Research on prediction of municipal solid waste generation based on grey system
-
摘要:
探究“无废城市”建设下城市生活垃圾产生量影响因素有助于指导城市制定有效的治理方案。基于灰色系统,以11个国内“无废城市”建设试点城市为对象,采用灰色关联分析法研究城市生活垃圾产生量的相关影响因素,并通过灰色预测模型预测城市未来9年的生活垃圾产生量。结果表明:1)城市的经济发展水平对生活垃圾产生量的影响最大,其相关影响因素的影响程度表现为地区生产总值>社会消费品零售总额>第三产业占比>人均GDP。2)GM(1,1)模型预测10个试点城市生活垃圾产生量的结果表明,2023—2030年重庆市和深圳市的生活垃圾产生量年增长率基本保持不变,威海市、盘锦市、三亚市等8个城市的生活垃圾产生量年增长率逐年降低,以铜陵市的降低幅度最大,绍兴市最小。3)加入5个相关影响因素的GM(1,N)模型预测6个试点城市生活垃圾产生量表明,2023—2030年盘锦市和重庆市的生活垃圾产生量年增长率呈下降趋势,深圳市、许昌市、三亚市、徐州市的年增长率逐年上升,增长幅度最大的是深圳市,最小的是徐州市。研究结果可为“无废城市”建设背景下城市的固废管理提供有效策略支撑。
Abstract:Exploring the influencing factors of municipal solid waste (MSW) generation under the construction of "Zero-waste City" will help guide cities to formulate effective governance plans. Based on the grey system and taking 11 pilot cities for the construction of "Zero-waste City" in China as the object, the grey correlation analysis method was used to study the relevant influencing factors of MSW generation, and the amount of MSW generated in the next 9 years was predicted through the grey prediction model. The results show that the economic development level of cities has the greatest impact on the amount of MSW, and the influence degree of related influencing factors is in the order of regional GDP > total retail sales of consumer goods > proportion of tertiary industry > per capita GDP. The results of the GM(1,1) model predicting the MSW generation in 10 pilot cities show that the annual growth rate of MSW generation in Chongqing City and Shenzhen City will remain relatively stable from 2023 to 2030, and the annual growth rate of MSW generation in 8 cities, including Weihai City, Panjin City and Sanya City, will decrease year by year, with Tongling City having the largest decrease and Shaoxing City having the smallest decrease. The GM(1,N) model with five relevant influencing factors was used to predict the MSW generation of six pilot cities. The results show that the annual growth rate of MSW generation in Panjin City and Chongqing City from 2023 to 2030 will have a decreasing trend, while the annual growth rate of Shenzhen City, Xuchang City, Sanya City, and Xuzhou City will increase year by year, with the largest increase in Shenzhen City and the smallest in Xuzhou City. The research results could provide effective strategic support for urban solid waste management in the context of "Zero-waste City" construction.
-
表 1 预测精度等级划分[26]
Table 1. Prediction accuracy classification table
C P 预测精度等级 q 预测精度等级 <0.35 >0.95 好 0~≤0.01 一级 <0.5 >0.8 合格 0.01~≤0.05 二级 <0.65 >0.7 勉强合格 0.05~≤0.10 三级 ≥0.65 ≤0.7 不合格 0.10~≤0.20 四级 表 2 国内生活垃圾产生量相关影响因素研究
Table 2. Research on the relevant influencing factors of MSW generationn
区域范围 研究工具 相关影响因素 全国[34] 多元线性回归模型 人均消费总支出>年底常住人口>社会消费品零售总额>人均可支配收入>地区生产总值 全国[35] 斯皮尔曼相关性分析 第三产业占比、建成区面积、人口密度 全国[36] 灰色多元线性回归模型 建成区面积、市政道路清扫面积、城市供暖区、地区生产总值、人均消费总支出、
人均可支配收入、年底常住人口258个地级市[37] 最小二乘模型+地理加权
回归模型人均GDP、年底常住人口、城市化率、第三产业占比 31个省(区、市)[38] 斯皮尔曼相关性分析 地区生产总值、城市化率、人均可支配收入、生活垃圾处理厂数量、
