AI- and Machine Learning-Enabled Decision Systems for Strengthening Transportation Reliability in Nationally Critical Supply Chain Infrastructure

The integration of artificial intelligence (AI) and machine learning (ML) technologies into transportation decision systems has emerged as a transformative approach for enhancing supply chain reliability in nationally critical infrastructure. This comprehensive review examines the current state of AI/ML-enabled decision systems, their applications in transportation logistics, and their impact on strengthening supply chain resilience. Through systematic analysis of recent literature and empirical evidence, this paper identifies key technological frameworks, implementation strategies, and performance metrics that characterize successful AI/ML deployments in transportation systems. The findings reveal that organizations implementing AI-driven predictive analytics achieve significant improvements in on-time delivery rates, cost reduction, and risk mitigation capabilities. Furthermore, the study explores the challenges associated with technology adoption, including data quality issues, integration complexities, and workforce adaptation requirements. The research contributes to the growing body of knowledge on smart transportation systems by providing a structured framework for evaluating AI/ML solutions and offers practical recommendations for policymakers and industry practitioners seeking to enhance transportation reliability through intelligent decision support systems.