Knowledge Graph-Driven Process-Level Carbon Emission Control for Green Building Construction

DOI: https://doi.org/10.62517/jes.202602221

Author(s)

Guanqing Gao*

Affiliation(s)

Beijing University of Technology, Beijing, China *Corresponding Author

Abstract

Carbon emissions during the building construction phase are characterized by high intensity, temporal concentration, and complex influencing factors. Traditional post-event accounting and static evaluation methods cannot achieve dynamic monitoring or precise control of process-level carbon emissions. To address this issue, this paper proposes and constructs a Green Construction Carbon Emission Knowledge Graph (GCCE-KG). First, a 50-project green construction case library is built. It has a three-dimensional stratification covering building type, climate zone, and optimization standard. A two-stage expert verification process confirms its representativeness. Second, a four-dimensional carbon reduction measure system is developed for the four major high-carbon work packages. The dimensions are material, process, equipment, and management. A precise mapping matrix linking measures, processes, and emission sources is also established. On this basis, a knowledge graph ontology model is designed with the construction process as the core hub. Six core entity types and their semantic relationships are clearly defined. A hybrid strategy combining structured data mapping and deep learning-based extraction from unstructured text is used for knowledge extraction. Furthermore, based on the reasoning capability of the knowledge graph, a full-process intelligent reasoning system is constructed. It covers high-carbon process identification, emission exceedance root cause tracing, similar case matching, and carbon reduction measure recommendation. A three-tier hierarchical early warning and closed-loop control mechanism is also established. A public building renovation project in Beijing was selected as the demonstration scenario. A six-month engineering application validation was conducted during the main structure construction period. The results show that the average carbon emission intensity of core processes decreased by 24.1%. The average response time to emission exceedance incidents was reduced by 66.7%. The on-site implementation rate of carbon reduction measures reached 100%. The comprehensive evaluation score of green construction improved by 16.6%. This study provides a reusable knowledge base and technical paradigm for refined and intelligent carbon emission control during the building construction phase.

Keywords

Green Construction; Carbon Emission; Knowledge Graph; Process-Level Control; Ontology Model; Intelligent Reasoning

