All Issue

2025 Vol.4, Issue 3 Preview Page

Research Article

Estimation of Unit Maintenance Costs by Tunnel Construction Methods Using XGBoost

XGBoost 기반 터널 공법별 단위 보수 비용 예측

Sugyeom Lee1
,
Yeonwoo Nam2
,
Byounggil Shin3
,
Taehyung Lee4
,
Seokho Chi5*
이 수겸1
,
남 연우2
,
신 병길3
,
이 태형4
,
지 석호5*
1Integrated M.S & Ph.D. Student, Department of Civil and Environmental Engineering, Seoul National University
2Ph.D. Student, Department of Civil and Environmental Engineering, Seoul National University
3Director, Research Institute for Safety Performance, Korea Authority of Land & Infrastructure Safety
4Deputy General Manager, Research Institute for Safety Performance, Korea Authority of Land & Infrastructure Safety
5Corresponding Author, Member, Professor, Department of Civil and Environmental Engineering, Seoul National University, Adjunct Professor, Institute of Construction and Environmental Engineering, Seoul National University
1서울대학교 건설환경공학부 석박통합과정
2서울대학교 건설환경공학부 박사과정
3국토안전관리원 정책연구실 차장
4국토안전관리원 정책연구실 실장·공학박사
5교신저자 ‧ 정회원 ‧ 서울대학교 건설환경공학부 교수·서울대학교 건설환경종합연구소 겸임교수
*Corresponding Author
30 September 2025. pp. 17-21
PDF XML Citation
Abstract

The accelerated deterioration of tunnel infrastructure has highlighted the growing importance of effective maintenance. Predicting maintenance costs is a critical component of budget allocation and planning. This study addresses the limitations of conventional methods based on approximate unit costs by proposing a machine learning model that uses actual repair records. A dataset of 6,611 records covering 36 repair methods was collected between 2019 and 2023. The XGBoost algorithm was applied to develop models for cost estimation. As a result, models were developed for 13 methods, achieving an average accuracy of 95.1% and a weighted F1-score of 0.945. The models also achieved an average MAE of 22,822 KRW and an average MAPE of 35.5%. These results show that the proposed approach significantly outperforms traditional unit-price methods. The findings demonstrate the potential of machine learning to improve the accuracy of cost estimation and to support more rational and sustainable budget planning for tunnel maintenance.

Keywords
Tunnel
Maintenance
Cost Estimation
Machine Learning
XGBoost

터널의 노후화가 가속화됨에 따라 유지관리의 중요성이 대두되고 있다. 유지관리 비용을 예측하는 것은 예산 산정 및 계획 수립을 위해 필수적이다. 본 연구는 기존의 개략 단가 기반 예산 산정 방식의 한계를 극복하기 위해, 실제 보수 ∙ 보강 이력을 활용한 머신러닝 기반 터널 시설물의 단위 보수비용 예측 모델을 개발하는 것을 목적으로 한다. 이를 위해 2019년부터 2023년까지 5개년의 36개 보수 ∙ 보강 공법, 6,611건의 데이터를 수집하였으며, XGBoost 알고리즘을 적용하여 비용 예측 모델을 개발하였다. 그 결과 13개 공법에 대한 예측 모델이 구축되었으며, 평균 정확도 95.1%, Weighted F1-score 0.945로 우수한 성능을 보였다. 또한 평균 MAE는 22,822원, 평균 MAPE는 35.5%로, 기존 개략 단가 방식 대비 비용 예측 정확성이 크게 향상되었다. 이는 정확한 비용 예측을 통한 터널 유지관리 예산의 합리적 편성에 기여할 수 있다.

키워드
터널
유지관리
비용 예측
머신러닝
XGBoost
References
1

Avelino, J. G., Cavalcanti, G. D. C., and Cruz, R. M. O. (2024). Resampling strategies for imbalanced regression: a survey and empirical analysis. Artif Intell Rev, 57, article number 82. https://doi.org/10.1007/s10462-024-10724-3

10.1007/s10462-024-10724-3
2

Chen, T., and Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16), 785–794. ACM.

