基于特征优化贝叶斯分类算法的中国城市碳强度分析

doi:10.7523/j.ucas.2023.090

摘要/Abstract

摘要： 基于改进型的贝叶斯分类算法，通过2005—2019年期间省级能源消费数据核算所得碳强度类型，结合社会经济等多重属性指标，将省级碳强度及其对应的优化属性特征作为样本，训练降尺度至所辖城市单元应用识别其碳强度类型，并与CEADs数据以及传统基于夜间灯光数据拟合得到的碳排放数据进行对比分析。结果显示本文提出的基于特征优化的贝叶斯分类方法具有一定优势。进一步采用该方法揭示中国282座主要城市2005—2019年间的碳强度演化特征，发现绝大部分城市的碳强度均呈现由高向低的转变态势，其中南北区域的城市在碳强度类型和改善状况方面长期存在显著差异，未来中西部资源型城市将是碳强度减排的重点关注地区。此外基于特征优化的贝叶斯分类法也具有良好的可扩展性，可望在区县小尺度的碳强度核算中应用。

关键词: 特征优化, 贝叶斯分类算法, 城市碳强度, 演化

Abstract: Cities serve as the primary hubs for human activities, and the successful realization of China’s “Dual Carbon” goals critically hinges on the effective reduction of carbon emissions in urban areas. However, due to the lack of detailed disaggregated data on energy consumption by source, urban carbon emission accounting has emerged as a crucial research area. This study, based on an enhanced Bayesian classification algorithm, leverages provincial-level energy consumption data from 2005 to 2019. It combines this data with various multi-dimensional attributes, including socioeconomic indicators, to determine carbon intensity types. The approach involves training on optimized attributes corresponding to provincial-level carbon intensity and then downscaling them to identify carbon intensity types at the city level. Comparative analysis with data from the carbon emission assessment database system (CEADs) and traditional methods highlights the advantages of the proposed feature-optimized Bayesian classification method. Furthermore, this method unveils the carbon intensity evolution of 282 major Chinese cities from 2005 to 2019, revealing a notable shift from high to low carbon intensity in the majority of cities. Notably, significant disparities persist in carbon intensity types and improvement trends between cities in the northern and southern regions. In the future, special attention should be paid to carbon intensity reduction efforts in resource-rich cities in central and western China. Additionally, the feature-optimized Bayesian classification method proposed in this study exhibits strong scalability, holding promise for applications at smaller scales, including county-level carbon intensity assessments.

Key words: feature optimization, Bayesian classification algorithm, urban carbon intensity, evolution

中图分类号:

K901

宋文明, 邹嘉龄, 唐志鹏. 基于特征优化贝叶斯分类算法的中国城市碳强度分析[J]. 中国科学院大学学报, 2025, 42(6): 747-757.

SONG Wenming, ZOU Jialing, TANG Zhipeng. Carbon intensity analysis of Chinese cities based on feature optimization Bayesian classification algorithm[J]. Journal of University of Chinese Academy of Sciences, 2025, 42(6): 747-757.