References

[1] National Bureau of Statistics of China. China Statistical Yearbook 2020 [M]. Beijing: China Statistics Press, 2020. (in Chinese) [2] Chen Y, Wu Y, Chen N, Kang C, Du J, Luo C. Calculation of energy consumption and carbon emissions in the construction stage of large public buildings and an analysis of influencing factors based on an improved STIRPAT model [J]. Buildings, 2022, 12(12): 2211. [3] Sandanayake M, Zhang G, Setunge S, Luo W, Li C Q. Estimation and comparison of environmental emissions and impacts at foundation and structure construction stages of a building – A case study [J]. Journal of Cleaner Production, 2017, 151: 319–329. [4] Huang Z J, Zhou H, Yu J, et al. Process-based research on carbon emissions from prefabricated steel structure floor construction [J]. Industrial Construction, 2024, 54(1): 147–155. (in Chinese) [5] Peng C. Calculation of a building‘s life cycle carbon emissions based on Ecotect and building information modeling [J]. Journal of Cleaner Production, 2016, 112(1): 453–465. [6] Yang H. Real-time monitoring and multi-objective optimization of carbon emissions in prefabricated construction sites based on CPS [D]. Chongqing: Chongqing University, 2020. (in Chinese) [7] Peng C. Calculation of a building’s life cycle carbon emissions based on Ecotect and building information modeling [J]. Journal of Cleaner Production, 2016, 112(1): 453–465. [8] Cheng H, Lu Y H, Lu S F. Green construction evaluation of prefabricated building based on G1-entropy-independence weight method [J]. Mathematics in Practice and Theory, 2021, 51(4): 75–87. [9] Tang X, Chen Y J. Comprehensive evaluation method of high-rise building green construction based on cloud model [J]. Open Journal of Business and Management, 2021, 9(6): 2719–2734. [10] Dehdasht G, Ferwati M S, Zin R M, et al. A hybrid approach using entropy and TOPSIS to select key drivers for a successful and sustainable lean construction implementation [J]. PLOS ONE, 2020, 15(2): e0228746. [11] Zhang C, Fang Y T, Dong Z J, et al. Testability index allocation method based on fuzzy analytic network process and group decision-making [J]. Systems Engineering and Electronics, 2025, 47(8): 2570–2580. (in Chinese) [12] Eirgash M A, Toğan V. A dual opposition learning-based multi-objective Aquila Optimizer for trading-off time-cost-quality-CO₂ emissions of generalized construction projects [J]. Engineering Computations, 2024, 41(8/9): 2074–2101. [13] Su S, Sun A, Yan H, et al. Optimization of construction program for economic and environmental sustainability [J]. Renewable and Sustainable Energy Reviews, 2025, 208: 115006. [14] Zhao N, Zhang J, Ding C, Zhang J. Multi-objective optimization of low-carbon highway construction scheduling using ACEMO-TOPSIS algorithm [J]. Journal of Cleaner Production, 2025, 522: 146371. [15] Tan W B, Guo H X, Gong P S, et al. Safety risk assessment of deep foundation pit construction based on ontology and case-based reasoning [J]. Journal of Engineering Management, 2020, 34(2): 147–152. (in Chinese) [16] IPCC. Sixth Assessment Report Synthesis Report: Climate Change 2023 [EB/OL]. https://www.ipcc.ch/report/ar6/syr/, 2023. [17] Chen Y, Wu Y, Chen N, Kang C, Du J, Luo C. Calculation of energy consumption and carbon emissions in the construction stage of large public buildings and an analysis of influencing factors based on an improved STIRPAT model [J]. Buildings, 2022, 12(12): 2211. [18] Sandanayake M, Zhang G, Setunge S, Luo W, Li C Q. Estimation and comparison of environmental emissions and impacts at foundation and structure construction stages of a building – A case study [J]. Journal of Cleaner Production, 2017, 151: 319–329. [19] Huo T, Cong X, Cheng C, Cai W, Zuo J. What is the driving mechanism for the carbon emissions in the building sector? An integrated DEMATEL-ISM model [J]. Energy, 2023, 274: 127399. [20] Abulibdeh A. Geospatial assessment of the carbon footprint of water and electricity consumption in residential buildings in Doha, Qatar [J]. Journal of Cleaner Production, 2024, 445: 141262. [21] Zhao Y, Liu L, Yu M. Comparison and analysis of carbon emissions of traditional, prefabricated, and green material buildings in materialization stage [J]. Journal of Cleaner Production, 2023, 406: 137152. [22] Chen L, Yang M Y, Chen Z H, et al. Conversion of waste into sustainable construction materials: A review of recent developments and prospects [J]. Materials Today Sustainability, 2024, 27: 100930. [23] Cheng H, Lu Y H, Lu S F. Green construction evaluation of prefabricated building based on G1-entropy-independence weight method [J]. Mathematics in Practice and Theory, 2021, 51(4): 75–87. [24] Wenjie X, Song J, Fei G, et al. Application effectiveness evaluation of novel technologies in green construction for substations based on AHP group decision–EWM combination variable-weight model [J]. Sustainability, 2025, 17(17): 7593. [25] Khoshnava S M, Rostami R, Valipour A, et al. Rank of green building material criteria based on the three pillars of sustainability using the hybrid multi criteria decision making method [J]. Journal of Cleaner Production, 2018, 173: 82–99. [26] Qiu B L, Luo D K. A grey multi-level evaluation of industrial park ecology based on a coefficient of variation-attribute hierarchy model [J]. Sustainability, 2021, 13(4): 1805. [27] Eirgash M A, Toğan V. A novel oppositional teaching learning strategy based on the golden ratio to solve the time-cost-environmental impact trade-off optimization problems [J]. Expert Systems with Applications, 2023, 224: 119995. [28] Eirgash M A, Toğan V. A dual opposition learning-based multi-objective Aquila Optimizer for trading-off time-cost-quality-CO2 emissions of generalized construction projects [J]. Engineering Computations, 2024, 41(8/9): 2074–2101. [29] Su S, Sun A, Yan H, et al. Optimization of construction program for economic and environmental sustainability [J]. Renewable and Sustainable Energy Reviews, 2025, 208: 115006. [30] Zhao N, Zhang J, Ding C, Zhang J. Multi-objective optimization of low-carbon highway construction scheduling using ACEMO-TOPSIS algorithm [J]. Journal of Cleaner Production, 2025, 522: 146371. [31] Tao F, Zhang H, Qi Q L, et al. Ten questions on digital twins: analyses and reflections [J]. Computer Integrated Manufacturing Systems, 2020, 26(1): 1–17. [32] Dietz M, Pernul G. Digital twin: empowering enterprises towards a system-of-systems approach [J]. Business & Information Systems Engineering, 2020, 62(2): 179–184. [33] Park K T, Lee J, Kim H J, et al. Digital twin-based cyber physical production system architectural framework for personalized production [J]. International Journal of Advanced Manufacturing Technology, 2020, 106(5): 1787–1810. [34] Chao L, He J, Wang T, Chu W. PairRE: Knowledge graph embeddings via paired relation vectors [C] // Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021: 4360–4369. [35] Lian Z N, Su X P. Calculation of carbon emissions during the civil construction stage of substations based on bill of quantities and construction process energy consumption [J]. Electric Power and Energy, 2025, 46(4): 454–457. (in Chinese) [36] Huang Z J. Construction and application of a basic database of carbon emissions for prefabricated construction processes [J]. World Architecture, 2024(11): 14–15. (in Chinese) [37] Mao J. Carbon emission monitoring and multi-objective optimization of prefabricated building construction stage based on BIM [D]. Xi‘an: Xi’an University of Architecture and Technology, 2024. (in Chinese)