nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg journalInfo journalinfonormal searchdiv searchzone qikanlogo popupnotification paper paperNew
人工智能赋能低碳治理的技术机会预测
基金项目(Foundation): 国家社会科学基金项目“人工智能赋能低碳治理的信息处理模式创新研究”(24BTQ064)
邮箱(Email):
DOI:
发布时间: 2026-05-09
出版时间: 2026-05-09
网络发布时间: 2026-05-09
移动端阅读
摘要:

运用BP神经网络模型,基于历史数据对人工智能发展水平与碳排放强度、能源消费结构、低碳政府财政支持率、生活交通脱碳率、人均公园面积、低碳技术专利数之间的相关性进行分析,并对未来几年的发展趋势展开预测。结合图神经网络(GCN-GAE)模型,构建人工智能与低碳治理技术概念关联分析框架,通过优化数据划分和负采样策略,确定模型最佳超参数配置,精准捕捉人工智能技术与低碳治理的关联,进而预测人工智能赋能低碳治理的关键技术方向、路径支撑和政策方案,为“双碳”目标推进与人工智能技术创新提供参考。

Abstract:

Utilizing a BP neural network model and based on historical data, this study analyzes the correlations between the development level of artificial intelligence and several key variables, including carbon emission intensity, energy consumption structure, government fiscal support rate for low-carbon initiatives, decarbonization rate of daily transportation, per capita park area, and the number of low-carbon technology patents. Furthermore, it forecasts the development trends for the coming years. By incorporating a Graph Convolutional Network–Graph Autoencoder (GCN-GAE) model, an analytical framework is constructed to capture the conceptual associations between artificial intelligence and low-carbon governance technologies. Through optimized data partitioning and negative sampling strategies, the optimal hyperparameter configuration of the model is determined, enabling the precise identification of relationships between AI technologies and low-carbon governance. Based on these findings, the study predicts key technological directions, pathway supports, and policy options for AI-enabled low-carbon governance, thereby providing references for advancing the “dual carbon” goals and fostering innovation in artificial intelligence technologies.

参考文献

[1]Van Deursen M, Gupta A. Is enhanced transparency the “backbone” of the Paris agreement? A critical assessment[J]. Transnational Environmental Law, 2025, 14(1): 41-68.

[2]Guo X, Xu J. Carbon reduction in the AI era: how does urban digital intelligence transformation facilitate low-carbon development?[J]. Urban Climate, 2025, 61: 102449.

[3]王海峰,张磊. 人工智能驱动的循证社会治理模式:证据逻辑与实现路径[J].贵州大学学报(社会科学版),2025,43(4):52-66.

[4]Nordhaus W D. Are we approaching an economic singularity? Information technology and the future of economic growth[J]. American Economic Journal: Macroeconomics, 2021, 13(1): 299-332.

[5]朱巧玲,李敏.人工智能、技术进步与劳动力结构优化对策研究[J].科技进步与对策,2018,35(6):36-41.

[6]许年行,王崇骏,刘佳琪.人工智能技术驱动的公司财务研究进展[J].中国科学基金,2024,38(5):806-819.

[7]吴波,张磊,窦军生,等. 穿越技术封锁:人工智能技术驱动中国跨国公司国际化广度发展的机理研究[J/OL].https://link.cnki.net/urlid/50.1023.C.20250716.1602.002,2025-07-17.

[8]陈艺心.人工智能技术在文学领域研究中的应用[J].自然辩证法通讯,2025,47(8):93-99.

[9]古惠冬,杨维光,陈文捷.绿色技术创新对城市碳减排的效应研究[J].学术探索,2022(3):120-132.

[10]朱旭峰,薛佳依,魏俊杰.“双碳”目标下企业绿色转型和低碳发展的路径研究[J].生态文明研究,2024(5):24-36.

[11]陈明华,史楠,张边秀,等.国家重大战略区域绿色低碳发展绩效时空分异与演进趋势[J].资源科学,2024,46(11):2178-2193.

[12]刘伦,杨浩杰,吴俐颖,等.城市社区低碳治理研究进展:框架、潜力与路径[J].规划师,2025,41(5):32-39.

