Identifying, Analyzing, and forecasting commuting patterns in urban public Transportation: A review

With the continuous evolution and refinement of urban functional spaces, the escalating reliance of commuters on public transportation for work-related travel has surged with time. This paper offers a multidimensional overview of research pertaining to identifying, analyzing, and forecasting of urban public transportation commuting patterns. Initially, emphasis is placed on the identification of commuting patterns. We delineate the characteristics of four data sources, summarize the establishing of travel chains, and classify the approaches involved in identifying commuting patterns. Subsequent to this, we delve into the type of determinants influencing commuters, exploring the ramifications of spatial–temporal heterogeneities. Thereafter, we classify and expound upon forecasting methodologies for commuter flow, elucidating principles behind predictive algorithms and composite models grounded in statistical and time-series analyses, discrete choice modeling, conventional machine learning, and advanced deep learning techniques. Concurrently, a comparative assessment of the strengths, limitations, and applicability of each method is presented. Concluding our exposition, predicated on current research landscapes and inherent challenges, prospective trajectories for future exploration are proposed, including multi-source data fusion, real-time commuting pattern detection, precise public transit for commuting, and commuting travel under shared transportation.