ABSTRACT The use of interdisciplinary approaches and the application of artificial intelligence tools can be of significant value in addressing the most pressing engineering needs. The use of artificial intelligence in tunnelling has expanded rapidly, with machine learning (ML) emerging as a particularly prominent subfield. However, although the advent of new technologies has made it possible to acquire large amounts of data at a faster rate, the amount of data obtained from tunnelling projects remains relatively modest. Moreover, as explained in a recent paper [1], the datasets obtained in the field may be subject to noise and may contain missing data, mainly due to loss of signal from sensors or their damage, distortion of monitoring points, lack of light, obstructed access to the area to be monitored, etc. Therefore, it is necessary to evaluate the potential contribution of ML to the design of underground structures, mainly in terms of its efficiency and accuracy with limited field data. The main purpose of this paper is to present the main findings of the exploratory work carried out based on different case studies [1, 2, 3] and to provide feedback that could serve as a basis for future research and engineering applications. The use of ensemble learning with small data sets and their applicability to tunnel projects will be discussed, as well as the possibility of obtaining incremental learning - interpretable models that can be used from the start of excavation. REFERENCES [1] Guayacán-Carrillo LM and Sulem J (2024). Symbolic regression based prediction of anisotropic closure in deep tunnels. Computers and Geotechnics, 171:106355. [2] Richa T, Pereira JM, Guayacán-Carrillo LM, Chapron G, Lanquette F (2024). Accuracy of Machine Learning techniques in forecasting tunnelling-induced soil settlements with limited data. XVIII European Conference on Soil Mechanics and Geotechnical Engineering. Lisbonne, August 2024. [3] Tristani A, Guayacán-Carrillo LM, Sulem J & Donzis S (2023). Applicability of Artificial Neural Networks (ANN) for equilibrium state prediction in tunnel excavation. In: Schubert & Kluckner (eds.), Challenges in Rock Mechanics and Rock Engineering. Proc. 15th ISRM Congress 2023 & 72nd Geomechanics Colloquium. Salzburg, October 2023. pp. 1699-1704.