Machine learning-driven CO2 emission forecasting for light-duty vehicles in China

IF 7.3 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment Pub Date : 2024-11-12 DOI:10.1016/j.trd.2024.104502

Guiliang Zhou , Lina Mao , Tianwen Bao , Feipeng Zhuang

{"title":"Machine learning-driven CO2 emission forecasting for light-duty vehicles in China","authors":"Guiliang Zhou , Lina Mao , Tianwen Bao , Feipeng Zhuang","doi":"10.1016/j.trd.2024.104502","DOIUrl":null,"url":null,"abstract":"<div><div>The research examines the carbon dioxide (CO2) emissions produced by light-duty vehicles (LDVs) utilizing a thorough dataset of 7,384 cars gathered by the Chinese government between 2018 and 2022. The research aimsto attain a 40–45% decrease in CO2 emissions by 2030 by the application of advanced machine learning algorithms, specifically Catboost. The results reveal that Catboost, recognized for its data efficiency and capability to manage categorical information, surpasses other models in predictive accuracy, including support vector regression and ridge regression. It is particularly notable for its capability to estimate emissions using just a limited set of vehicle attributes. The research offers crucial insights into air pollution, providing vital suggestions for car owners and manufacturers to reduce their environmental effects. Future investigations should prioritize improving the precision of the model and broadening the datasets to enhance the quality of forecasts.</div></div>","PeriodicalId":23277,"journal":{"name":"Transportation Research Part D-transport and Environment","volume":"137 ","pages":"Article 104502"},"PeriodicalIF":7.3000,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transportation Research Part D-transport and Environment","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1361920924004590","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}

引用次数: 0

Abstract

The research examines the carbon dioxide (CO2) emissions produced by light-duty vehicles (LDVs) utilizing a thorough dataset of 7,384 cars gathered by the Chinese government between 2018 and 2022. The research aims to attain a 40–45% decrease in CO2 emissions by 2030 by the application of advanced machine learning algorithms, specifically Catboost. The results reveal that Catboost, recognized for its data efficiency and capability to manage categorical information, surpasses other models in predictive accuracy, including support vector regression and ridge regression. It is particularly notable for its capability to estimate emissions using just a limited set of vehicle attributes. The research offers crucial insights into air pollution, providing vital suggestions for car owners and manufacturers to reduce their environmental effects. Future investigations should prioritize improving the precision of the model and broadening the datasets to enhance the quality of forecasts.

查看原文本刊更多论文

机器学习驱动的中国轻型汽车二氧化碳排放预测

该研究利用中国政府在 2018 年至 2022 年间收集的 7384 辆汽车的完整数据集，对轻型汽车（LDV）产生的二氧化碳（CO2）排放量进行了研究。研究旨在通过应用先进的机器学习算法，特别是 Catboost，到 2030 年实现二氧化碳排放量减少 40-45%。研究结果表明，Catboost 因其数据效率和管理分类信息的能力而得到认可，其预测准确性超过了其他模型，包括支持向量回归和脊回归。尤其值得注意的是，它只需使用有限的车辆属性集就能估算排放量。这项研究提供了对空气污染的重要见解，为车主和制造商减少对环境的影响提供了重要建议。未来的研究应优先考虑提高模型的精度和扩大数据集，以提高预测质量。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Transportation Research Part D-transport and Environment 工程技术-运输科技

CiteScore

14.40

自引率

9.20%

发文量

314

审稿时长

39 days

期刊介绍： Transportation Research Part D: Transport and Environment focuses on original research exploring the environmental impacts of transportation, policy responses to these impacts, and their implications for transportation system design, planning, and management. The journal comprehensively covers the interaction between transportation and the environment, ranging from local effects on specific geographical areas to global implications such as natural resource depletion and atmospheric pollution. We welcome research papers across all transportation modes, including maritime, air, and land transportation, assessing their environmental impacts broadly. Papers addressing both mobile aspects and transportation infrastructure are considered. The journal prioritizes empirical findings and policy responses of regulatory, planning, technical, or fiscal nature. Articles are policy-driven, accessible, and applicable to readers from diverse disciplines, emphasizing relevance and practicality. We encourage interdisciplinary submissions and welcome contributions from economically developing and advanced countries alike, reflecting our international orientation.