10.1145/2939672.2939785
3

Chen, Z. -L., Chen, J. -Y., Liu, H., and Zhang, Z. -F. (2018). Present status and development trends of underground space in Chinese cities. Tunnelling and Underground Space Technology, 71, pp. 253–270. https://doi.org/10.1016/j.tust.2017.08.027

10.1016/j.tust.2017.08.027
4

KALIS (Korea Authority of Land & Infrastructure Safety). (2024). Statistical Yearbook of 2023 Construction･Infrastructure Safety, (Assessed August 25, 2025)

5

Kim, S. -H. (2023). The effects of newly constructed expressways on regional economies. Journal of the Korean Society of Transportation, 41(1), pp. 68-80. https://doi.org/10.7470/jkst.2023.41.1.068

10.7470/jkst.2023.41.1.068
6

Lee, G., Chang, T., and Chi, S. (2023). Data-driven bridge maintenance cost estimation framework for annual expenditure planning. Journal of Management in Engineering, 40(2). https://doi.org/10.1061/JMENEA.MEENG-5706

10.1061/JMENEA.MEENG-5706
7

Lim, S., and Chi, S. (2019). Xgboost application on bridge management systems for proactive damage estimation. Advanced Engineering Informatics, 41, 100922. https://doi.org/10.1016/j.aei.2019.100922

10.1016/j.aei.2019.100922
8

Mahmoodzadeh, A., Nejati, H., and Mohammadi, M. (2022). Optimized machine learning modelling for predicting the construction cost and duration of tunnelling projects. Automation in Construction, 139, 104305 https://doi.org/10.1016/j.autcon.2022.104305

10.1016/j.autcon.2022.104305
9

Mohamed, A. G., Ghaly, J. E., and Marzouk, M. (2024). Revolutionizing semantic integration of maintenance cost prediction for building systems using artificial neural networks. Journal of Building Engineering, 96, 110416. https://doi.org/10.1016/j.jobe.2024.110416

10.1016/j.jobe.2024.110416
10

MOLIT (Ministry of Land, Infrastructure and Transport). (2024). 2024 road bridge and tunnel status report, (Assessed August 24, 2025).

11

Petroutsatou, K., Georgopoulos, E., Lambropoulos, S., and Pantouvakis, J. -P. (2012). Early Cost Estimating of Road Tunnel Construction Using Neural Networks. Journal of Construction Engineering and Management, 138(6), pp. 679-687. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000479

10.1061/(ASCE)CO.1943-7862.0000479
12

Petroutsatou, K., Vagdatli, T., and Maravas, A. (2023). Probabilistic approach of pre-estimating life-cycle costs of road tunnels. Structure and Infrastructure Engineering, 20(12), pp. 1896–1911. https://doi.org/10.1080/15732479.2023.2165120

10.1080/15732479.2023.2165120
13

Rostami, J., Sepehrmanesh, M., Gharahbagh, E., and Mojtabai, N. (2013). Planning level tunnel cost estimation based on statistical analysis of historical data. Tunnelling and Underground Space Technology, 33, pp. 22-33. https://doi.org/10.1016/j.tust.2012.08.002

10.1016/j.tust.2012.08.002
14

Wang, C., Yao, C., Zhao, S., Zhao, S., and Li, Y. (2022). A comparative study of a fully-connected artificial neural network and a convolutional neural network in predicting bridge maintenance costs. Applied Sciences, 12(7), 3595. https://doi.org/10.3390/app12073595

10.3390/app12073595
15

Wu, X., Shi, X., Li, Y., and Gong, X. (2022). Estimation of Annual Routine Maintenance Cost for Highway Tunnels. Advances in Civil Engineering. https://doi.org/10.1155/2022/5374461

10.1155/2022/5374461
Information
  • Publisher :Korean Society of Automation and Robotics in Construction
  • Publisher(Ko) :(사)한국건설자동화·로보틱스학회
  • Journal Title :Journal of Construction Automation and Robotics
  • Journal Title(Ko) :건설자동화·로보틱스 논문집
  • Volume : 4
  • No :3
  • Pages :17-21
  • Received Date : 2025-09-04
  • Revised Date : 2025-09-15
  • Accepted Date : 2025-09-15
  • DOI :https://doi.org/10.55785/JCAR.4.3.17
Journal Informaiton Journal of Construction Automation and Robotics Journal of Construction Automation and Robotics
Online Submission
  • crossref crossmark
  • crossref cited-by
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close