Open Access

REVIEW

A Review of Artificial Intelligence-Enhanced Fuzzy Multi-Criteria Decision-Making Approaches for Sustainable Transportation Planning

Nezir Aydin^1,2,*, Melike Cari³, Betul Kara³, Ertugrul Ayyildiz^1,3

1 College of Science and Engineering, Hamad bin Khalifa University, Doha, 34110, Qatar
2 Department of Industrial Engineering, Yildiz Technical University, Istanbul, 34349, Türkiye
3 Department of Industrial Engineering, Karadeniz Technical University, Trabzon, 61080, Türkiye

* Corresponding Author: Nezir Aydin. Email:

(This article belongs to the Special Issue: Fuzzy Logic: Next-Generation Algorithms and Applications)

Computers, Materials & Continua 2025, 85(2), 2625-2650. https://doi.org/10.32604/cmc.2025.067290

Received 29 April 2025; Accepted 25 August 2025; Issue published 23 September 2025

Abstract

Transportation systems are rapidly transforming in response to urbanization, sustainability challenges, and advances in digital technologies. This review synthesizes the intersection of artificial intelligence (AI), fuzzy logic, and multi-criteria decision-making (MCDM) in transportation research. A comprehensive literature search was conducted in the Scopus database, utilizing carefully selected AI, fuzzy, and MCDM keywords. Studies were rigorously screened according to explicit inclusion and exclusion criteria, resulting in 73 eligible publications spanning 2006–2025. The review protocol included transparent data extraction on methodological approaches, application domains, and geographic distribution. Key findings highlight the prevalence of hybrid fuzzy AHP and TOPSIS methods, the widespread integration of machine learning for prediction and optimization, and a predominant focus on logistics and infrastructure planning within the transportation sector. Geographic analysis underscores a marked concentration of research activity in Asia, while other regions remain underrepresented, signaling the need for broader international collaboration. The review also addresses persistent challenges such as methodological complexity, data limitations, and model interpretability. Future research directions are proposed, including the integration of reinforcement learning, real-time analytics, and big data-driven adaptive solutions. This study offers a comprehensive synthesis and critical perspective, serving as a valuable reference for researchers, practitioners, and policymakers seeking to enhance the efficiency, resilience, and sustainability of transportation systems through intelligent decision-making frameworks.

---

Keywords

---