政府环境财政支出、技术市场成交额10个城市[39] 灰色关联分析 人均GDP>社会消费品零售总额>人均可支配收入>人均地方一般
公共预算收入>居民消费价格指数3个典型城市[40] 岭回归分析 年底常住人口、城市化率、人均可支配收入、人均消费总支出、第三产业占比 深圳市[41] 灰色关联分析 食品消费>人均可支配收入>年底常住人口>衣着消费>建成区面积 上海市[42] 灰色关联分析 城市基础设施投资额>年底常住人口>地区生产总值>人均可支配收入>社会消费品零售总额 重庆市[5] 灰色关联分析 人均可支配收入>人均消费总支出>城市化率>教育程度>市政道路清扫面积 青岛市[43] 文献调研 地区生产总值、第三产业占比、人均消费总支出、年底常住人口、旅游人数 西宁市[44] 文献调研和多元线性回归模型 年底常住人口、地区生产总值、人均消费总支出、市政道路清扫面积 乌鲁木齐市[45] 灰色关联分析 人均可支配收入、地区生产总值、年底常住人口、旅游收入、人口密度 东南部城市某县级市[6] 灰色关联分析 生活用水消耗量>农村总生产总值>年底常住人口>城市建设面积>乡村人口 表 3 样本城市生活垃圾GM(1,1)预测值的误差分析
Table 3. Error analysis of the predicted values of GM(1,1) of MSW in the pilot cities
城市 C P q 数值 等级 数值 等级 数值/% 等级 深圳 0.06 好 1 好 2.99 二级 包头 0.12 好 0.89 合格 2.97 二级 铜陵 0.08 好 1 好 10.89 四级 威海 0.07 好 1 好 4.92 二级 重庆 0.01 好 1 好 1.81 二级 绍兴 0.19 好 0.78 合格 4.73 二级 三亚 0.03 好 1 好 5.56 三级 许昌 0.31 好 0.78 勉强合格 9.22 三级 徐州 0.07 好 1 好 4.46 二级 盘锦 0.28 好 0.78 勉强合格 16.05 四级 西宁 0.64 勉强合格 0.44 不合格 13.36 四级 表 4 样本城市生活垃圾GM(1,N)预测值的误差分析
Table 4. Error analysis of the predicted values of GM(1,N) of MSW in the pilot cities
城市 C P q 数值 等级 数值 等级 数值/% 等级 深圳 0.096 好 1 好 1.08 二级 包头 0.530 勉强合格 0.67 不合格 6.00 三级 铜陵 0.110 好 1 好 4.35 二级 威海 0.230 好 1 好 3.97 二级 重庆 0.022 好 1 好 0.32 一级 三亚 0.086 好 1 好 0.91 一级 许昌 0.018 好 1 好 0.55 一级 徐州 0.038 好 1 好 0.79 一级 盘锦 0.050 好 1 勉强合格 0.99 二级 绍兴 0.053 好 1 好 1.56 一级 西宁 0.640 不合格 勉强合格 13.36 0.44 四级 -
[1] 国家统计局. 2022年中国统计年鉴[M]. 北京: 中国统计出版社, 2023. [2] RAMACHANDRA T V, BHARATH H A, KULKARNI G, et al. Municipal solid waste: generation, composition and GHG emissions in Bangalore, India[J]. Renewable and Sustainable Energy Reviews,2018,82:1122-1136. doi: 10.1016/j.rser.2017.09.085 [3] 国务院办公厅. 关于印发“无废城市”建设试点工作方案的通知[A/OL]. [2023-12-07]. http://www.gov.cn/zhengce/content/2019-01/21/content_5359620.htm. [4] 皇甫慧慧, 李红艳. 城市生活垃圾产生量的影响因素分析[J]. 科技与管理,2018,20(4):44-49.HUANGFU H H, LI H Y. Analysis of the factors affecting the production of municipal solid waste[J]. Science-Technology and Management,2018,20(4):44-49. [5] 闫芳, 舒垚, 李宗敏. 基于GA-BP神经网络的重庆市生活垃圾量预测模型研究[J]. 武汉理工大学学报(信息与管理工程版),2022,44(2):252-257.YAN F, SHU Y, LI Z M. Research on forecasting model of household garbage amount in Chongqing based on GA-BP neural network[J]. Journal of Wuhan University of Technology (Information & Management Engineering),2022,44(2):252-257. [6] 赵天瑞, 刘一鸣, 吕鹏召, 等. 无废城市建设场景下LightGBM垃圾产量预测模型构建[J]. 环境工程,2023,41(3):210-215.ZHAO T R, LIU Y M, LÜ P Z, et al. Construction of lightgbm waste production predict model in a scenario of zero-waste city[J]. Environmental Engineering,2023,41(3):210-215. [7] 高晨琦, 孙英杰, 卞荣星, 等. 碳达峰碳中和视角下中国“无废城市” 建设问题及对策[J]. 