参考文献

[1] 刘竹, 耿涌, 薛冰, 等. 城市能源消费碳排放核算方法[J]. 资源科学, 2011, 33(7): 1325-1330.
[2] 顾朝林, 谭纵波, 刘宛, 等. 气候变化、碳排放与低碳城市规划研究进展[J]. 城市规划学刊, 2009(3): 38-45. DOI: 10.3969/j.issn.1000-3363.2009.03.005.
[3] Guan D B, Liu Z, Geng Y, et al. The gigatonne gap in China’s carbon dioxide inventories[J]. Nature Climate Change, 2012, 2(9): 672-675. DOI: 10.1038/nclimate1560.
[4] Liu Z, Guan D B, Wei W, et al. Reduced carbon emission estimates from fossil fuel combustion and cement production in China[J]. Nature, 2015, 524(7565): 335-338. DOI: 10.1038/nature14677.
[5] Gurney K R, Romero-Lankao P, Seto K C, et al. Climate change: track urban emissions on a human scale[J]. Nature, 2015, 525(7568): 179-181. DOI: 10.1038/525179a.
[6] Shan Y L, Guan D B, Liu J H, et al. Methodology and applications of city level CO₂ emission accounts in China[J]. Journal of Cleaner Production, 2017, 161: 1215-1225. DOI: 10.1016/j.jclepro.2017.06.075.
[7] Chen D K, Chen S Y, Jin H. Industrial agglomeration and CO₂ emissions: evidence from 187 Chinese prefecture-level cities over 2005-2013[J]. Journal of Cleaner Production, 2018, 172: 993-1003. DOI: 10.1016/j.jclepro.2017.10.068.
[8] Davis S J, Caldeira K. Consumption-based accounting of CO₂ emissions[J]. Proceedings of the National Academy of Sciences of the United States of America, 2010, 107(12): 5687-5692. DOI: 10.1073/pnas.0906974107.
[9] Cai B F, Liang S, Zhou J, et al. China high resolution emission database (CHRED) with point emission sources, gridded emission data, and supplementary socioeconomic data[J]. Resources, Conservation and Recycling, 2018, 129: 232-239. DOI: 10.1016/j.resconrec.2017.10.036.
[10] Wang H, Zhang R, Liu M, et al. The carbon emissions of Chinese cities[J]. Atmospheric Chemistry and Physics, 2012, 12(14): 6197-6206. DOI: 10.5194/acp-12-6197-2012.
[11] Byrne B, Baker D F, Basu S, et al. National CO₂ budgets (2015-2020) inferred from atmospheric CO₂ observations in support of the global stocktake[J]. Earth System Science Data, 2023, 15(2): 963-1004. DOI: 10.5194/essd-15-963-202.
[12] Shan Y L, Guan D B, Zheng H R, et al. China CO₂ emission accounts 1997-2015[J]. Scientific Data, 2018, 5: 170201. DOI: 10.1038/sdata.2017.201.
[13] Eggleston H S, Buendia L, Miwa K, et al. 2006 IPCC guidelines for national greenhouse gas inventories[R]. kanagawa, Japan: Institute of Global Environmental Strategies. 2006.
[14] Elvidge C, Ziskin D, Baugh K, et al. A fifteen year record of global natural gas flaring derived from satellite data[J]. Energies, 2009, 2(3): 595-622. DOI: 10.3390/en20300595.
[15] Su Y X, Chen X Z, Li Y, et al. China’s 19-year city-level carbon emissions of energy consumptions, driving forces and regionalized mitigation guidelines[J]. Renewable and Sustainable Energy Reviews, 2014, 35: 231-243. DOI: 10.1016/j.rser.2014.04.015.
[16] Wang S J, Liu X P. China’s city-level energy-related CO₂ emissions: spatiotemporal patterns and driving forces[J]. Applied Energy, 2017, 200: 204-214. DOI: 10.1016/j.apenergy.2017.05.085.
[17] Sun Y, Zheng S, Wu Y Z, et al. Spatiotemporal variations of city-level carbon emissions in China during 2000-2017 using nighttime light data[J]. Remote Sensing, 2020, 12(18): 2916. DOI: 10.3390/rs12182916.
[18] Chen J D, Gao M, Cheng S L, et al. China’s city-level carbon emissions during 1992-2017 based on the inter-calibration of nighttime light data[J]. Scientific Reports, 2021, 11: 3323. DOI: 10.1038/s41598-021-81754-y.
