All Issue

2026 Vol.44, Issue 2 Preview Page

Article

Prediction of Road Maintenance Intervention and Assessment of Influencing Factors with ML-SHAP: Focusing on Road Traffic Conditions in Jeju

ML-SHAP 기반 도로 유지보수 발생 예측 및 영향요인 검토: 제주도 도로 교통 현황을 중심으로

Yeonwoo SEO1
,
Taeseong KIM1
,
Gyugeun YOON2*
,
Young Joon LEE3
서 연우1
,
김 태성1
,
윤 규근2*
,
이 영준3
1The Integrated Master and Ph.D. Course, Department of Civil, Urban and Environmental Engineering, Seoul National University, Seoul 08826, Korea
2Assistant Professor, Department of Civil, Urban and Environmental Engineering, Seoul National University, Seoul 08826, Korea
3Associate Professor, Department of Artificial Intelligence, Cheju Halla University, Jeju Special Self-Governing Province 63092, Korea
1서울대학교 건설환경도시공학부 석박사통합과정
2서울대학교 건설환경도시공학부 조교수
3제주한라대학교 인공지능학과 부교수
*Corresponding Author
30 April 2026. pp. 289-305
PDF XML Citation
Abstract

Pavement performance deterioration is known to result from the combined effects of traffic demand, axle loading, climatic conditions, and coastal environments. A wide range of models has been proposed worldwide to predict pavement deterioration and the timing of maintenance. In recent years, Jeju Province has experienced a sustained increase in traffic volumes driven by annual visits of more than 10 million tourists, which may accelerate the aging of road infrastructure and raise maintenance costs. In Jeju City, pothole-related complaints are occurring at an average of 3,000 to 4,000 per year, and the number of pothole repairs over the past three years has averaged approximately 2,400 per year. To quantitatively analyze future road maintenance needs, it is required to link Jeju’s distinct road-transport environment, characterized by a maritime climate, frequent rainfall, and a high proportion of coastal roads, with maintenance records. Therefore, this study reviews Jeju’s road-transport conditions and constructs an annual, link-level dataset that integrates road, traffic, and weather factors for both national and local roads. Based on the integrated dataset, a machine learning model is developed to predict future maintenance occurrence, and SHAP (SHapley Additive exPlanations) is applied to interpret the relative importance and directional contributions of key factors associated with maintenance events. The results provide that even when direct pavement condition indices (i.e., cracking and rutting) are not readily available, annual traffic, weather, and road characteristics alone can be used to proactively identify links with a high likelihood of maintenance (intervention) in the following year. The findings provide empirical evidence that can support the selection of maintenance targets and annual budget allocation, as well as priority-setting linked to peak-season traffic management in Jeju.

Keywords
explainable artificial intelligence
heterogeneous data
machine learning
pavement management system
road maintenance

포장도로의 성능 저하는 교통량과 축하중, 기후 조건, 해안 환경 등의 다양한 요인의 복합적 영향으로 발생하며, 이를 규명하기 위해 국내외 도로 성능 저하 및 보수 시점을 예측하는 다양한 모형들이 제안되고 있다. 최근 제주특별자치도는 연간 1,000만 명이 넘는 관광객 방문으로 인하여 교통량이 지속적으로 증가하고 있으며, 이는 도로 기반 시설의 조기 노후화와 유지 관리 비용 증가로 이어질 수 있다. 일례로, 제주시에서는 포트홀 관련 민원이 연간 3,000~4,000건 수준으로 발생하고 있으며, 최근 3년간 포트홀 보수 건수도 연 평균 약 2,400건에 달했다. 제주도의 장래 도로보수 수요를 정량적으로 분석하기 위해서는 해양성 기후와 잦은 강우, 높은 해안 인접 도로 비율 등으로 대표되는 교통 환경 특성과 유지보수 기록을 직접 연계하는 연구가 필요한 실정이다. 이에 본 연구는 제주도 도로 교통 현황을 검토하고, 국지도 및 지방도를 대상으로 연간 도로·교통·기상 자료를 통합한 데이터셋을 구축하였다. 또한, 이를 활용하여 머신러닝(Machine Learning; ML) 기반 장래 유지보수 발생 예측 모형을 구축하고, SHAP(SHapley Additive exPlanations)을 적용하여 유지보수 발생에 영향을 미치는 주요 요인의 중요도와 기여 방향을 해석하였다. 본 연구의 결과는 유지보수 소요 가능성이 높은 구간을 선제적으로 도출하는 정량적 근거를 제시하며, 제주도 도로의 유지보수 대상 선정과 연차별 예산 분배 및 우선순위 결정 등에 활용될 수 있을 것으로 기대된다.

키워드
해석가능한 인공지능
이질적 데이터
머신러닝
포장관리시스템
도로 유지보수
References
1

Ayoub J., Yang X. J., Zhou F. (2021), Modeling Dispositional and Initial Learned Trust in Automated Vehicles with Predictability and Explainability, Transportation Research Part F: Traffic Psychology and Behaviour, 77, 102-116.