环境污染与防治,2023,45(9):1312-1315.GAO C Q, SUN Y J, BIAN R X, et al. The problem and countermeasure for "zero-waste city" construction from the perspective of carbon peak and carbon neutralization[J]. Environmental Pollution & Control,2023,45(9):1312-1315. [8] MA W T, de JONG M, ZISOPOULOS F, et al. Introducing a classification framework to urban waste policy: analysis of sixteen zero-waste city in China[J]. Waste Management,2023,165:94-107. doi: 10.1016/j.wasman.2023.04.012 [9] FANG W, DING Y M, GENG J H, et al. High potential of coupling the source-separation and incineration promotion to reduce costs based on city-level cost-benefit analysis of municipal solid waste management strategies in China[J]. Resources, Conservation and Recycling,2023,197:107099. doi: 10.1016/j.resconrec.2023.107099 [10] ZHAO T R, GAO Y D, ZHAN W, et al. Municipal solid waste (MSW) under the population shrinking and aging: spatio-temporal patterns, driving forces, and the impact of smart city development[J]. Journal of Cleaner Production,2024,434:140124. doi: 10.1016/j.jclepro.2023.140124 [11] 张万里, 郑永浩, 邢万丽, 等. 基于ARIMA模型的环渤海典型城市生活垃圾产量预测研究[J]. 环境工程技术学报,2022,12(3):861-868. doi: 10.12153/j.issn.1674-991X.20210496ZHANG W L, ZHENG Y H, XING W L, et al. Prediction of municipal solid waste production of typical cities around Bohai Region based on ARIMA model[J]. Journal of Environmental Engineering Technology,2022,12(3):861-868. doi: 10.12153/j.issn.1674-991X.20210496 [12] 姜丽兰. 江苏省城市生活垃圾产生量的影响因素分析[J]. 环境卫生工程,2017,25(1):48-50. doi: 10.3969/j.issn.1005-8206.2017.01.013JIANG L L. Influencing factors on municipal solid waste production in Jiangsu Province[J]. Environmental Sanitation Engineering,2017,25(1):48-50. doi: 10.3969/j.issn.1005-8206.2017.01.013 [13] LI J, MA L, LUO W, et al. Forecast of plastic waste production in China's coastal cities: a case of Shanghai[C]//Proceedings of the 9th Academic Conference of Geology Resource Management and Sustainable Development. Beijing: Aussino Academic Publishing House, 2022. [14] 王磊, 李振山, 焦安英, 等. 北京市生活垃圾堆肥设施耗能、排污及影响因素[J]. 环境科学研究,2013,26(11):1212-1218.WANG L, LI Z S, JIAO A Y, et al. Characteristics and influencing factors of energy consumption and pollution discharge of the household refuse composting facilities in Beijing City[J]. Research of Environmental Sciences,2013,26(11):1212-1218. [15] 王耕, 李优. 基于SD模型的城市生活垃圾资源化处理模拟研究: 以大连市为例[J]. 环境工程技术学报,2016,6(5):493-500. doi: 10.3969/j.issn.1674-991X.2016.05.072WANG G, LI Y. Simulation of municipal solid waste resource recovery based on system dynamics model: the case of Dalian[J]. Journal of Environmental Engineering Technology,2016,6(5):493-500. doi: 10.3969/j.issn.1674-991X.2016.05.072 [16] LI H, ZHENG Y, LAI K, et al. Forecasting municipal solid waste generation using a hybrid method of support vector regression and grey wolf optimizer[J]. Journal of Cleaner Production,2018,189:492-502. [17] DUAN H S, MENG X, TANG J, et al. Prediction of NO x concentration using modular long short-term memory neural network for municipal solid waste incineration[J]. Chinese Journal of Chemical Engineering,2023,56:46-57. doi: 10.1016/j.cjche.2022.06.028 [18] WEI Y W, XUE Y L, YIN J Y, et al. Prediction of municipal solid waste generation in China by multiple linear regression method[J]. International Journal of Computers and Applications, 2013: 35(3): 136-140 [19] 唐万梅. 