ABSTRACT
The integration of Machine Learning (ML) and Artificial Intelligence (AI) offers significant potential to enhance efficiency, safety, and sustainability. The International Tunnelling Association (ITA) Working Group 22 (WG22), now renamed “Digitalisation and Automation,” is at the forefront of this digital transformation. This paper introduces an initiative to explore comprehensive frameworks for applying ML and AI in the tunnelling industry. WG22’s subgroup will focus on defining current definitions, workflows, frameworks, datasets, ethics, and use cases specific to tunnelling projects. Our goal is to create a robust foundation that supports the adoption and integration of these advanced technologies across the tunnelling industry.
This paper focuses on: a) Definitions and Terminology: Establishing clear and consistent definitions for ML and AI concepts within the context of tunnelling to ensure a common understanding among stakeholders; b) Workflows and Frameworks: Developing standardised workflows and frameworks that outline the processes for implementing ML and AI in tunnelling projects, from design and construction to operation and maintenance; c) Datasets: Identifying and curating relevant datasets essential for training and validating ML models, including geological data, construction records, and real-time monitoring information; d) Ethics: Addressing the ethical considerations and challenges associated with the use of ML and AI, such as data privacy, algorithmic transparency, and the implications of automated decision-making; and e) Use Cases: Documenting practical use cases that demonstrate the benefits and applications of ML and AI in tunnelling, such as predictive maintenance, risk assessment, and real-time construction monitoring. This initiative aims to facilitate collaboration among global stakeholders, promote innovation, and establish ITA WG22 as a leader in the digital transformation of the tunnelling industry. By leveraging ML and AI, we strive to enhance the efficiency, safety, and sustainability of tunnelling projects, ultimately contributing to the advancement of the field and the achievement of global sustainability goals.
