Journal of Transportation Systems

Integration of Digital Twin and AI for Real-Time Prediction and Management of Concrete Deterioration in Structures

2026-04-03T04:22:31+00:00

This paper presents a simplified yet practical AI-integrated Digital Twin framework for predicting concrete deterioration in reinforced concrete structures. The proposed methodology combines Indian Standard (IS) code-based material and exposure parameters with manually fed and simulated sensor data representing strain, temperature, humidity, crack width, ultrasonic pulse velocity, rebound hammer values, and corrosion potential. A virtual structural model acts as a Digital Twin, while a machine learning-based prediction module processes the combined inputs to assess deterioration risk levels and provide maintenance-oriented recommendations. The results demonstrate that the proposed framework is capable of identifying early-stage deterioration trends, including micro-crack initiation and corrosion risk, which are often overlooked by traditional inspection approaches. The study highlights the advantages of AI-based Digital Twins in terms of early warning capability, data-driven interpretation, and long-term maintenance planning. The proposed framework offers a scalable foundation for future real-time implementations and contributes toward the adoption of intelligent monitoring systems for reinforced concrete infrastructure.

Road Safety Audit of Provincial Roads in Karnali Province, Nepal: A GIS-based Assessment of Baluwasangrahi-Kupinde-Khalanga and Devsthal-Chaurjahari-Dolpa Road

2026-03-30T08:16:32+00:00

Road traffic crashes kill over 1.19 million people each year around the world. They are the top cause of death for people aged 5–29. Countries like Nepal, which fall under low- and middle-income categories, are part of a group that accounts for about 92% of global road traffic deaths, despite having only around 60% of the world’s vehicles. In Nepal, rural roads often lack safety features like barriers and signs, which adds to the problem, especially in tough areas like Karnali Province. Karnali has many road safety issues because of fast-growing roads and no regular safety checks at the provincial level. This study does Road Safety Audits on two roads: the 11 km Baluwasangrahi-Kupinde Khalanga section and the 13 km Devsthal-Kainkada-Chaurajahari-Dolpa section. The paper used GPS dashcams to record videos, ArcGIS to map risks and on-site visits to find main problems—narrow roads, deep unprotected sides, rockfall spots, sharp turns, and no school zone signs. About 70% of the road parts are at high or extreme risk. Simple steps like adding zebra crossings, gabions, road markings and signs (B11 for bends, B23 for schools) can reduce crash risks by 30-40%, following global standards. This fits with SDG 3.6 and 9.1, and Nepal's NRSAP (2021-2030). It gives a GIS-based way to improve safety on provincial roads.

Application of Artificial Intelligence in Intelligent Transportation Systems of Indian Smart Cities

2026-01-07T04:55:21+00:00

India’s rapid urbanization, with an urban population projected to reach 600 million by 2031, has intensified challenges such as traffic congestion, road safety concerns, and environmental degradation in cities like Delhi, Mumbai, and Bengaluru. The Smart Cities Mission, launched in 2015, seeks to address these issues through technology-driven solutions, with intelligent transportation systems (ITS) playing a pivotal role. Artificial intelligence (AI), encompassing machine learning, computer vision, and internet of things (IoT) integration, is transforming ITS by enabling real-time traffic management, public transportation optimization, road safety enhancements, and sustainable mobility solutions. This paper explores AI applications in Indian smart cities, analyzing their implementation, impact, and challenges through case studies and data-driven insights. Three tables present current data on AI-driven ITS deployments, performance metrics, and environmental outcomes. Key findings highlight reductions in traffic delays (up to 20%), increased public transport ridership (8–15%), and lowered emissions (8–12%). Challenges include infrastructure limitations, data quality issues, and policy gaps. The study proposes strategies for scalable, equitable ITS solutions, positioning India as a global leader in AI-driven urban mobility.

Analysis of Vehicle Speed Patterns on Urban Arterial Roads: A Case Study of Satdobato-Budhanilkantha Section

2026-04-02T09:09:46+00:00

Urban arterial roads in developing cities frequently encounter challenges related to speeding and traffic safety, stemming from mixed traffic conditions, inadequate enforcement, and suboptimal road design. This study analyses vehicle speed patterns on the Satdobato-Budhanilkantha arterial road in Kathmandu Valley, Nepal, using spot speed data collected via radar guns across six segments. The research examines speed distributions for dominant vehicle types (cars, motorcycles, and buses), evaluates compliance with speed limits, and identifies high-risk zones where speeding correlates with accident propensity. Key findings reveal that motorcycles exhibit the highest average speeds (56.2km/h), particularly in the Maharajgunj-Budhanilkantha section, where 85th percentile speeds exceed safe limits. In contrast, buses demonstrate more regulated speeds (avg. 32.4km/h), though erratic speed variations are observed near intersections. Spatial analysis using GIS highlights critical segments requiring traffic calming measures, such as enhanced signage, speed bumps, and stricter enforcement. The study highlights the need for context-sensitive speed management strategies in urban arterial roads to strike a balance between mobility and safety in rapidly motorising cities. These insights can inform policymakers and transport planners in Nepal and similar regions to mitigate speed-related crash risks.

An Estimation of Pavement Remaining Life Using the Surface Distress Index (SDI)

2026-03-28T04:33:30+00:00

Effective pavement maintenance is essential for ensuring road safety, optimizing performance, and managing infrastructure costs efficiently. This study presents a practical approach for estimating the remaining service life of pavement using the Surface Distress Index (SDI), with a focus on the Kamalbinayak–Dekocha road section in Bhaktapur, Nepal. A comprehensive visual condition survey was conducted to identify and quantify various surface distresses, including cracks, rutting, potholes, and exposed base layers. The distress data were analyzed by segment, and SDI scores were calculated to assess the overall health of the pavement. Based on terrain type and traffic volume, a standard maintenance cycle of six years was implemented. Age correction factors were applied to adjust the pavement age according to the SDI values, allowing for the estimation of the remaining service life for each section. The findings revealed that two out of three segments had already exceeded their expected lifespan, while the third was approaching a critical condition. The overall average remaining life was approximately 0.45 years, indicating an urgent need for maintenance. This SDI-based methodology demonstrates itself as a cost-effective and reliable tool for evaluating pavement conditions and can facilitate improved decision-making in road maintenance planning, particularly in resource-constrained environments.