几个预测方法及模型的研究[D]. 呼和浩特: 内蒙古大学, 2006. [20] 陈严. 城市生活垃圾管理系统动力学模型研究[D]. 杭州电子科技大学, 2012. [21] 刘力铭. 重庆市城市生活垃圾产量的影响因素分析及预测研究[D]. 重庆: 重庆大学, 2021. [22] GU R J, LI W. Temperature prediction using gray model based on data open platform[C]//2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE). Dalian: IEEE, 2021: 172-175. [23] 吴永强, 李明凯, 唐中楠, 等. 基于灰色动态模型群的衡水市居民年用水量预测[J]. 环境工程技术学报,2022,12(1):267-274.WU Y Q, LI M K, TANG Z N, et al. Projection of residential annual water consumption in Hengshui City based on dynamic gray model groups[J]. Journal of Environmental Engineering Technology,2022,12(1):267-274. [24] LIU Q, XIAO J T, SHI Z Y, et al. Talent and urban development based on gray prediction model[C]//YANG C T, PEI Y, CHANG J W. Innovative computing. Singapore: Springer, 2020: 1117-1126. [25] 李懿洋. 甘肃省产业结构与经济增长的灰色关联分析[J]. 企业经济,2011,30(5):20-23. [26] 李秀央, 李振洪, 蔡雪霞. 用EXCEL实现灰色数列模型GM(1, 1)的预测[J]. 数理医药学杂志,2000,13(4):296-297. doi: 10.3969/j.issn.1004-4337.2000.04.005LI X Y, LI Z H, CAI X X. Realizing grey dynamics model GM(1, 1) forecasting by EXCEL[J]. Journal of Mathematical Medicine,2000,13(4):296-297. doi: 10.3969/j.issn.1004-4337.2000.04.005 [27] 谢乃明, 刘思峰. 离散GM(1, 1)模型与灰色预测模型建模机理[J]. 系统工程理论与实践,2005,25(1):93-99.XIE N M, LIU S F. Discrete GM(1, 1) and mechanism of grey forecasting model[J]. Systems Engineering-theory & Practice,2005,25(1):93-99. [28] 国家统计局. 中国统计年鉴[M]. 北京: 中国统计出版社, 2021. [29] 河南省统计局, 国家统计局河南调查总队. 河南统计年鉴[M]. 北京: 中国统计出版社, 2021. [30] 徐州市统计局, 国家统计局徐州调查总队. 徐州统计年鉴[M]. 北京: 中国统计出版社, 2021. [31] 盘锦市统计局, 国家统计局盘锦调查总队. 盘锦统计年鉴[M]. 北京: 中国统计出版社, 2021. [32] 西宁市环境保护局. 2021年度西宁市大中城市固体废物污染环境防治信息发布内容[A/OL]. (2022-08-30)[2023-12-07]. https://shj.xining.gov.cn/zwgk/xxgknb/202208/t20220830_119479.html. [33] 三亚市生态环境局. 三亚市生态环境局关于2020年三亚市环境状况的公报[A/OL]. (2021-06-05)[2023-12-07]. http://hbj.sanya.gov.cn/sthjsite/tzgg/202106/289b859dbe59473fbb6d4be6163d1fe6.shtml. [34] 陈国艳, 张衍国, 曾纪进. 灰色系统理论对我国垃圾产量的预测[J]. 环境保护科学,2011,37(4):29-32. doi: 10.3969/j.issn.1004-6216.2011.04.010CHEN G Y, ZHANG Y G, ZENG J J. Forecasting municipal solid wastes (MSW) production by gray system theory in China[J]. Environmental Protection Science,2011,37(4):29-32. doi: 10.3969/j.issn.1004-6216.2011.04.010 [35] 姚雁彬. “碳中和” 愿景下我国城市生活垃圾低碳管理研究: 时空演化、驱动因素、减排路径[D]. 扬州: 扬州大学, 2022. [36] GUO R, LIU H M, SUN H H, et al. Forecasting of municipal solid waste generation in China based on an optimized grey multiple regression model[J]. Journal of Material Cycles and Waste Management,2022,24(6):2314-2327. doi: 10.1007/s10163-022-01479-6 [37] 成金华, 易佳慧, 史峰雨. 中国城市生活垃圾排放及其影响因素的时空变化研究[J]. 华中师范大学学报(自然科学版),2020,54(4):511-521.CHENG J H, YI J H, SHI F Y. Study on the temporal and spatial changes of municipal solid waste generation and influencing factors in China[J]. Journal of Central China Normal University (Natural Sciences),2020,54(4):511-521. [38] 马涛, 王晓磊, 洪涛, 等. 我国城市生活垃圾能源化利用潜力时空分析及影响因素分析[J]. 