All Issue

2025 Vol.19, Issue 4 Preview Page

Research Article

Identification and Validation of Causal Structure to Weather Data

인과구조 식별 및 구조 신뢰성 검정: 기상 데이터 중심으로

Han-Gyeong Chu1
,
Hye-Gi Kim2
,
Deuk-Woo Kim2*
추 한경1
,
김 혜기2
,
김 덕우2*
1Post Doctoral Researcher, Korea Institute of Civil Engineering and Building Technology, Goyang, Korea
2Senior Researcher, Korea Institute of Civil Engineering and Building Technology, Goyang, Korea
1한국건설기술연구원 건축에너지연구본부 박사후연구원
2한국건설기술연구원 건축에너지연구본부 수석연구원
*Corresponding Author
30 August 2025. pp. 149-159
PDF XML Citation
Abstract

To enable rapid analysis of building energy, data-driven approaches—which allow for swift model construction with a minimal number of input variables—are commonly employed. However, conventional machine learning models primarily focus on correlations among data and often lack sufficient consideration of the causal relationships that drive changes in outcomes. To overcome these limitations, causal inference methods have been introduced to systematically uncover cause-and-effect relationships among variables. Nevertheless, it is impractical for researchers to define all causal relationships solely based on domain knowledge. Therefore, a data-driven approach using causal discovery methods is necessary to identify causal structures directly from the data. In this study, two causal discovery algorithms—PC and FCI—were applied to weather data, and the resulting causal structures were comparatively analyzed. Additionally, two validation methods were proposed to evaluate the statistical reliability of the discovered structures. The analysis showed that both algorithms provided meaningful insights into the causal relationships among variables, and revealed discrepancies between the causal structure designed based on the researcher’s domain knowledge and the structure discovered by the algorithms. Finally, the proposed validation approaches proved effective in confirming the statistical reliability of the discovered structures.

Keywords
Causal discovery
PC algorithm
FCI algorithm
Permutation test
Repetition test
키워드
인과발견
PC 알고리즘
FCI 알고리즘
순열검증
반복검증
References
1

Assaad, C.K., Devijver, E., Gaussier, E. (2022). Survey and evaluation of causal discovery methods for time series. Journal of Artificial Intelligence Research, 73, 767-819.

10.1613/jair.1.13428
2

Chen, X., Abualdenien, J., Singh, M.M., Borrmann, A., Geyer, P. (2022). Introducing causal inference in the energy-efficient building design process. Energy and Buildings, 277, 112583.

10.1016/j.enbuild.2022.112583
3

Choi, K., Park, J., Kim, D.W., Joe, J. (2024). Development of a Regression Model for Evaluating Energy Consumption Performance of Daycare Centers Using Open Public Data. Journal of the Korean Solar Energy Society, 44(6), 35-48.

10.7836/kses.2024.44.6.035
4

Eberhardt, F. (2017). Introduction to the foundations of causal discovery. International Journal of Data Science and Analytics, 3, 81-91.

10.1007/s41060-016-0038-6
5

Kim, D.W., Kim, Y.M., Lee, S.E. (2019). Development of an energy benchmarking database based on cost-effective energy performance indicators: Case study on public buildings in South Korea. Energy and Buildings, 191, 104-116.

10.1016/j.enbuild.2019.03.009
6

Kim, H.J., Joo, H.B., Kim, D.W., Heo, Y.S. (2024a). Examining the Influencing Factors of Base and Heating Energy Use Intensities for the Energy Benchmarking of School Buildings. Journal of Korean Institute of Architectural Sustainable Environment and Building Systems, 18(6), 491-501.

7

Kim, J.H., Kim, S., Park, Y.J., Kim, D.W., Kim, E. (2024b). Correlation Analysis Between Non-Energy Public Data of Residential Buildings and Annual Energy Consumption by Usage. Korea Journal of Air-Conditioning and Refrigeration Engineering, 36(12), 606-618.

10.6110/KJACR.2024.36.12.606
8

Ko, Y.D., Park, C.S. (2021). Parameter estimation of unknown properties using transfer learning from virtual to existing buildings. Journal of Building Performance Simulation, 14(5), 503-514.

10.1080/19401493.2021.1972159
9

Mun, J., Park, C.S. (2025). Beyond correlation: A causality-driven model for indoor temperature control. Energy and Buildings, 338, 115739.

10.1016/j.enbuild.2025.115739
10

Nogueira, A.R., Pugnana, A., Ruggieri, S., Pedreschi, D., Gama, J. (2022). Methods and tools for causal discovery and causal inference. Wiley interdisciplinary reviews: data mining and knowledge discovery, 12(2), e1449.

10.1002/widm.1449
11

Shin, H.R., Kim, H.G., Kim, D.W. (2024). DataNet: A Framework for Linking Nationwide Building Energy Datasets to Support Effective Performance Analysis. Journal of Korean Institute of Architectural Sustainable Environment and Building Systems, 18(6), 564-575.

12

Spirtes, P., Glymour, C., Scheines, R., Kauffman, S., Aimale, V., Wimberly, F. (2000). Constructing Bayesian network models of gene expression networks from microarray data. DOI: 10.1184/r1/6491291.v1.

10.1184/r1/6491291.v1
13

Zheng, Y., Huang, B., Chen, W., Ramsey, J., Gong, M., Cai, R., Shimizu, S., Spirtes, P., Zhang, K. (2024). Causal-learn: Causal discovery in python. Journal of Machine Learning Research, 25(60), 1-8.

14

Zhou, A., Wang, S., Chen, B. (2023). Impact of new energy demonstration city policy on energy efficiency: evidence from China. Journal of Cleaner Production, 422, 138560.

10.1016/j.jclepro.2023.138560
15

Kim, H.G., Shin, H., Kim, D.W. (2024c). DataNet Project: A Framework For Linking Multi- Faceted Building Energy Datasets For Effective Performance Analysis, ASim 2024. The 5th Asia Conference of the IBPSA, Osaka, Japan, Dec 8-10, 2024.

16

Meek, C. (2013). Causal inference and causal explanation with background knowledge. arXiv preprint arXiv:1302.4972.

17

Spirtes, P.L., Meek, C., Richardson, T.S. (2013). Causal inference in the presence of latent variables and selection bias. arXiv preprint arXiv:1302.4983.

18

Bareinboim, E., Correa, J.D., Ibeling, D., Icard, T. (2022). On Pearl’s hierarchy and the foundations of causal inference. In Probabilistic and causal inference: the works of judea pearl, 507-556.

10.1145/3501714.3501743
19

Spirtes, P., Glymour, C., Scheines, R. (2001). Causation, prediction, and search. MIT press.

10.7551/mitpress/1754.001.0001
Information
  • Publisher :Korean Institute of Architectural Sustainable Environment and Building Systems
  • Publisher(Ko) :한국건축친환경설비학회
  • Journal Title :Journal of Korean Institute of Architectural Sustainable Environment and Building Systems
  • Journal Title(Ko) :한국건축친환경설비학회논문집
  • Volume : 19
  • No :4
  • Pages :149-159
  • Received Date : 2025-08-08
  • Revised Date : 2025-08-21
  • Accepted Date : 2025-08-21
  • DOI :https://doi.org/10.22696/jkiaebs.20250013
Journal Informaiton Journal of Korean Institute of Architectural Sustainable Environment and Building Systems Journal of Korean Institute of Architectural Sustainable Environment and Building Systems
Manuscript Submission
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close