Yusuf, Rasheed, Lindseth and Slaastuen approach public transport as a data-rich operational field whose latent patterns can be extracted, cleaned and reorganised for predictive urban mobility systems. The work’s iconic idea is that historical transit data, when enriched with temporal, geospatial and operational metadata, can become a precursor to dynamic mobility digital twins. Its theoretical contribution is modest but technically important: it treats public transport not as a static service network, but as an evolving informational environment in which demand, punctuality, spatial distribution and external conditions interact. Methodologically, the paper performs a preprocessing and exploratory analysis of AtB bus data in Trondheim, using passenger-counting records to identify regularities, anomalies and modelling possibilities. Its bridge to the wider field is the convergence between transport engineering, machine learning, smart mobility and urban governance: data quality becomes the condition under which digital twins can move from representational ambition to operational decision support.