|Table of Contents|

Identification and prediction of impact indicators for LCA carbon emissions from highway construction integrated with machine learning(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2026年2期
Page:
151-167
Research Field:
交通工程
Publishing date:

Info

Title:
Identification and prediction of impact indicators for LCA carbon emissions from highway construction integrated with machine learning
Author(s):
LYU Pu1;  WU Yuan-zhe1;  LIU Bei2;  WANG Yuan-qing1*
(1. School of Transportation Engineering, Chang'an University, Xi'an 710061, Shaanxi, China; 2. Suzhou Industry Park Mapping Co., Ltd., Suzhou 215127, Jiangsu, China)
Keywords:
traffic engineering;  carbon emission prediction;  machine learning;  impact indicator;  highway construction;  life cycle assessment(LCA)
PACS:
U491
DOI:
10.19721/j.cnki.1671-8879.2026.02.011
Abstract:
To identify the key impact factors of carbon emission at highway construction stage and predict the carbon emission amount, based on the data of 30 newly constructed highway projects in Guangdong Province, the process-based life cycle assessment(LCA)method was used to systematically calculated the carbon emission amount at the expressway construction stage from bottom to top. Combining the bibliometric method and engineering mechanism analysis, 19 potential impact indicators were preliminarily screened. The judgment criterion was that both the Pearson correlation coefficient and Spearman correlation coefficient were not less than 0.7. Therefore, 13 key indicators strongly related to the carbon emission amount from expressway construction were identified. The consumptions of diesel and electricity were used to reflect the energy consumption level, the consumptions of cement, steel reinforcement and crushed stone were used to reflect the carbon emission characteristics at the material production stage. Indicators such as the total route length, tunnel length, bridge and culvert lengths, fill volume, and cut volume were used to characterized the engineering scale, structural complexity, and construction intensity. On this basis, three machine learning methods, including the support vector regression(SVR), random forest(RF)and back propagation neural network(BPNN), were used to establish the carbon emission prediction amount models. The mean squared error(MSE), root mean squared error(RMSE), mean absolute error(MAE), and coefficient of determination were selected as the model performance evaluation metrics to comparatively analyze the prediction performance of different models. The analysis results show that the random forest model and back propagation neural network model have relatively high prediction accuracies. Their coefficients of determination reach 0.967 8 and 0.972 4, respectively. The back propagation neural network model performs best on the mean squared error and root mean squared error metrics, which are 0.001 6 and 0.039 8, respectively, indicating that the model has a good prediction effect under the current sample conditions.4 tabs, 11 figs, 37 refs.

References:

