Construction Risk Assessment Prediction of Bridge Project Failures: A Case Study of the Proposed Vikramshila Parallel Bridge, Bhagalpur

Abstract

Large-scale bridge construction projects are exposed to numerous risks due to their technical complexity, challenging environmental conditions, and involvement of multiple stakeholders. This study examines the proposed Vikramshila Parallel Bridge Project in Bhagalpur, Bihar, as a representative case for evaluating construction-related risks in river-crossing infrastructure. The primary objective is to identify, categorize, and assess the major risk factors affecting project performance and structural safety while recommending appropriate mitigation measures. A mixed-method research approach was employed, integrating qualitative risk assessment techniques, including expert consultation and Probability–Impact Matrix analysis, with quantitative prediction using the Random Forest machine learning algorithm. Historical project risk-event data from 2014 to 2025 were analyzed to identify trends and assess overall risk patterns. The results indicate that technical deficiencies, project management shortcomings, environmental challenges, and institutional constraints are the most significant contributors to project disruptions. The Random Forest model demonstrated satisfactory predictive capability in forecasting potential risk scenarios, highlighting its effectiveness as a decision-support tool for infrastructure projects. The study proposes an integrated risk management framework that combines engineering expertise with data-driven analytics to enhance safety, reliability, and sustainability in future bridge construction projects.

Introduction

Bridge construction projects are essential for improving transportation and economic development but involve high levels of complexity, cost, and risk. The study focuses on the Vikramshila Parallel Bridge Project over the Ganga River in Bhagalpur, Bihar, which faces challenges such as fluctuating water levels, river scour, foundation instability, material issues, and management problems. These risks can significantly impact safety, cost, and timely completion.

The research aims to develop an integrated risk management framework that combines traditional qualitative methods with machine learning-based prediction (Random Forest model) to improve risk identification, assessment, and forecasting in bridge construction projects. The literature review highlights that bridge failures are commonly caused by design flaws, poor materials, environmental factors, and weak management practices, while also emphasizing the growing use of AI techniques for risk prediction, though still limited in India.

The methodology uses a mixed-method approach, including case study analysis, expert interviews, historical risk data (2014–2025), and technical documents. Risks are classified into technical, managerial, environmental, and institutional categories, and assessed using a Probability–Impact Matrix. A Random Forest model is then applied to predict future risks and identify key influencing factors. Based on findings, risk response strategies such as avoidance, mitigation, transfer, and acceptance are proposed.

