Transportation infrastructures, including roads, bridges, tunnels, stations, airports and subways, play fundamental roles in modern society. Engineering failures of transportation infrastructures may result in significant damage to the public. The traditional methods are to monitor, store and analyze the information during the infrastructure and material design, testing, construction, numerical simulations, evaluation, operation, maintenance and preservation, using mechanistic-based, material-based and statistics-based approaches. In recent decades, artificial intelligence (AI) has drawn the attention of many researchers and has been used as a powerful tool to understand and analyze the engineering failures in transportation infrastructure and materials. AI has the advantages of conveniently characterizing infrastructure materials in multi-scale, extracting failure information from images and cloud points, evaluating performance from the signals of sensors, predicting the long-term performance of infrastructure based on big data and optimizing infrastructure maintenance strategies, etc. In the future, AI techniques will be more effective and promising for data collection, transmission, fusion, mining and analysis, which will help engineers quickly detect, analyze and finally prevent the engineering failures of transportation infrastructure and materials. This theme issue presents the latest developments of AI in failure analysis of transportation infrastructure and materials. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.