One of the main problems in the study of human migration is predicting how many people will migrate from one place to another. An important model used for this problem is the radiation model for human migration, which models locations as attractors whose attractiveness is moderated by distance as well as attractiveness of neighboring locations. In the model, the measure used for attractiveness is population which is a proxy for economic opportunities and jobs. However, this may not be valid, for example, in developing countries, and fails to take into account people migrating for non-economic reasons such as quality of life. Here, we extend the radiation model to include the number of amenities (offices, schools, leisure places, etc.) as features aside from population. We find that the generalized radiation model outperforms the radiation model by as much as 10.3 percent relative improvement in mean absolute percentage error based on actual census data five years apart. The best performing model does not even include population information which suggests that amenities already include the information that we get from population. The generalized radiation model provides a measure of feature importance thus presenting another avenue for investigating the effect of amenities on human migration.

We develop a numerical model using both artificial and empirical inputs to analyze taxi dynamics in an urban setting. More specifically, we quantify how the supply and demand for taxi services, the underlying road network, and the public acceptance of taxi ridesharing (TRS) affect the optimal number of taxis for a particular city, as well as commuters' average waiting time and trip time. Results reveal certain universal features of the taxi dynamics with real-time taxi-booking—that there is a well-defined transition between the oversaturated phase when demand exceeds supply, and the undersaturated phase when supply exceeds demand. The boundary between the two phases gives the optimal number of taxis a city should accommodate, given the specific demand, road network and commuter habits. Adding or removing taxis may affect commuter experience very differently in the two phases revealed. In the oversaturated phase the average waiting time is affected exponentially, while in the undersaturated phase it is affected sub-linearly. We analyze various factors that can shift the phase boundary, and show that an increased level of acceptance for TRS universally shifts the phase boundary by reducing the number of taxis needed. We discuss some of the useful insights on the benefits and costs of TRS, especially how under certain situations TRS will not only have economic benefits for commuters, but can also save the overall travel time for the shared parties, by significantly reducing the time commuters spend on waiting for taxis. Our simulations also suggest that simple artificial taxi systems can capture most of the universal features of the taxi dynamics. The relevance of the assumptions and the overall methodology are also illustrated using the empirical road network and taxi demand in Singapore.

Here, using an ensemble of machine learning models, a procedure is demonstrated that classifies passengers (Adult, Child/Student, and Senior Citizen) based on their three-month travel patterns. The method proceeds by constructing distinct commuter matrices, we refer to as eigentravel matrices, that capture a commuter’s characteristic travel routine. Comparing various classification models, we show that the gradient boosting method gives the best prediction with 76% accuracy, 81% better than the minimum model accuracy (42%) computed using proportional chance criterion.

In this work, we particularly focus on the complex relationship between land-use and transport offering an innovative approach to the problem by using land-use features at two differing levels of granularity (the more general land-use sector types and the more granular amenity structures) to evaluate their impact on public transit ridership in both time and space. To quantify the interdependencies, we explored three machine learning models and demonstrate that the decision tree model performs best in terms of overall performance—good predictive accuracy, generality, computational efficiency, and “interpretability”.