Methods of Artificial Intelligence in Infrastructure System

Abstract

The artificial intelligence (AI) revolution offers significant opportunities to capitalise on the growth 
of digitalisation and has the potential to enable the ‘system of systems’ approach required in increasingly complex 
infrastructure systems. This paper reviews the extent to which research in economic infrastructure sectors has 
engaged with fields of AI, to investigate the specific AI methods chosen and the purposes to which they have been 
applied both within and across sectors. Machine learning is found to dominate the research in this field, with 
methods such as artificial neural networks, support vector machines, and random forests among the most popular. 
The automated reasoning technique of fuzzy logic has also seen widespread use, due to its ability to incorporate 
uncertainties in input variables. Across the infrastructure sectors of energy, water and wastewater, transport, and 
telecommunications, the main purposes to which AI has been applied are network provision, forecasting, routing, 
maintenance and security, and network quality management. The data-driven nature of AI offers significant 
flexibility, and work has been conducted across a range of network sizes and at different temporal and geographic 
scales. However, there remains a lack of integration of planning and policy concerns, such as stakeholder 
engagement and quantitative feasibility assessment, and the majority of research focuses on a specific type of 
infrastructure, with an absence of work beyond individual economic sectors. To enable solutions to be implemented 
into real-world infrastructure systems, research will need to move away from a siloed perspective and adopt a more 
interdisciplinary perspective that considers the increasing interconnectedness of these systems.