基于遥感和机器学习的中国典型城市碳排放驱动因子及预测分析

doi:10.3969/j.issn.1673-503X.2024.01.0013

Abstract

Abstract:

Utilizing national statistical data and remote sensing nighttime light data, this study performs a contribution rate analysis of the influencing factors on carbon emissions in 15 typical cities through the Logarithmic Mean Divisia Index (LMDI), and constructs three sets of variables for predictive analysis using machine learning Ridge and Lasso regression models. The results indicate that seven factors including urban Gross Domestic Product (GDP), Energy Consumption (ES), Population (P), Real Estate Construction Area (RECA), Nighttime Light Intensity (NL), Cargo Transportation Volume (CT), and Passenger Transportation Volume (PT) play a promoting role in CO₂ emissions, whereas Energy Consumption Structure (EI) and the Proportion of Tertiary Industry (TIR) have an inhibiting effect on CO₂ emissions. The more mature a city, the richer the industry, the more diverse the impacting factors of carbon emissions. The correlation coefficient exceeds 0.8 between simulated results from predictive models of ridge and Lasso regression across variables set 1 to set 3 and the results from the test datasets. Among them, the result from set 1 is the best, followed by set 2, and finally, set 3.

Key words: Remote sensing, Machine learning, Carbon emissions, Influencing factors

CLC Number:

P236
F205

Yuheng WU,Jingchang BAI. Analysis and prediction of driving factors for carbon emissions in typical cities of China based on remote sensing data and machine learning method[J]. Journal of Meteorology and Environment, 2024, 40(1): 105-112.