[1] 余 博,王 尹,柴俊松,等.基于LASSO-GSWOA-KELM模型的石化行业碳排放预测研究[J].现代化工,2024,44(增2):378-385.
YU Bo, WANG Yin, CHAI Jun-song, et al. Prediction of carbon dioxide emission in petrochemical industry based on LASSO-GSWOA-KELM model[J]. Modern Chemical Industry,2024, 44(S2): 378-385.
[2]陈 浩,胡静茹,王寿兵,等.中国钢铁行业CO2排放特征和减排路径研究——基于ARIMA-LEAP模型[J].中国环境科学,2024,44(6):3531-3543.
CHEN Hao, HU Jing-ru, WANG Shou-bing, et al. Research on carbon dioxide emission characteristics and emission reduction path of China's iron and steel industry based on ARIMA-LEAP model[J]. China Environmental Science, 2024, 44(6): 3531-3543.
[3]CHENG A, HAN X R, JIANG G G. Decomposition and scenario analysis of factors influencing carbon emissions: A case study of Jiangsu Province, China[J]. Sustainability, 2023, 15(8): 6718.
[4]贾 敏,张 立,张 哲,等.动态省级电力CO2排放因子对区域碳达峰路径的影响[J].中国工程科学,2024,26(4):121-133.
JIA Min, ZHANG Li, ZHANG Zhe, et al. Impacts of dynamic province-level power-grid CO2 emission factor on regional carbon-peaking pathways[J]. Strategic Study of CAE, 2024, 26(4): 121-133.
[5]WEN L, YUAN X Y. Forecasting CO2 emissions in Chinas commercial department, through BP neural network based on random forest and PSO[J]. Science of the Total Environment, 2020, 718: 137194.
[6]乔 朋,梁志强,徐 凯,等.基于机器学习的中小跨径桥梁技术状况评估[J].长安大学学报(自然科学版),2021,41(6):39-52.
QIAO Peng, LIANG Zhi-qiang, XU Kai, et al. Evaluation of technical condition of medium and small-span bridge based on machine learning[J]. Journal of Chang'an University(Natural Science Edition), 2021, 41(6): 39-52.
[7]陈明圣,洪小燕,彭清霞,等.基于网格搜索-随机森林算法的农业碳足迹水平及其影响因素——以福建省为例[J].生态学报,2025,45(14):6871-6885.
CHEN Ming-sheng, HONG Xiao-yan, PENG Qing-xia, et al. Agricultural carbon footprint evaluation and its influencing factors based on grid search-random forest algorithm: Taking Fujian Province as an example[J]. Acta Ecologica Sinica, 2025, 45(14): 6871-6885.
[8]金国辉,史雅婕,史智婕,等.基于随机森林算法的内蒙古西部绿色低碳农宅灰色模糊综合评价[J].科学技术与工程,2025,25(8):3340-3348.
JIN Guo-hui, SHI Ya-jie, SHI Zhi-jie, et al. Grey fuzzy comprehensive evaluation of green and low-carbon farmhouses in Western Inner Mongolia based on random forest algorithm[J]. Science Technology and Engineering, 2025, 25(8): 3340-3348.
[9]CHU X L, ZHAO R J. A building carbon emission prediction model by PSO-SVR method under multi-criteria evaluation[J]. Journal of Intelligent and Fuzzy Systems, 2021, 41(6): 7473-7484.
[10]FENG M D, DUAN Y H, WANG X, et al. Carbon price prediction based on decomposition technique and extreme gradient boosting optimized by the grey wolf optimizer algorithm[J]. Scientific Reports, 2023, 13(1): 18447.
[11]PAN H Z, WU C J. Bayesian optimization+XGBoost based life cycle carbon emission prediction for residential buildings—An example from Chengdu, China[J]. Building Simulation, 2023, 16(8): 1451-1466.
[12]ZHAO S L, LI Z T, DENG H, et al. Spatial-temporal evolution characteristics and driving factors of carbon emission prediction in China—Research on ARIMA-BP neural network algorithm[J]. Frontiers in Environmental Science, 2024, 12: 1497941.
[13]LUO C, GAO Y Y, JIANG Y D, et al. Predictive modeling of carbon emissions in Jiangsu Province's construction industry: An MEA-BP approach[J]. Journal of Building Engineering, 2024, 86: 108903.
[14]CHANDRASHEKAR C, CHATTERJEE P, PAWAR D S. Modeling real-world diesel car tailpipe emissions using regression-based approaches[J]. Transportation Research Part D: Transport and Environment, 2024, 128: 104092.
[15]KHAJAVI H, RASTGOO A. Predicting the carbon dioxide emission caused by road transport using a random forest(RF)model combined by meta-heuristic algorithms[J]. Sustainable Cities and Society, 2023, 93: 104503.
[16]林宇亮,熊锦江,邢 浩,等.基于XGBoost-SVR组合模型的高速公路建造碳排放量预测方法研究[J].中南大学学报(自然科学版),2024,55(7):2588-2599.
LIN Yu-liang, XIONG Jin-jiang, XING Hao, et al. Research on carbon emission prediction method of expressway construction based on XGBoost-SVR combined model[J]. Journal of Central South University(Science and Technology), 2024, 55(7): 2588-2599.
[17]WU Q X, CHEN Y, LI C Y, et al. Carbon emission scenario prediction for highway construction projects[J]. Frontiers in Environmental Science, 2024, 11: 1302220.
[18]YU C, WU L, LIU Y, et al. Estimating greenhouse gas emissions from road construction by considering the regional differences in carbon emission factors of cement: The case of China[J]. Buildings, 2022, 12(9): 1341.
[19]LIU N, WANG Y Q, BAI Q, et al. Road life-cycle carbon dioxide emissions and emission reduction technologies: A review[J]. Journal of Traffic and Transportation Engineering(English Edition), 2022, 9(4): 532-555.