[13]Gao Z, Zhou P, Wen W. What drives urban low-carbon transition? Findings from China[J]. Environmental Impact Assessment Review, 2025, 110: 107679.

[14]刘晓琳.超大城市“双碳”指数得分影响因素及低碳治理策略研究——以北京、深圳、重庆、成都为例[J].中国经贸导刊,2025(14):91-93.

[15]杨龙,王闻娟,覃哲,等.中国大学生气候认知与低碳行为及其影响因素研究——基于随机森林模型分析[J].文化与传播,2022,11(2):6-15.

[16]张友国,白羽洁.区域差异化“双碳”目标的实现路径[J].改革,2021(11):1-18.

[17]孙全胜.数字经济赋能低碳发展的动力机制和实现路径研究[J].兰州财经大学学报,2025,41(1):54-64.

[18]孙振清,杨锐.人工智能技术创新对区域碳排放的影响——机制识别与回弹效应[J].科技管理研究,2024,44(5):168-177.

[19]周嘉,苏秦. “双碳”目标下数字技术赋能工业低碳转型的突破机制与实现路径[J].西安交通大学学报(社会科学版),2025,45(3):92-103.

[20]王娇,孙慧,廖振良. 人工智能技术促进“双碳”目标实现机制研究[J/OL].https://link.cnki.net/urlid/42.1224.G3.20250723.1005.004,2025-07-23.

[21]毛荐其,陆高潮,刘娜,等.面向创新全链条的碳捕获、利用与封存领域技术机会预测[J].情报杂志,2025,44(4):160-172.

[22]李田华,海楠.基于BP神经网络模型的农产品跨境电商供应链需求波动风险预测研究[J].价值工程,2025,44(27):75-78.

[23]梅旭,李明.基于BP神经网络的高新技术企业价值评估[J].商业观察,2025,11(24):54-59.

[24]Zhao X, Ma X, Chen B, et al. Challenges toward carbon neutrality in China: Strategies and countermeasures[J]. Resources, Conservation and Recycling, 2022, 176: 105959.

[25]Pan A, Zhang W, Shi X, et al. Climate policy and low-carbon innovation: evidence from low-carbon city pilots in China[J]. Energy Economics, 2022, 112: 106129.

[26]Pardo Martínez C I, Silveira S. Energy efficiency and CO2 emissions in swedish manufacturing industries[J]. Energy Efficiency, 2013, 6(1): 117-133.

[27]ZHANG X, HOU Y, GENG K. Environmental regulation, green technology innovation, and industrial green transformation: Empirical evidence from a developing economy[J]. Sustainability, 2024, 16(16): 6833.

[28]Wang B, Wang J, Dong K, et al. How does artificial intelligence affect high-quality energy development? Achieving a clean energy transition society[J]. Energy Policy, 2024, 186: 114010.

[29]李昕浩.人工智能对城市碳排放的影响研究[D].长春:吉林建筑大学,2024.

[30]Güran A, Ate? E. Twitter iletileri duygu de?erleri ve bist 30 endeksi günlük de?er de?i?imlerinin pearson korelasyonu ve granger nedensellik analizi[J]. Gazi üniversitesi Mühendislik Mimarl?k Fakültesi Dergisi,2021, 36(3): 1687-1702.

[31]杨亮亮,姚双,李跃艳,等. 基于GCN两阶段特征构造的链路预测与多维评价的技术机会识别研究[J].数据分析与知识发现,2025,9(12):1-17.

[32]邓纹.基于图卷积神经网络的多模态实体对齐算法研究[D].长沙:中南林业科技大学,2025.

[33]毛荐其,陆高潮,刘娜,等.多链路预测指标融合的技术机会预测方法研究[J].情报杂志,2025,44(11):114-124.

基本信息:

中图分类号:TP18;X321

引用信息:

[1]赵晓春,占冉.人工智能赋能低碳治理的技术机会预测[J].山东工商学院学报().

基金信息:

国家社会科学基金项目“人工智能赋能低碳治理的信息处理模式创新研究”(24BTQ064)

发布时间:

2026-05-09

出版时间:

2026-05-09

网络发布时间:

2026-05-09

检 索 高级检索

引用

GB/T 7714-2015 格式引文
MLA格式引文
APA格式引文