Figures/Tables 8

Table 1

Fig.1

Table 2

Table 3

Fig.2

Fig.3

Fig.4

Table 4

References 30

1	Shan Y L , Guan D B , Hubacek K , et al. City-level climate change mitigation in China[J]. Science Advances, 2018, 4 (6): eaaq0390. doi: 10.1126/sciadv.aaq0390
2	赵俊刚, 董鑫, 尹名强, 等. 基于碳中和及气候适应性原则的被动式建筑应用潜力研究——以重庆市为例[J]. 气象与环境学报, 2022, 38 (5): 1- 14.
3	Hoekstra R , Jeroen C J. M . Comparing structural decomposition analysis and index[J]. Energy Economics, 2003, 25 (1): 39- 64. doi: 10.1016/S0140-9883(02)00059-2
4	Ang B W . Decomposition analysis for policymaking in energy: which is the preferred method?[J]. Energy Policy, 2004, 32 (9): 1131- 1139. doi: 10.1016/S0301-4215(03)00076-4
5	李小冬, 朱辰. 我国建筑碳排放核算及影响因素研究综述[J]. 安全与环境学报, 2020, 20 (1): 317- 327.
6	Ye B , Jiang J J , Li C S , et al. Quantification and driving force analysis of provincial-level carbon emissions in China[J]. Applied Energy, 2017, 198, 223- 238. doi: 10.1016/j.apenergy.2017.04.063
7	Akpan U , Bhattacharyya S C , Isihak S R , et al. Effect of technology change on CO₂ emissions in Japan's industrial sectors in the period 1995-2005:an input-o utput structural decomposition analysis[J]. Environmental and Resource Economics, 2015, 61 (2): 165- 189. doi: 10.1007/s10640-014-9787-7
8	Wang R , Zheng X , Wang H , et al. Emission drivers of cities at different industrialization phases in China[J]. Journal of Environmental Management, 2019, 250, 109494. doi: 10.1016/j.jenvman.2019.109494
9	郑颖, 逯非, 刘晶茹, 等. 我国典型城市化石能源消费CO₂排放及其影响因素比较研究[J]. 生态学报, 2020, 40 (10): 3315- 3327.
10	钟宇峰, 牛涛, 贾文贤, 等. 阅海湿地芦苇NPP遥感估算及其时空变化分析[J]. 气象与环境学报, 2021, 37 (6): 71- 78. doi: 10.3969/j.issn.1673-503X.2021.06.009
11	冯锐, 纪瑞鹏, 武晋雯, 等. 基于FY3/MERSI数据的辽宁省植被指数重建及时空变化分析[J]. 气象与环境学报, 2022, 38 (1): 65- 73.
12	李雨鸿, 陶苏林, 李荣平, 等. 辽宁省净初级生产力时空演变及其对地形因子的响应[J]. 气象与环境学报, 2021, 37 (5): 107- 112. doi: 10.3969/j.issn.1673-503X.2021.05.016
13	Li J F , Wang F F , Fu Y C , et al. A novel SUHI referenced estimation method for multicenters urban agglomeration using DMSP/OLS nighttime light data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13, 1416- 1425. doi: 10.1109/JSTARS.2020.2981285
14	York R , Rosa E A , Dietz T . IPAT and Impact: analytic tools for unpacking the driving forces of environmental impacts[J]. Ecological Economics, 2003, 46 (3): 351- 365. doi: 10.1016/S0921-8009(03)00188-5
15	唐赛, 付杰文, 武俊丽. 中国典型城市碳排放影响因素分析[J]. 统计与决策, 2021, 37 (23): 59- 63.
16	申笑颜. 中国碳排放影响因素的分析与预测[J]. 统计与决策, 2010, 26 (19): 90- 92.
17	赵爱文, 李东. 中国碳排放灰色预测[J]. 数学的实践与认识, 2012, 42 (4): 61- 69.
18	朱海龙, 李萍萍. 基于岭回归和LASSO回归的安徽省财政收入影响因素分析[J]. 江西理工大学学报, 2022, 43 (1): 59- 65.
19	Chen J , Gao M , Cheng S , 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 (1): 3323. doi: 10.1038/s41598-021-81754-y
20	谢守红, 王利霞, 邵珠龙. 国内外碳排放研究综述[J]. 干旱区地理, 2014, 37 (4): 720- 730.
21	Shan Y , Guan D , Liu J , 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
22	王艳军, 王孟杰, 柳林, 等. DMSP/OLS夜光数据的珠三角碳排放时空差异性分析[J]. 遥感学报, 2022, 26 (9): 1824- 1837.
23	Earth Observation Group (EOG). DMSP Nighttime Lights Time Series. Colorado School of Mines, Earth Observation Group. Version 4.0. (2002-2021).
24	Ang B W . The LMDI approach to decomposition analysis: a practical guide[J]. Energy Policy, 2005, 33 (7): 867- 871. doi: 10.1016/j.enpol.2003.10.010
25	贾俊平, 何晓群, 金勇进. 统计学(7版)[M]. 北京/西安: 世界图书出版公司, 2020.
26	郭玉杰, 张一瑾, 杨馥源, 等. 基于LMDI模型的能源系统碳排放影响因素分析[J]. 分布式能源, 2022, 7 (3): 30- 36.
27	佟昕, 陈凯, 李刚. 中国碳排放影响因素分析和趋势预测—基于STIRPAT和GM(1, 1)模型的实证研究[J]. 东北大学学报(自然科学版), 2015, 36 (2): 297- 300. doi: 10.3969/j.issn.1005-3026.2015.02.031
28	凤凰网. 各大银行房地产贷款占比大全[EB/OL]. 北京, 轻金融, 2019. (2019/08/02)[2022/10/02]. https://ishare.ifeng.com/c/s/7opZnd0zEvB.
29	新京报. "克强指数"折射了什么[EB/OL]. 北京, 卢锋, 2013. (2013/04/13)[2022/10/02]. http://epaper.bjnews.com.cn/html/2013-03/21/content_419032.html.
30	国家统计局. 中国统计年鉴[EB/OL]. 北京, 国家统计局, 2002-2021. http://www.stats.gov.cn/.

