheres, 129, e2023JD040086.
https://doi.org/10.1029/2023jd040086
[13] Li, B., Shi, X., Liu, Y., Lu, L., Wang, G., Thapa, S., et al. (2020) Long-Term Characteristics of Criteria Air Pollutants in Megacities of Harbin-Changchun Megalopolis, Northeast China: Spatiotemporal Variations, Source Analysis, and Meteorological Effects. Environmental Pollution, 267, Article 115441.
https://doi.org/10.1016/j.envpol.2020.115441
[14] 环境气象数据服务平台. 中国空气质量监测站点数据[DS/OL].
http://eia-data.com/pm25_download/, 2026-04-17.
[15] Xue, T., Zheng, Y., Geng, G., Xiao, Q., Meng, X., Wang, M., et al. (2020) Estimating Spatiotemporal Variation in Ambient Ozone Exposure during 2013-2017 Using a Data-Fusion Model. Environmental Science & Technology, 54, 14877-14888.
https://doi.org/10.1021/acs.est.0c03098
[16] Xiao, Q., Geng, G., Xue, T., Liu, S., Cai, C., He, K. and Zhang, Q. (2021) Tracking PM2.5 and O3 Pollution and the Related Health Burden in China 2013-2020. Environmental Science & Technology, 56, 6922-6932.
[17] Sims, K., Reith, A., Bright, E., Kaufman, J., Pyle, J., Epting, J., et al. (2023) LandScan Global 2022 [Data Set]. Oak Ridge National Laboratory.
[18] Dobson, J.E., Bright, E.A., Coleman, P.R., Durfee, R.C. and Worley, B.A. (2000) LandScan: A Global Population Database for Estimating Populations at Risk. Photogrammetric Engineering and Remote Sensing, 66, 849-857.
[19] 何雨璐, 王薇, 张小玲, 等. 2015-2022年四川盆地臭氧污染时空分布特征及其人口暴露水平评估[J]. 生态与农村环境学报, 2025, 41(4): 506-516.
[20] Yin, P., Chen, R., Wang, L., Meng, X., Liu, C., Niu, Y., et al. (2017) Ambient Ozone Pollution and Daily Mortality: A Nationwide Study in 272 Chinese Cities. Environmental Health Perspectives, 125, Article 117006.
https://doi.org/10.1289/ehp1849
[21] 国家卫生健康委员会. 中国卫生健康统计年鉴2023 [M]. 北京: 中国协和医科大学出版社, 2023.
[22] 哈尔滨市统计局. 哈尔滨统计年鉴2023 [M]. 北京: 中国统计出版社, 2023.
[23] 李莉莉, 王隆, 刘喜平, 等. 哈尔滨市臭氧时空分布特征及与气象要素的关系[J]. 环境科学, 2020, 40(5): 2034-2044.
[24] 赵璞, 姜盼, 周炎, 等. 工业园区和城区VOCs组成及化学活性的空间差异对清远大气臭氧污染分布的影响[J]. 中国环境监测, 2022, 38(6): 58-68.
[25] 李飞, 孔少杰, 屈志光, 等. 中国臭氧时空分异及热点城市群气象关联特征[J]. 中国环境科学, 2023, 43(4): 1539-1549.
[26] 黄小刚, 赵景波, 曹军骥, 等. 中国城市O₃浓度时空变化特征及驱动因素[J]. 环境科学, 2019, 40(3): 1120-1131.
[27] 辛艾萱. 中国城市地表臭氧的驱动因素与人口暴露风险分析[D]: [硕士学位论文]. 武汉: 武汉大学, 2022.
[28] 阚瑞, 梁琳, 陈学伟, 等. 气候变化情景下东北城市夏季臭氧浓度预测模型构建和优化[J]. 环境科学学报, 2026, 46(4): 1-14.
[29] Eyring, V., Bony, S., Meehl, G.A., Senior, C.A., Stevens, B., Stouffer, R.J., et al. (2016) Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) Experimental Design and Organization. Geoscientific Model Development, 9, 1937-1958.
https://doi.org/10.5194/gmd-9-1937-2016
[30] Griffiths, P.T., Murray, L.T., Zeng, G., Shin, Y.M., Abraham, N.L., Archibald, A.T., et al. (2021) Tropospheric Ozone in CMIP6 Simulations. Atmospheric Chemistry and Physics, 21, 4187-4218.
https://doi.org/10.5194/acp-21-4187-2021
[31] Zhang, Y.F., Ma, Y.X., Shen, J.H., Li, H.P., Wang, H., et al. (2022) Effect of Ambient O3 on Mortality Due to Circulatory and Respiratory Diseases in a High Latitude City of Northeast China. Environmental Science and Pollution Research, 29, 67776-67786.
https://doi.org/10.1007/s11356-022-20585-4