10.1016/j.trf.2020.12.015
2

Bae Y. S., Lee S. Y., Shin K. Y. (2012), The Study and Analysis of Road Pavement Management in Seoul, Seoul City Research, 13(2), The Seoul Institute, 207-219.

10.23129/SEOULS.13.2.201206.207
3

Breiman L. (2001), Random Forests, Machine Learning, 45, 5-32.

10.1023/A:1010933404324
4

Chen T., Guestrin C. (2016), XGBoost: A Scalable Tree Boosting System, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794.

10.1145/2939672.2939785
5

Cherkassky V., Ma Y. (2004), Practical Selection of SVM Parameters and Noise Estimation for SVM Regression, Neural Networks, 17(1), 113-126.

10.1016/S0893-6080(03)00169-2
6

Cho E. S., Jo Y., Gu Y. S., Oh C., Lee G. W. (2023), Detection of Risk Riding Events for Delivery Scooter: Methodology and Application, J. Korean Soc. Transp., 41(1), Korean Society of Transportation, 19-34.

10.7470/jkst.2023.41.1.019
7

Famewo B. G., Shokouhian M. (2025), A Review of Pavement Performance Deterioration Modeling: Influencing Factors and Techniques, Symmetry, 17(11), 1992.

10.3390/sym17111992
8

Gharaibeh N. G., Darter M. I. (2003), Probabilistic Analysis of Highway Pavement Life for Illinois, Transportation Research Record, 1823(1), 111-120.

10.3141/1823-13
9

Gope A., Pal A., Tetseo S., Gogoi T., Borah D. (2024), Multi-Class Identification of Tonal Contrasts in Chokri Using Supervised Machine Learning Algorithms, Humanities and Social Sciences Communications, 11(1), 1-13.

10.1057/s41599-024-03113-2
10

Hajihosseinlou M., Maghsoudi A., Ghezelbash R. (2023), A Novel Scheme for Mapping of MVT-Type Pb-Zn Prospectivity: LightGBM, a Highly Efficient Gradient Boosting Decision Tree Machine Learning Algorithm, Natural Resources Research, 32(6), 2417-2438.

10.1007/s11053-023-10249-6
11

Jee J. H., Gu Y. S., Jo Y., Oh C. (2023), Identification of Crash-Prone Road Segments Based on an Ensemble Machine Learning Strategy: Use of Driving Behavior Data, J. Korean Soc. Transp., 41(6), Korean Society of Transportation, 739-752.

10.7470/jkst.2023.41.6.739
12

Jeju Special Self-Governing Province (JSSGP) (2024), General Weather Condition Data, https://www.data.go.kr/tcs/dss/selectFileDataDetailView.do?publicDataPk=15010338, 2026.01.10.

13

Jeju Tourism Organization (JTO) (2024), Statistics of Jeju Visitors, https://www.data.go.kr/data/15007317/fileData.do, 2026.01.10.

14

Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W. et al. (2017), LightGBM: A Highly Efficient Gradient Boosting Decision Tree, Advances in Neural Information Processing Systems, 30.

15

Kim C. H. (2024), https://www.ihalla.com/article.php?aid=1706687083752751044, 2026.02.05.

16

Kim C. W., An S. H., Park H. Y., Lee J. H., Jung C. K. (2015), A Study to Analyze Service Life of Expressway Pavement According to Traffic Volumes and De-Icing Chemicals, International Journal of Highway Engineering, 17(1), Korean Society of Road Engineers, 35-41.

10.7855/IJHE.2015.17.1.035
17

Kim Y. M., An J. H., Shin H. J., Song J. H., Hwang S. D. (2021), A Study of Road Distress Analysis and Design Improvement According to Traffic Characteristics of the Logistic Road for Port Freight Transport, International Journal of Highway Engineering, 23(6), Korean Society of Road Engineers, 137-146.

10.7855/IJHE.2021.23.6.137
18

Korea Institute of Civil Engineering and Building Technology (KICT) (2022), Development of Jeju Pavement Maintenance and Management Technology for the Regional Characteristics of Jeju Island, Goyang, South Korea.

19

Korea Meteorological Administration (KMA) (2024), Open MET Data Portal, https://data.kma.go.kr/cmmn/main.do, 2026.01.10.

20

Korea Transport Institute (KOTI) (2024), View-T: A Data-Driven Service for Mobility Index & Analysis and Data Visualization, https://viewt.ktdb.go.kr/cong/map/page.do, 2026.01.10.

21

Kuruvachalil L., Karim F., Masoud A. R., Hasan U., Ali L., Sulaiman F. B. et al. (2025), Advancing Pavement Management: A Comprehensive Review of Smart Models for Better Decisions, Transportation Research Interdisciplinary Perspectives, 34, 101711.

10.1016/j.trip.2025.101711
22

Kwon S. A., Yoo P. J., Kim K. H., Cho Y. H. (2002), Selection of Long-Term Pavement Performance Sections for Development of Distress Prediction Model in National Asphalt Pavement, International Journal of Highway Engineering, 4(1), Korean Society of Road Engineers, 123-134.