城市类型	城市名称	划分依据	数据来源
超大城市	北京、上海、广州	省会城市和直辖市中，年末户籍人口超过800万，且2016—2020年5 a内，年均第三产业GDP占全年GDP的70%以上。	国家统计局与部分城市能源统计年鉴
技术创新型	南京、杭州、成都、济南	省会城市中，2016—2020年5 a内，年均第三产业GDP占全年GDP的60%以上。
工业发展型	西安、沈阳、哈尔滨、武汉、重庆	省会城市和直辖市中，2016—2020年5 a内年均第二产业GDP占全年GDP的45%以上。
能源依赖型	太原、呼和浩特、乌鲁木齐	省会城市所在省级单位，位列全国资源型城市名单(2013年)数量大于8个，资源型城市是以本地区矿产、森林等自然资源开采、加工为主导产业的城市。

数据	数据定义	数据来源	起止年份
城市碳排放总量(CE)(10⁶ T/年)	城市碳排放指的是城市辖区内的所有直接排放、城市辖区外的与城市内部活动有关的间接排放之和。	中国碳核算数据库 https://www.ceads.net.cn/	2002—2017
城市生产总值(￥10⁹/年)	城市所有常住单位在一定时期内生产活动的最终成果，城市生产总值等于各产业增加值之和。	国家统计局 http://www.stats.gov.cn/sj/	2002—2017
能源消费量(ES)(10⁴T/年)	城市在报告期内实际消费的各种能源的数量。		2002—2017
城市人口(P)(10⁴人/年)	城市人口等于城市行政区划内的人口，包括所辖区和代管县的城市和农村人口。		2002—2017
第三产业占比(TIR)(无量纲，取值0~1)	第三产业占比是第三产业产值占地区生产总值的比重。		2002—2017
年旅客运输量(PT)(10⁴人/年)	旅客运输量是运输部门在一定时期内实际运送旅客的数量。		2002—2017
年货物运输量(CT)(10⁴ T/年)	货物运输量是按重量“吨”为单位计算的需要发送的货物数量。		2002—2017
房地产开发施工面积(RECA)(10⁴m²/年)	房地产开发施工面积是指报告期内施工的全部房屋(包括地下室、半地下室以及配套房屋)建筑面积。		2002—2017
能源消费结构(EI)(无量纲)	本研究中，能源消费结构是指天然气消费占总能源消费比重。		2002—2017
夜间灯光强度(NL)(NW/cm²/sr)	夜间灯光强度是指夜光遥感卫星获取地表发射的可见光-近红外电磁波，在单位投影面积、单位立体角上的辐射通量。	DMSP卫星OLS传感器数据 https://eogdata.mines.edu/products/dmsp/	2002—2013
		NPP卫星VIIRS传感器数据 https://eogdata.mines.edu/products/vnl/	2014—2017

组合	参数
组合1(s1)	城市生产总值，能源消费量(ES)，第三产业占比(TIR)，城市人口(P)，能源消费结构(EI)，房地产开发施工面积(RECA)，旅客运输量(PT)，货物运输量(CT)，夜间灯光强度(NL)。
组合2(s2)	城市生产总值，能源消费量(ES)，第三产业占比(TIR)，城市人口(P)，能源消费结构(EI)。
组合3(s3)	房地产开发施工面积(RECA)，旅客运输量(PT)，货物运输量(CT)，夜间灯光强度(NL)。

类型	RMSE	r²	best_lambda
Lasso_s1	16.64	0.88	0.0357
Lasso_s2	17.80	0.85	0.0001
Lasso_s3	21.14	0.81	0.0001
ridge_s1	16.80	0.88	0.0304
ridge_s2	17.77	0.86	0.0329
ridge_s3	20.67	0.81	0.0387