References

[1] D. Zhou, J. Wang, Y. Li, and K. Chen, \"Risk assessment of bridge construction using random forest algorithm,\" Scientific Reports, vol. 14, no. 2, pp. 1132–1147, 2024. [2] R. Singh and V. Mehta, \"Infrastructure risk trends in India,\" Int. J. Infrastructure Manage., vol. 9, no. 4, pp. 245–262, 2022. [3] Y. Chen, Z. Liu, and T. Zhang, \"Structural collapse prediction using machine learning,\" Engineering Structures, vol. 258, 114012, 2023. [4] Indian Roads Congress, Manual on Road Safety Audit (IRC SP 88:2019), New Delhi: IRC, 2019. [5] A. Patel, \"Lifecycle cost analysis in bridge projects: A case-based assessment,\" Indian Highways J., vol. 48, no. 6, pp. 32–39, 2020. [6] World Bank, Quality Infrastructure in Developing Countries, Washington, D.C.: World Bank Group, 2021. [7] S. Kumar and D. Ghosh, \"Case study of the Farakka Barrage,\" J. Civil Eng. Archit., vol. 15, no. 3, pp. 188–195, 2021. [8] N. Sharma, \"Risk categorization in riverine bridge projects,\" ASCE India Conf. Proc., pp. 55–63, 2022. [9] Bureau of Indian Standards, IS 456:2000—Plain and Reinforced Concrete—Code of Practice, New Delhi: BIS, 2000. [10] Bureau of Indian Standards, IS 1343:2012—Prestressed Concrete—Code of Practice, New Delhi: BIS, 2012. [11] A. Bansal and P. Roy, \"AI and IoT in infrastructure auditing,\" Autom. Constr., vol. 147, 104761, 2023. [12] P. Ghosh and K. C. Iyer, \"Delay analysis in public infrastructure projects,\" Constr. Manage. Rev., vol. 12, no. 2, pp. 97–109, 2020. [13] L. Tao, Y. Zhang, and H. Lin, \"Monte Carlo simulations for bridge risk forecasting,\" J. Bridge Eng., vol. 27, no. 4, 04022015, 2022. [14] R. Das, \"Geotechnical failures in riverbed foundations,\" Indian Geotech. J., vol. 49, no. 3, pp. 311–320, 2019. [15] V. K. Raina, Fundamentals of Bridge Engineering, New Delhi: Tata McGraw-Hill, 2015. [16] NITI Aayog, National Infrastructure Pipeline: Vision 2025, Government of India, 2021. [17] A. Kumawat and A. Srivastava, \"Structural health monitoring with fiber optics,\" Sensors Smart Infrastruct., vol. 11, no. 2, pp. 125–136, 2023. [18] W. Lin, R. Huang, and S. Xu, \"Bridge construction accidents in East Asia,\" Eng. Fail. Anal., vol. 112, 104299, 2020. [19] Ministry of Road Transport and Highways, Guidelines for Bridge Inspection and Maintenance, Government of India, 2020. [20] S. Ahmed and M. Pathak, \"BIM for risk planning in bridge construction,\" Int. J. BIM Res., vol. 3, no. 1, pp. 45–53, 2021. [21] P. Bhargava, \"Forensic engineering in bridge failures,\" J. Struct. Forensics, vol. 8, no. 1, pp. 21–29, 2023. [22] M. Choudhary and R. Sinha, \"Probabilistic risk analysis for bridge components,\" Bridge Struct. J., vol. 15, no. 2, pp. 144–150, 2019. [23] A. Sharma, T. Verma, and R. Desai, \"Scour risk evaluation for river bridges,\" Hydraulic Eng. J., vol. 56, no. 4, pp. 277–285, 2020. [24] H. Li and X. Yu, \"Machine learning in civil infrastructure,\" Autom. Constr., vol. 94, pp. 215–227, 2018. [25] R. Gupta and D. Chauhan, \"AI-driven construction quality control,\" Constr. Technol. Today, vol. 18, no. 5, pp. 36–42, 2022. [26] P. Prasad, \"Case study of cable-stayed bridge failures,\" Bridge Eng. Rev., vol. 23, no. 3, pp. 51–58, 2019. [27] B. Rajan, \"Safety compliance in public works projects,\" Indian Infrastruct., vol. 19, no. 7, pp. 28–34, 2020. [28] Z. Wang, Y. Liu, and J. Han, \"Multivariate risk modeling for structural integrity,\" Struct. Saf., vol. 89, 102026, 2021. [29] A. Pandey and V. Gopal, \"Contractor-induced delays in highway projects,\" Transp. Eng. Rev., vol. 9, no. 1, pp. 13–21, 2018. [30] Japan International Cooperation Agency (JICA), Infrastructure Risk Assessment Frameworks in Asia, JICA, 2020. [31] Ministry of Statistics and Programme Implementation, Time and Cost Overrun Reports of Infrastructure Projects, Government of India, 2021. [32] R. Chatterjee and A. Gaur, \"E-governance for project monitoring,\" Proj. Manage. J., vol. 52, no. 6, pp. 540–551, 2021. [33] J. Lee, C. Park, and H. Kim, \"Predictive analytics in urban infrastructure,\" Smart Cities J., vol. 7, no. 2, pp. 89–101, 2020. [34] K. Suresh and R. Rathi, \"Analysis of prestressed girder bridge failures,\" J. Bridge Technol., vol. 15, no. 4, pp. 198–205, 2021.

Copyright

Copyright © 2026 Mr. Lakhan Singh Panwar, Mr. Qadir Raza. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.