23

Lee K. J., Kim Y. S. (2021), Predictive Model for the Employment Retention of Persons with Disabilities, Journal of Special Education, 37(2), 73-95.

10.31863/JSE.2021.05.37.2.73
24

Lee M. S., Kim Y. J. (2009), A Study on Freight-Only-Lane and Freight-Only-Highway Policies Implemented in the Incheon City, Journal of Korea Port Economic Association, 25(3), The Korea Port Economic Association, 117-138.

25

Lee Y. (2013), A Study on the Method of Establishing Road Maintenance Strategy Considering the Forecasting Traffic Demand, Hanbat University, Master Thesis.

26

Lee Y. J., Sun J. W. (2020), Predicting Highway Concrete Pavement Damage Using XGBoost, Korean Journal of Construction Engineering and Management, 21(6), Korea Institute of Construction Engineering and Management, 46-55.

27

Lee Y. M., Oh S. Y., Lee S. J. (2018), A Study on Prediction of Road Freezing in Jeju, Journal of Environmental Science International, 27(7), The Korean Environmental Sciences Society, 531-541.

10.5322/JESI.2018.27.7.531
28

Lin W., Wu Z., Lin L., Wen A., Li J. (2017), An Ensemble Random Forest Algorithm for Insurance Big Data Analysis, IEEE Access, 5, 16568-16575.

10.1109/ACCESS.2017.2738069
29

Lundberg S. M., Lee S. I. (2017), A Unified Approach to Interpreting Model Predictions, Advances in Neural Information Processing Systems, 30.

30

Ministry of Land, Infrastructure and Transport (MOLIT) (2024a), Vehicle Registration Statistics, https://www.data.go.kr/data/15024777/fileData.do, 2026.01.10.

31

Ministry of Land, Infrastructure and Transport (MOLIT) (2024b), Road Statistics, https://stat.molit.go.kr/portal/cate/statMetaView.do?hRsId=59, 2026.01.10.

32

Ministry of Land, Infrastructure and Transport (MOLIT) (2025a), Pavement Design Guideline (도로포장 설계 요령), South Korea.

33

Ministry of Land, Infrastructure and Transport (MOLIT) (2025b), Traffic Monitoring System (TMS), https://www.road.re.kr/main/main.asp, 2026.01.10.

34

Oh J. H., Hwang K. S., Kim K. B., Yang J. C. (2016), The Traffic Accident Factors and Reduction Method in the Hazard Zone of Mountain Sightseeing Roads: Focused on Jeju Local Roads, Journal of the Korea Academia-Industrial Cooperation Society, 17(1), Korea Academia-Industrial Cooperation Society, 374-388.

10.5762/KAIS.2016.17.1.374
35

Park C. M., Kim S. H. (2004), Analysis of the Visual Blockage Ratio of the Buildings on Seaside Road: Focused on the Coastal Round Road in Jeju-Si, Journal of Korea Planning Association, 39(5), Korea Planning Association, 135-154.

36

Park N. R., Park J. Y. (2024), Multi-Stage Machine Learning Approach to Assess Crash Risk Using Vehicle Maneuver Data, J. Korean Soc. Transp., 42(3), Korean Society of Transportation, 331-347.

10.7470/jkst.2024.42.3.331
37

Shapley L. S. (1953), A Value for N-Person Games, Contributions to the Theory of Games II, Princeton University Press, Princeton, 307-317.

10.1515/9781400881970-018
38

Yang J. H., Park J. S., Rim H. S., Kim K. H., Song T. J. (2024), Identifying Factors Affecting the Severity of Rear-End Crashes at Signalized Intersection Approaches Using Machine Learning Technologies, J. Korean Soc. Transp., 42(2), Korean Society of Transportation, 739-752.

10.7470/jkst.2024.42.2.212
39

Yang J., Jiang P., Suhail S. A., Sufian M., Deifalla A. F. (2023), Experimental Investigation and AI Prediction Modelling of Ceramic Waste Powder Concrete: An Approach Towards Sustainable Construction, Journal of Materials Research and Technology, 23, 3676-3696.

10.1016/j.jmrt.2023.02.024
40

Yoo J. E. (2015), Random Forests, An Alternative Data Mining Technique to Decision Tree, Educational Evaluation Study, 28(2), 427-448.

41

Yoon B. J., Lee S. M., Park H. G. (2025), Analysis of Factors Influencing the Severity of Rental Cars Crashes in Tourist Areas Using Machine Learning Algorithms, Journal of the Society of Disaster Information, 21(1), The Korean Society of Disaster Information, 260-272.

42

Yuan R., Li Z., Guan X., Xu L. (2010), An SVM-Based Machine Learning Method for Accurate Internet Traffic Classification, Information Systems Frontiers, 12, 149-156.

10.1007/s10796-008-9131-2
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 44
  • No :2
  • Pages :289-305
  • Received Date : 2026-01-26
  • Revised Date : 2026-02-02
  • Accepted Date : 2026-02-19
  • DOI :https://doi.org/10.7470/jkst.2026.44.2.289
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close