基于BP神经网络的四川省碳排放预测
成都信息工程大学, 应用数学学院, 四川成都 610225
| 摘 要： | 为应对全球气候变暖问题，中国提出力争2030年前实现碳达峰。四川省是中国西部大省，在中国西部地区具有重大示范作用。因此，以四川省为例，通过查询国家统计局网站和中国碳核算数据库，收集四川省1997年至2021年的碳排放量及其影响因素的历史数据。分析四川省碳排放强度，通过计算影响因素与碳排放量的皮尔逊相关系数，最终选择7个重要影响因素并使用EViews软件预测其未来值。通过实验选择最佳节点数，建立BP神经网络模型（7-3-1结构）并预测2022年至2035年四川省碳排放量。结果表明该BP神经网络模型效果良好，各样本相关系数值均高于0.99，均方根误差RMSE为7.6078（单位：百万吨）。预测结果显示，2022年至2035年四川省碳排放量先增后降，碳达峰时间为2025年，峰值281.2988百万吨。 |
| 关 键 词： | BP神经网络; 四川省碳排放; 碳排放强度; 碳达峰; 相关系数; 预测 |
| DOI： | 10.57237/j.se.2024.01.001 |
View:
Downloads:
收稿日期: 2023-12-04
接受日期: 2024-01-15
在线出版日期: 2024-02-04
Carbon Emission Prediction in Sichuan Province Based on BP Neural Network
College of Applied Mathematics, Chengdu University of Information Technology, Chengdu 610225, China
| Abstract: | To address the issue of global climate change, China proposed to strive to achieve the goal of peaking carbon emissions before 2030. Sichuan Province is a major province in western China and has a significant demonstration role in the western region. Therefore, taking Sichuan Province as an example, historical data on carbon emissions and their influencing factors from 1997 to 2021 were collected by querying the website of the National Bureau of Statistics and the CEADs. The paper analyzed the carbon emission intensity in Sichuan Province, selected 7 important influencing factors by calculating the Pearson correlation coefficient between the influencing factors and carbon emissions and predicted their future values by EViews. Then, selected the optimal number of nodes through experiments, established a BP neural network model (7-3-1 structure) and predicted the carbon emissions of Sichuan Province from 2022 to 2035. The results showed that the BP neural network model had good performance, with correlation coefficient values of all samples higher than 0.99 and root mean square error RMSE of 7.6078 million tons. The prediction results showed that from 2022 to 2035, the carbon emissions in Sichuan Province would first increase and then decrease, with a peak of 281.2988 million tons in 2025. |
| Keywords: | BP Neural Network; Carbon Emissions in Sichuan Province; Carbon Emission Intensity; Carbon Peaking; Correlation Coefficient; Prediction |
参考文献
| [1] | Li D Z, Huang G Y, Zhang G M, et al. Driving factors of total carbon emissions from the construction industry in Jiangsu Province, China [J]. Journal of Cleaner Production, 2020, 276: 123179. |
| [2] | 方晓丽, 骆勇. 四川省公路水路货运能耗及碳排放趋势预测方法研究 [J]. 交通节能与环保, 2019, 15(3): 23-26. |
| [3] | 张丹, 刘建文, 高一茹. 四川省工业碳排放量影响因素与预测 [J]. 重庆交通大学学报: 社会科学版, 2019, 19(4): 90-96. |
| [4] | 廖祖君, 张剑宇, 陈诗薇. 碳排放影响因素及达峰路径研究——基于四川省的分析 [J]. 软科学, 2023, 37(9): 95-101. |
| [5] | 李乔楚, 陈军华, 何京. 基于系统动力学-Visual Studio集成模型的区域碳排放中长期变化趋势预测——以四川省为例 [J]. 环境污染与防治, 2022, 44(12): 1669-1675. |
| [6] | 李乔楚, 陈军华. 集成系统动力学和清单算法的能源结构调整对碳排放影响研究——以四川省为例 [J]. 安全与环境学报, 2023, 网络首发. https://doi.org/10.13637/j.issn.1009-6094.2023.0603 |
| [7] | 卢奕亨, 田云, 周丽丽. 四川省农业碳排放时空演变特征及其影响因素研究 [J]. 中国农业资源与区划, 2023, 网络首发. https://kns.cnki.net/kcms/detail//11.3513.s.20230116.1840.008.html |
| [8] | 赵金元, 马振, 唐海亮. BP神经网络和多元线性回归模型对碳排放预测的比较 [J]. 科技和产业, 2020, 20(11): 172-176. |
| [9] | 赵成柏, 毛春梅. 基于ARIMA和BP神经网络组合模型的我国碳排放强度预测 [J]. 长江流域资源与环境, 2012, 21(6): 665-671. |
| [10] | 胡振, 龚薛, 刘华. 基于BP模型的西部城市家庭消费碳排放预测研究——以西安市为例 [J]. 干旱区资源与环境, 2020, 34(7): 82-89. |
| [11] | Wang W X, Tang R C, Li C, et al. A BP neural network model optimized by Mind Evolutionary Algorithm for predicting the ocean wave heights [J]. Ocean Engineering, 2018, 162: 98-107. |
| [12] | Shan Y, Guan D, Zheng H, et al. China CO2 emission accounts 1997-2015 [J]. Scientific Data, 2018, 5: 1-14. |
| [13] | Shan Y, Huang Q, Guan D, et al. China CO2 emission accounts 2016-2017 [J]. Scientific Data, 2020, 7(1): 1-9. |
| [14] | Guan Y, Shan Y, Huang Q, et al. Assessment to China’s Recent Emission Pattern Shifts [J]. Earth’s Future, 2021, 9(11): 1-13. |
| [15] | Shan Y, Liu J, Liu Z, et al. New provincial CO2 emission inventories in China based on apparent energy consumption data and updated emission factors [J]. Applied Energy, 2016, 184: 742-750. |
| [16] | 曾鸿, 耿源. “双碳”战略下四川省碳排放规模影响因素研究 [J]. 科技和产业, 2022, 22(11): 280-283. |
| [17] | 杨俊祺, 范晓军, 赵跃华等. 基于PSO-BP神经网络的山西省碳排放预测[J]. 环境工程技术学报, 2023, 13(6): 2016-2014. |
| [18] | 燕振刚, 李薇, Yan T等. BP神经网络算法在河西绿洲玉米生产碳排放评估中的应用及算法有效性研究 [J]. 中国生态农业学报, 2018, 26(8): 1100-1106. |
