Leveraging Advanced Technologies for (Smart) Transportation Planning: A Systematic Review
Heejoo Son; Jinhyeok Jang; Jihan Park; Akos Balog; Patrick Ballantyne; Heeseo Rain Kwon; Alex Singleton; Jinuk Hwang (2025). Sustainability, 17(5), 2245. DOI: 10.3390/su17052245
Abstract
Transportation systems worldwide are facing numerous challenges, including congestion, environmental impacts, and safety concerns. This study used a systematic literature review to investigate how advanced technologies (e.g., IoT, AI, digital twins, and optimization methods) support smart transportation planning. Specifically, this study examines the interrelationships between transportation challenges, proposed solutions, and enabling technologies, providing insights into how these innovations support smart mobility initiatives. A systematic literature review, following PRISMA guidelines, identified 26 peer-reviewed articles published between 2013 and 2024, including studies that examined smart transportation technologies. To quantitatively assess relationships among key concepts, a Sentence BERT-based natural language processing approach was employed to compute alignment scores between transportation challenges, technological solutions, and implementation strategies. The findings highlight the fact that real-time data collection, predictive analytics, and digital twin simulations significantly enhance traffic flow, safety, and operational efficiency while mitigating environmental impacts. The analysis further reveals strong correlations between traffic congestion and public transit optimization, reinforcing the effectiveness of integrated, data-driven strategies. Additionally, IoT-based sensor networks and AI-driven decision-support systems are shown to play a critical role in sustainable urban mobility by enabling proactive congestion management, multimodal transportation planning, and emission reduction strategies. From a policy perspective, this study underscores the need for investment in urban-scale data infrastructures, the integration of digital twin modeling into long-term planning frameworks, and the alignment of optimization tools with public transit improvements to foster equitable and efficient mobility. These findings offer actionable recommendations for policymakers, engineers, and planners, guiding data-driven resource allocation and legislative strategies that support sustainable, adaptive, and technologically advanced transportation ecosystems.
Extended Summary
This research examines how emerging technologies including Internet of Things (IoT), artificial intelligence, digital twins, and optimisation algorithms are transforming transportation planning and operations to address mounting urban mobility challenges. The study employed a systematic literature review methodology following PRISMA guidelines, analysing 26 peer-reviewed articles published between 2013 and 2024 that examined smart transportation technologies. To quantify relationships between transportation challenges, proposed solutions, and enabling technologies, the research utilised a Sentence BERT-based natural language processing approach to compute alignment scores and identify key patterns. The analysis reveals six major transportation challenges: technical capability and real-time data utilisation issues, traffic congestion, public transit and multimodal system inefficiencies, safety and accident risks, environmental impacts, and operational management difficulties. The research identifies corresponding solutions including real-time traffic monitoring and control systems, predictive analytics, public transit optimisation, safety enhancement measures, dynamic traffic flow management, and scenario-based planning approaches. Key findings demonstrate that IoT-based sensor networks and big data processing form the foundation of modern smart transportation systems, with strong correlations between real-time data collection capabilities and predictive analytics (BERT similarity score of 0.9175). Digital twin technologies show particular promise for scenario planning and strategic simulations, whilst machine learning and AI-based approaches excel in traffic prediction and congestion classification tasks. The study reveals significant alignment between traffic congestion challenges and public transit optimisation solutions (similarity score of 0.8186), suggesting that integrated multimodal strategies are essential for addressing urban mobility problems. Technical capability and real-time data utilisation challenges show strongest correlation with predictive analytics solutions (0.9285), highlighting the critical importance of robust data processing infrastructure. From a policy perspective, this research emphasises the need for substantial investment in urban-scale data infrastructure, including public-private partnerships and open data platforms to support congestion management and safety enforcement. The findings advocate for integrating digital twin modelling into long-term planning frameworks to enable scenario-based assessments of policy interventions before major financial commitments. The research also highlights the importance of aligning optimisation tools with public transit improvements to promote equitable, efficient mobility services whilst reducing environmental impacts through AI-driven predictive analytics and emission reduction strategies.
Key Findings
- Real-time data collection and predictive analytics demonstrate the strongest technological alignment in smart transportation systems with similarity scores above 0.9.
- Traffic congestion challenges correlate strongly with public transit optimisation solutions, emphasising the effectiveness of integrated multimodal strategies.
- IoT-based sensor networks and digital twin technologies form critical infrastructure for proactive congestion management and scenario-based planning.
- Technical capability and data utilisation challenges require substantial investment in urban-scale infrastructure and standardised interoperability protocols.
- Machine learning and AI-based decision support systems enable dynamic traffic management whilst addressing safety, environmental, and operational efficiency concerns.
Citation
@article{son2025leveraging,
author = {Heejoo Son; Jinhyeok Jang; Jihan Park; Akos Balog; Patrick Ballantyne; Heeseo Rain Kwon; Alex Singleton; Jinuk Hwang},
title = {Leveraging Advanced Technologies for (Smart) Transportation Planning: A Systematic Review},
journal = {Sustainability},
year = {2025},
volume = {17(5)},
pages = {2245},
doi = {10.3390/su17052245}
}