Carbon Performance Evaluation of Urban Buildings Using Machine Learning-Based Energy Models

  • Yunliang Liu
  • Wei TianEmail author
  • Xiang ZhouEmail author
Conference paper
Part of the Environmental Science and Engineering book series (ESE)


Because of the large number of buildings and the complexity of influencing factors in urban building energy analysis, the computational cost of large-scale energy models for urban buildings is high. Hence, this paper implements a machine learning-based approach to assess carbon emissions of urban buildings. A campus in China is used as a case study to demonstrate this approach, including four steps: automation of construction of engineering-based energy models in a geographic information system (GIS) environment, construction of a matrix of input and output data, creating machine learning models, and sensitivity and carbon emission analysis of urban buildings. The results indicate that this method can effectively assess carbon emissions for urban buildings with different energy-saving measures based on machine learning energy models. The accuracy of machine learning models should be carefully evaluated before implementing them in carbon emission analysis for urban buildings.


Machine learning Building energy model Urban buildings Predictive performance Carbon performance 



This research was supported by the National Natural Science Foundation of China (No. 51778416) and the Key Projects of Philosophy and Social Sciences Research, Ministry of Education (China) (contract No. 16JZDH014).


  1. 1.
    Tian, W., Liu, Y., Heo, Y., Yan, D., Li, Z., An, J., et al.: Relative importance of factors influencing building energy in urban environment. Energy 111, 237–250 (2016)CrossRefGoogle Scholar
  2. 2.
    Reinhart, C.F., Cerezo Davila, C.: Urban building energy modeling—a review of a nascent field. Build. Environ. 97, 196–202 (2016)CrossRefGoogle Scholar
  3. 3.
    Tian, W., Rysanek, A., Choudhary, R., Heo, Y.: High resolution energy simulations at city scale. In: IBPSA Building Simulation Conference (BS2015), Hyderabad, India, 7–9 Dec 2015Google Scholar
  4. 4.
    Tian, W., Choudhary, R.: A probabilistic energy model for non-domestic building sectors applied to analysis of school buildings in greater London. Energy Build. 54, 1–11 (2012)CrossRefGoogle Scholar
  5. 5.
    Schiefelbein, J., Rudnick, J., Scholl, A., Remmen, P., Fuchs, M., Müller, D.: Automated urban energy system modeling and thermal building simulation based on OpenStreetMap data sets. Build. Environ. 149, 630–639 (2019)CrossRefGoogle Scholar
  6. 6.
    Wei, L., Tian, W., Silva, E.A., Choudhary, R., Meng, Q., Yang, S.: Comparative study on machine learning for urban building energy analysis. Procedia Eng. 121, 285–292 (2015)CrossRefGoogle Scholar
  7. 7.
    Yu, D.: A two-step approach to forecasting city-wide building energy demand. Energy Build. 160, 1–9 (2018)CrossRefGoogle Scholar
  8. 8.
    MOC, GB50189-2005: Energy Conservation Design Regulation for Public Buildings. Ministry of Construction (MOC) of P.R.China, China Planning Press (2005) (in Chinese)Google Scholar
  9. 9.
    Liu, Y.: Energy Saving of Urban Buildings Based on 3D Geographic Information System. Master Degree Master Thesis, Tianjin University of Science and Technology, Tianjin, China (2018)Google Scholar
  10. 10.
    DOE: EnergyPlus V9.0.1, October 2018, Department of Energy, USA (2018)Google Scholar
  11. 11.
    R Core Team: R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2017). URL Accessed 10 Dec 2018
  12. 12.
    Ding, Y., Zhang, Z., Zhang, Q., Lv, W., Yang, Z., Zhu, N.: Benchmark analysis of electricity consumption for complex campus buildings in China. Appl. Therm. Eng. 131, 428–436 (2018)CrossRefGoogle Scholar
  13. 13.
    TURCTC, DB29-153-2010: Tianjin design standard for energy efficiency of public buidings. Tianjin Urban-Rural Construction and Transportation Commission (TURCTC). (in Chinese) (2010)Google Scholar
  14. 14.
    Tian, W.: A review of sensitivity analysis methods in building energy analysis. Renew. Sustain. Energy Rev. 20, 411–419 (2013)CrossRefGoogle Scholar
  15. 15.
    Kuhn, M., Johnson, K.: Applied Predictive Modeling. Springer, Berlin (2013)CrossRefGoogle Scholar
  16. 16.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, Berlin (2009)CrossRefGoogle Scholar
  17. 17.
    Chipman, H., George, E.I., Gramacy, R.B., McCulloch, R.: Bayesian treed response surface models. Wiley Interdisc. Rev. Data Min. Knowl. Discovery 3, 298–305 (2013)CrossRefGoogle Scholar
  18. 18.
    Amasyali, K., El-Gohary, N.M.: A review of data-driven building energy consumption prediction studies. Renew. Sustain. Energy Rev. 81, 1192–1205 (2018)CrossRefGoogle Scholar
  19. 19.
    Kim, J.-H.: Estimating classification error rate: repeated cross-validation, repeated hold-out and bootstrap. Comput. Stat. Data Anal. 53, 3735–3745 (2009)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.School of Mechanical EngineeringTongji UniversityShanghaiChina
  2. 2.College of Mechanical EngineeringTianjin University of Science and TechnologyTianjinChina
  3. 3.Tianjin International Joint Research and Development Center of Low-Carbon Green Process EquipmentTianjinChina

Personalised recommendations