[19] 张晓平, 高珊珊, 陈明星, 等. 夜间灯光数据在城市化及其资源环境效应研究中的热点主题追踪[J]. 中国科学院大学学报, 2022, 39(4): 490-501. DOI: 10.7523/j.ucas.2021.0010.
[20] Liu X P, Ou J P, Wang S J, et al. Estimating spatiotemporal variations of city-level energy-related CO₂ emissions: an improved disaggregating model based on vegetation adjusted nighttime light data[J]. Journal of Cleaner Production, 2018, 177: 101-114. DOI: 10.1016/j.jclepro.2017.12.197.
[21] Wei W, Zhang X Y, Zhou L, et al. How does spatiotemporal variations and impact factors in CO₂ emissions differ across cities in China?:investigation on grid scale and geographic detection method[J]. Journal of Cleaner Production, 2021, 321: 128933. DOI: 10.1016/j.jclepro.2021.128933.
[22] Shi K F, Shen J W, Wu Y Z, et al. Carbon dioxide (CO₂) emissions from the service industry, traffic, and secondary industry as revealed by the remotely sensed nighttime light data[J]. International Journal of Digital Earth, 2021, 14(11): 1514-1527. DOI: 10.1080/17538947.2021.1946605.
[23] Meng X, Han J, Huang C. An improved vegetation adjusted nighttime light urban index and its application in quantifying spatiotemporal dynamics of carbon emissions in China[J]. Remote Sensing, 2017, 9(8): 829. DOI: 10.3390/rs9080829.
[24] Lin X W, Ma J J, Chen H, et al. Carbon emissions estimation and spatiotemporal analysis of China at city level based on multi-dimensional data and machine learning[J]. Remote Sensing, 2022, 14(13): 3014. DOI: 10.3390/rs14133014.
[25] 林伯强, 孙传旺. 如何在保障中国经济增长前提下完成碳减排目标[J]. 中国社会科学, 2011(1): 64-76, 221.
[26] 赵海霞, 李赟, 石洪波. 基于高维数据的加权朴素贝叶斯算法研究[J]. 统计与决策, 2020, 36(8): 5-9. DOI: 10.13546/j.cnki.tjyjc.2020.08.001.
[27] Székely G J, Rizzo M L, Bakirov N K. Measuring and testing dependence by correlation of distances[J]. The Annals of Statistics, 2007, 35(6): 2769-2794. DOI: 10.1214/009053607000000505.
[28] Reshef D N, Reshef Y A, Finucane H K, et al. Detecting novel associations in large data Sets[J]. Science, 2011, 334(6062): 1518-1524. DOI: 10.1126/science.1205438.
[29] 刘占成, 王安建, 于汶加, 等. 中国区域碳排放研究[J]. 地球学报, 2010, 31(5): 727-732.
[30] 温馨. “双碳”目标下的能源转型:多维阐释与中国策略[J]. 贵州社会科学, 2021(10): 145-151. DOI: 10.13713/j.cnki.cssci.2021.10.014.
[31] IPCC. Climate change:2007 the fourth assessment report of IPCC[M/OL]. Cambridge,UK:Cambridge University Press, 2007. (2007-05-30) [2023-03-11]. https://sciencepolicy.colorado.edu/admin/publication_files/resource-2523-Alvord_ipcc.pdf.
[32] 刘卫东, 唐志鹏, 夏炎, 等. 中国碳强度关键影响因子的机器学习识别及其演进[J]. 地理学报, 2019, 74(12): 2592-2603. DOI: 10.11821/dlxb201912012.
[33] Chen Z Q, Yu B L, Yang C S, et al. An extended time series (2000-2018) of global NPP-VIIRS-like nighttime light data from a cross-sensor calibration[J]. Earth System Science Data, 2021, 13(3): 889-906. DOI: 10.5194/essd-13-889-2021.
[34] 周彦楠, 杨宇, 程博, 等. 基于脱钩指数和LMDI的中国经济增长与碳排放耦合关系的区域差异[J]. 中国科学院大学学报, 2020, 37(3): 295-307. DOI: 10.7523/j.issn.2095-6134.2020.03.002.
[35] Shan Y L, Liu J H, Liu Z, et al. An emissions-socioeconomic inventory of Chinese cities[J]. Scientific Data, 2019, 6: 190027. DOI: 10.1038/sdata.2019.27.
[36] Shan Y L, Guan D B, Liu J H, et al. Methodology and applications of city level CO₂ emission accounts in China[J]. Journal of Cleaner Production, 2017, 161: 1215-1225. DOI: 10.1016/j.jclepro.2017.06.075.
[37] 于智涵, 方丹, 杨谨. 资源型经济转型试验区政策对碳排放的影响评估：以山西省为例[J]. 资源科学, 2021, 43(6): 1178-1192. DOI: 10.18402/resci.2021.06.10.