What question did this study set out to answer?

March 21, 2026Open Access

Artificial intelligence for integrating railway freight into multi-actor supply chains: insights from machine learning, deep learning and neural networks

TMTaoufiq El MoussaouiChouaib Doukkali University AMALAA EDDINE EL MOUSSAOUI

Key Points

The central aim is to explore how rail freight can be effectively integrated into multi-actor supply chains, particularly focusing on the impact of AI and coordination.
Quantitative survey of 3,185 stakeholders in rail and multimodal supply chains in Morocco.
Data analysis employing machine learning, deep learning, and artificial neural networks.
Assessment of organizational coordination and information quality's impact on integration outcomes.
Rail freight integration is primarily influenced by organizational and informational factors, not just infrastructure.
Inter-organizational coordination and logistics information quality are the most critical determinants of integration.
AI positively affects rail freight integration but is most effective when proper coordination and information sharing exist.

Abstract

Purpose Rail freight is widely recognized for its economic and environmental advantages, yet it remains weakly integrated into firms' supply chains, particularly in emerging economies. This study aims to investigate the conditions under which rail freight can be effectively integrated into multi-actor supply chains, with specific attention to the role of organizational coordination, information quality and artificial intelligence (AI) in shaping logistics integration outcomes. Design/methodology/approach The study draws on a quantitative survey of 3,185 stakeholders involved in rail-based and multimodal supply chains in Morocco. The data are analyzed using a combination of machine learning, deep learning and artificial neural network models. These methods are used not only to identify the main determinants of rail freight integration but also to capture non-linear relationships, interaction effects and potential integration trajectories that cannot be addressed through conventional linear models. Findings The results show that rail freight integration depends primarily on organizational and informational mechanisms rather than on infrastructure alone. Inter-organizational coordination and logistics information quality emerge as the most influential factors. AI contributes positively to rail freight integration, but its effect is conditional: AI tools significantly enhance integration only when adequate levels of coordination and information sharing are already in place. Scenario simulations further reveal that the strongest integration gains arise from the combined improvement of organizational practices and AI adoption. Originality/value This research contributes to the literature by shifting the focus from infrastructure-centered explanations toward a systemic understanding of rail freight integration. It is among the first studies to empirically combine machine learning, deep learning and artificial neural networks to analyze logistics integration in an emerging-economy context and to show that AI functions as a complementary and amplifying mechanism rather than a standalone solution.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper