Improving Cross-Regional Generalizability of Bridge Deck Deterioration Prediction through Transfer Learning and Explainable Discrete-Time Survival Models
DOI:
https://doi.org/10.54097/xfjhw285Keywords:
Bridge management, deterioration modelling, transfer learning, discrete-time survival analysis, gradient boosting, SHAP, National Bridge Inventory, domain shiftAbstract
Data-driven deterioration models for bridge decks are trained and validated on pooled national data but are used by individual agencies whose climate, materials and inspection practice differ. On the nationwide National Bridge Inventory panel of 150,144 concrete decks, the published discrete-time gradient-boosted hazard model (DT-GBH) reaches a C-index of 0.769 on a random split but only 0.647 on states withheld from training, no better than Cox regression, while its 5-year calibration error grows from 0.009 to 0.050. We show that this failure combines a shift in the level and shape of the hazard with a shift in covariate effects, and that covariate-shift reweighting and state-blocked model selection do not repair it. We propose TL-DTGBH, which adapts a national DT-GBH to a target state from a short local history in two stages on the hazard-logit scale: a five-parameter, ridge-shrunk recalibration of level, slope and period-specific baseline (HLR), followed by residual boosting whose size is chosen by spell-grouped cross-validation and may be zero. The adapted logit splits exactly into transferred national evidence, a local baseline correction and local covariate corrections, each attributed to features by TreeSHAP. In leave-one-state-out experiments on 14 states, HLR halves the calibration error, from 0.103 to 0.054 with only 50 local sojourns, and the full method raises the C-index from 0.666 to 0.684 with 100 and 0.732 with 500 local sojourns, outperforming local-only and Cox-updating models when local data are scarce and matching a pooled model that must be retrained on national data for every state. Under the original unseen-state protocol, a 20% local history lifts the pooled C-index from 0.646 to 0.757.
Downloads
References
[1] American Society of Civil Engineers. (2025). 2025 Report Card for America’s Infrastructure. ASCE.
[2] Federal Highway Administration. (1995). Recording and coding guide for the structure inventory and appraisal of the nation’s bridges (Rep. FHWA-PD-96-001). U.S. Department of Transportation.
[3] Madanat, S., Mishalani, R., & Ibrahim, W. H. W. (1995). Estimation of infrastructure transition probabilities from condition rating data. Journal of Infrastructure Systems, 1(2), 120–125. https://doi.org/10.1061/(ASCE)1076-0342(1995)1:2(120)
[4] Sobanjo, J. O. (2011). State transition probabilities in bridge deterioration based on Weibull sojourn times. Structure and Infrastructure Engineering, 7(10), 747–764. https://doi.org/10.1080/15732470902917028
[5] Manafpour, A., Guler, I., Radlińska, A., Rajabipour, F., & Warn, G. (2018). Stochastic analysis and time-based modeling of concrete bridge deck deterioration. Journal of Bridge Engineering, 23(9), 04018066. https://doi.org/10.1061/(ASCE)BE.1943-5592.0001285
[6] Fleischhacker, A., Ghonima, O., & Schumacher, T. (2020). Bayesian survival analysis for US concrete highway bridge decks. Journal of Infrastructure Systems, 26(1). https://doi.org/10.1061/(ASCE)IS.1943-555X.0000511
[7] Lu, M., & Guler, S. I. (2022). Comparison of random survival forest with accelerated failure time-Weibull model for bridge deck deterioration. Transportation Research Record, 2676(7). https://doi.org/10.1177/03611981221078281
[8] Valkonen, A., & Glisic, B. (2023). Effect of bridge data heterogeneity on neural network survival predictive performance. In Proceedings of the 14th International Conference on Applications of Statistics and Probability in Civil Engineering (ICASP14).
[9] Zhang, S., & Qiu, L. (2026). Explainable discrete-time survival learning for bridge deck deterioration and risk-based preservation prioritization. In Proceedings of AMMEE.
[10] Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. https://doi.org/10.1109/TKDE.2009.191
[11] Shimodaira, H. (2000). Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 90(2), 227–244. https://doi.org/10.1016/S0378-3758(00)00115-4
[12] Dai, W., Yang, Q., Xue, G.-R., & Yu, Y. (2007). Boosting for transfer learning. In Proceedings of the 24th International Conference on Machine Learning (ICML) (pp. 193–200). https://doi.org/10.1145/1273496.1273521
[13] Marcelino, P., Antunes, M. de L., Fortunato, E., & Gomes, M. C. (2020). Transfer learning for pavement performance prediction. International Journal of Pavement Research and Technology, 13, 154–167.
[14] Li, Y., Wang, L., Wang, J., Ye, J., & Reddy, C. K. (2016). Transfer learning for survival analysis via efficient L2,1-norm regularized Cox regression. In Proceedings of the IEEE 16th International Conference on Data Mining (ICDM) (pp. 231–240). https://doi.org/10.1109/ICDM.2016.0034
[15] Steyerberg, E. W., Borsboom, G. J. J. M., van Houwelingen, H. C., Eijkemans, M. J. C., & Habbema, J. D. F. (2004). Validation and updating of predictive logistic regression models: A study on sample size and shrinkage. Statistics in Medicine, 23(16), 2567–2586. https://doi.org/10.1002/sim.1844
[16] van Houwelingen, H. C. (2000). Validation, calibration, revision and combination of prognostic survival models. Statistics in Medicine, 19(24), 3401–3415.
[17] Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2(1), 56–67. https://doi.org/10.1038/s42256-019-0138-9
[18] Fleischhacker, A., Ghonima, O., & Schumacher, T. (2018). Bridge data and code to accompany Bayesian survival analysis for US concrete highway bridge decks [GitHub repository]. https://github.com/flyaflya/nbiData
[19] Bektas, B. A., Carriquiry, A., & Smadi, O. (2013). Using classification trees for predicting national bridge inventory condition ratings. Journal of Infrastructure Systems, 19(4), 425–433.
[20] Allison, P. D. (1982). Discrete-time methods for the analysis of event histories. Sociological Methods & Research, 13, 61–98. https://doi.org/10.2307/270718
[21] Tutz, G., & Schmid, M. (2016). Modeling discrete time-to-event data. Springer.
[22] Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems (Vol. 30, pp. 3146–3154).
[23] Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (Vol. 30, pp. 4765–4774).
[24] Kaplan, E. L., & Meier, P. (1958). Nonparametric estimation from incomplete observations. Journal of the American Statistical Association, 53(282), 457–481.
[25] Cox, D. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society. Series B (Methodological), 34(2), 187–220.
[26] Harrell, F. E., Califf, R. M., Pryor, D. B., Lee, K. L., & Rosati, R. A. (1982). Evaluating the yield of medical tests. JAMA, 247(18), 2543–2546.
[27] Uno, H., Cai, T., Pencina, M. J., D’Agostino, R. B., & Wei, L. J. (2011). On the C-statistics for evaluating overall adequacy of risk prediction procedures with censored survival data. Statistics in Medicine, 30(10), 1105–1117. https://doi.org/10.1002/sim.4154
[28] Graf, E., Schmoor, C., Sauerbrei, W., & Schumacher, M. (1999). Assessment and comparison of prognostic classification schemes for survival data. Statistics in Medicine, 18(17–18), 2529–2545.
[29] Pölsterl, S. (2020). scikit-survival: A library for time-to-event analysis built on top of scikit-learn. Journal of Machine Learning Research, 21(212), 1–6.
[30] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Advanced Engineering and Technology Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