节能技术,2021,39(2):99-106.MA T, WANG X L, HONG T, et al. Temporal and spatial variation & influence factors analysis of waste-to-energy utilization potential for municipal solid waste in China[J]. Energy Conservation Technology,2021,39(2):99-106. [39] 侯亚文. 基于灰色关联度的城市生活垃圾“零废弃”管理影响因素研究[D]. 北京: 北京化工大学, 2021. [40] 傅碧天. 基于STIRPAT模型的城市生活垃圾产生量影响因素分析研究[J]. 绿色科技,2020(12):130-132.FU B T. Influential factors of municipal solid waste generation based on STIRPAT model[J]. Journal of Green Science and Technology,2020(12):130-132. [41] 贾积身, 陈振坤. 基于分数阶GM(1, N)模型的深圳市生活垃圾产生量预测[J]. 安全与环境学报,2022,22(6):3387-3395.JIA J S, CHEN Z K. Prediction of municipal solid waste productionin Shenzhen based on fractional grey GM(1, N) model[J]. Journal of Safety and Environment,2022,22(6):3387-3395. [42] 都晓艺. 基于初始值与背景值双重优化的GM(1, N)幂模型构建研究[D]. 无锡: 江南大学, 2022. [43] ZHAO S F, REN T T, MA L, et al. Multi-period planning of municipal solid waste management: a case study in Qingdao[J]. Process Integration and Optimization for Sustainability,2023,7(1):107-126. [44] 李扬, 谭全银, 董庆银, 等. 中国西北典型城市西宁生活垃圾产生及回收[J]. 环境污染与防治,2020,42(3):385-388.LI Y, TAN Q Y, DONG Q Y, et al. Production and recycling of municipal solid waste in typical northwest city of China, Xining[J]. Environmental Pollution & Control,2020,42(3):385-388. [45] 万翼, 李莉, 菊春燕, 等. 乌鲁木齐市塑料垃圾年产量预测及影响因素分析[J]. 中国塑料,2022,36(4):121-127.WAN Y, LI L, JU C Y, et al. Prediction of annual output of plastic waste in Urumqi city and analysis of influence factors[J]. China Plastics,2022,36(4):121-127. [46] LIU C, WU X W. Factors influencing municipal solid waste generation in China: a multiple statistical analysis study[J]. Waste Management & Research,2011,29(4):371-378. [47] 郭秋雨. 基于BP神经网络的建筑垃圾产量预测研究[D]. 济南: 山东建筑大学, 2023. [48] 刘菊芳. 基于机器学习的城市生活垃圾产生量和热值的预测与优化研究[D]. 北京外国语大学, 2024. [49] ZHAO X, LIU H S, DING L L. Decomposition analysis of the decoupling and driving factors of municipal solid waste: taking China as an example[J]. Waste Management,2022,137:200-209. doi: 10.1016/j.wasman.2021.11.003 [50] 牛欢欢. 垃圾分类背景下上海市生活垃圾产生量的影响因素研究及预测[J]. 环境卫生工程,2023,31(2):41-45.NIU H H. Study on influencing factors and prediction of MSW production in Shanghai under the background of waste classification[J]. Environmental Sanitation Engineering,2023,31(2):41-45. [51] ZHAO Y, TAO Z, LI Y, et al. Prediction of municipal solid waste generation and analysis of dominant variables in rapidly developing cities based on machine learning: a case study of China[J]. Waste Management & Research, 2023: 734242X231192766. [52] 姚忠胜, 钱虹, 吴文军, 等. 基于多因素综合评价和改进灰色关联的供电可靠性研究[J]. 电力系统保护与控制,2021,49(11):28-34.YAO Z S, QIAN H, WU W J, et al. Research on power supply reliability based on multi-factor comprehensive evaluation and improved gray relation[J]. Power System Protection and Control,2021,49(11):28-34. [53] 汪平生, 陈俊, 陈召明, 等. 合肥市生活垃圾产量多模型预测与分析[J]. 环境监测管理与技术,2022,34(4):64-67.WANG P S, CHEN J, CHEN Z M, et al. Multi-model prediction and analysis of domestic waste output in Hefei[J]. The Administration and Technique of Environmental Monitoring,2022,34(4):64-67. □