[1]	Xu-ting ZHANG, Hui LIU, Rui-fang LIU, Fei JU, Jia-hui-min LIU, Xing-xing GAO, Shao-ni HUANG, Nan WANG. Study on hourly PM_2.5 concentration forecast based on XGBoost method in Xi'an city [J]. Journal of Meteorology and Environment, 2023, 39(1): 44-54.
[2]	Jing-li WANG, Tian-jiao GAO, Rong-ping LI, Peng-cheng YU, Yun-tao MA, Na MI, Ri-hong WEN, Kai ZHANG. Research on soil moisture retrieval model based on optical remote sensing and microwave remote sensing [J]. Journal of Meteorology and Environment, 2023, 39(1): 73-82.
[3]	Yu-qin HE,Hong XU,Jin-xin CHENG,Li-zhang FAN. Variation of ecosystem quality and its response to climatic factors in Erhai Basin [J]. Journal of Meteorology and Environment, 2023, 39(1): 100-106.
[4]	Tao WANG, Yi-shu WANG, Chun-yu ZHAO, Xiao-tao WANG, Mei-ou QIN, Yu-min SHEN, Yi-ling HOU, Jian-yun ZHAO. Prediction model of first-frost date in Liaoning province using machine learning methods [J]. Journal of Meteorology and Environment, 2022, 38(4): 47-56.
[5]	Yu-feng ZHONG, Tao NIU, Wen-xian JIA, Yun-lei CUI, Hong-li LIU, Bo-wen DENG, Yang CUI, Men-xin WU. Remote sensing estimation of reed NPP in Yuehai Wetland and characteristic analysis of its temporal and spatial changes [J]. Journal of Meteorology and Environment, 2021, 37(6): 71-78.
[6]	Yuan-mou WANG,Jia-qi LI,Shi-ji CHEN,Jia-ping TANG,Bai-cheng XIA,Shi-gang HAN. Identification of the fog image features on the Yangtze River waterways in Chongqing based on machine learning [J]. Journal of Meteorology and Environment, 2021, 37(1): 106-112.
[7]	Xing-xing GAO, Hai-lin GUI, Liu-jie PAN, Nan WANG, Jian-peng WANG. Statistical analysis of air pollution in Fenwei Plain based on satellite remote sensing and ground observation data [J]. Journal of Meteorology and Environment, 2020, 36(4): 36-44.
[8]	WU Gang-zhe;YAN Jin-zhe; REN Guo-yu; SUONAN Kan-zhuo. Relationship between fractional vegetation and climate factors in spring over the mid-west of DPR Korea [J]. Journal of Meteorology and Environment, 2018, 34(4): 112-118.
[9]	LIANG Dong-po, SUN Zhi-gui, GUO Jun, GUO Yu-di, WANG Jing, XU Jun-de. Study on meteorological disaster risk division in Jinnan District of Tianjin based on RS and GIS [J]. Journal of Meteorology and Environment, 2016, 32(6): 116-121.
[10]	WANG Ying, LI Guo-chun, GAO Yang-hua, DU Qin, ZHAO Zi-qi. Polarization-difference parameterization in estimating liquid water path based on AMSR-E data [J]. Journal of Meteorology and Environment, 2016, 32(2): 59-65.
[11]	WEN Ri-hong， WANG Xiao-ying， LV Guo-hong，XIE Yan-bing， JIANG Peng， LI Si-wen， LIU Xiao-mei. Remote sensing analysis of ecological recovery in the Liaohe river protection zone [J]. Journal of Meteorology and Environment, 2013, 29(6): 110-115.
[12]	YANG Yun-ling，WANG Cong-mei. Characteristics of acid rain and its influencing factors from 2006 to 2010 in Nangong, Hebei province [J]. Journal of Meteorology and Environment, 2012, 28(4): 79-83.
[13]	ZHAO Dong-Yan. Characteristics of variations of pan evaporation and its influencing factors in Dalian, Liaoning province [J]. Journal of Meteorology and Environment, 2011, 27(4): 34-38.
[14]	YU Wen-Ying, FENG Rui, JI Rui-Peng, ZHANG Yu-Shu, CHEN Peng-Shi, ZHAO Xian-Li, WU Jin-Wen. Advances in rice planting area extraction technology based on MODIS data [J]. Journal of Meteorology and Environment, 2011, 27(2): 56-61.
[15]	LI De-ping;CHENG Xing-hong;YU Yong-tao;CAO Hai-wei;LI Dong;XU Shi-qing. Effects of meteorological factors on air quality above the third grade pollution in Beijing [J]. Journal of Meteorology and Environment, 2010, 26(3): 7-13.

Analysis and prediction of driving factors for carbon emissions in typical cities of China based on remote sensing data and machine learning method

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 30

Related Articles 15

Metrics

Comments

Recommended 10