[20]ZHAO Y C, DUAN X Y, YU M. Calculating carbon emissions and selecting carbon peak scheme for infrastructure construction in Liaoning Province, China[J]. Journal of Cleaner Production, 2023, 420: 138396.
[21]ZHANG X C, SUN J Y, ZHANG X Q, et al. Assessment and regression of carbon emissions from the building and construction sector in China: A provincial study using machine learning[J]. Journal of Cleaner Production, 2024, 450: 141903.
[22]王元庆,李佳玥,刘 备,等.基于XGBoost-SHAP方法的建设项目碳排放空间异质性分析[J].环境科学,2025,46(7):4090-4100.
WANG Yuan-qing, LI Jia-yue, LIU Bei, et al. Spatial heterogeneity of carbon emissions from construction projects based on XGBoost-SHAP[J].Environmental Science, 2025, 46(7): 4090-4100.
[23]包 含,王 耿,晏长根,等.公路建设碳排放核算与岩土工程低碳措施及碳补偿研究综述[J].中国公路学报,2025,38(1):46-72.
BAO Han, WANG Geng, YAN Chang-gen, et al. Highway construction carbon emission assessment and low-carbon measures and carbon compensation for geotechnical engineering: A review[J]. China Journal of Highway and Transport, 2025, 38(1): 46-72.
[24]LIU Y Y, WANG Y Q, LI D. Estimation and uncertainty analysis on carbon dioxide emissions from construction phase of real highway projects in China[J]. Journal of Cleaner Production, 2017, 144: 337-346.
[25]LUO W K, SANDANAYAKE M, ZHANG G M, et al. Construction cost and carbon emission assessment of a highway construction—A case towards sustainable transportation[J]. Sustainability, 2021, 13(14): 7854.
[26]刘 备.考虑空间异质性的高速公路项目建设碳排放计算[D].西安:长安大学,2024.
LIU Bei. Calculation of carbon emissions from highway project construction considering spatial heterogeneity[D]. Xi'an: Chang'an University, 2024.
[27]孙付春.“双碳”背景下零碳高速公路建设探索与实践[J].公路,2024,69(12):433-439.
SUN Fu-chun. Exploration and practice of zero carbon highway construction under the background of “dual carbon” goal[J]. Highway, 2024, 69(12): 433-439.
[28]张金喜,苏 词,王 超,等.道路基础设施建设中的节能减排问题及技术综述[J].北京工业大学学报,2022,48(3):243-260.
ZHANG Jin-xi, SU Ci, WANG Chao, et al. Review of energy-saving and emission-reduction issues and technologies in the construction of road infrastructure[J]. Journal of Beijing University of Technology, 2022, 48(3): 243-260.
[29]宋永朝,舒 秦,金程容,等.中国区域交通碳排放预测与碳达峰路径规划[J].环境科学,2025,46(4):1995-2008.
SONG Yong-chao, SHU Qin, JIN Cheng-rong, et al. Regional transport carbon emission forecasting and peak carbon pathway planning in China[J]. Environmental Science, 2025, 46(4): 1995-2008.
[30]SMOLA A J, SCHÖLKOPF B. A tutorial on support vector regression[J]. Statistics and Computing, 2004, 14(3): 199-222.
[31]王巧玲,李双成.云南省碳排放时空演变特征及影响因素分析[J].中国环境科学,2025,45(1):528-537.
WANG Qiao-ling, LI Shuang-cheng. Dynamics of carbon emissions in Yunnan Province: Spatiotemporal characteristics and influencing factors[J]. China Environmental Science, 2025, 45(1): 528-537.
[32]WANG X, DONG X P, ZHANG Z H, et al. Transportation carbon reduction technologies: A review of fundamentals, application, and performance[J]. Journal of Traffic and Transportation Engineering(English Edition), 2024, 11(6): 1340-1377.
[33]冉茂平,邓须红,关佳希,等.基于LCA的道路基础设施碳排放核算与低碳减排技术综述[J].交通运输工程学报,2025,25(5):23-37.
RAN Mao-ping, DENG Xu-hong, GUAN Jia-xi, et al. Review on road infrastructure carbon emission accounting and low-carbon reduction technologies based on LCA[J]. Journal of Traffic and Transportation Engineering, 2025, 25(5): 23-37.
[34]刘卫东,唐志鹏,夏 炎,等.中国碳强度关键影响因子的机器学习识别及其演进[J].地理学报,2019,74(12):2592-2603.
LIU Wei-dong, TANG Zhi-peng, XIA Yan, et al. Identifying the key factors influencing Chinese carbon intensity using machine learning, the random forest algorithm, and evolutionary analysis[J]. Acta Geographica Sinica, 2019, 74(12): 2592-2603.
[35]樊海玮,张国翊,丁爱玲,等.BP改进算法及其在路面裂缝检测中的应用[J].长安大学学报(自然科学版),2010,30(1):46-53.
FAN Hai-wei, ZHANG Guo-yi, DING Ai-ling, et al. Improved BP algorithm and its application in detection of pavement crack[J]. Journal of Chang'an University(Natural Science Edition), 2010, 30(1): 46-53.
[36]钱汉强,时 玥,陈艳艳,等.考虑时间周期的图神经网络地铁客流预测[J].长安大学学报(自然科学版),2025,45(2):154-164.
QIAN Han-qiang, SHI Yue, CHEN Yan-yan, et al. Graph neural network-based subway passenger flow prediction considering time periods[J]. Journal of Chang'an University(Natural Science Edition), 2025, 45(2): 154-164.
[37]马亚飞,孙文康,何 羽,等.基于DC-Unet的混凝土桥梁表观裂缝识别方法[J].长安大学学报(自然科学版),2024,44(3):66-75.
MA Ya-fei, SUN Wen-kang, HE Yu, et al. Surface crack identification method of concrete bridge based on DC-Unet[J]. Journal of Chang'an University(Natural Science Edition), 2024, 44(3): 66-75.

Memo

Memo:
-
Last Update: 2026-04-20