Optimizing station locations along transit rail lines with geographic information systems and artificial intelligence

Abstract

Locating stations along transit rail lines is a challenging and interesting scientific problem. It requires careful investigation of the demand to be served, station construction cost, parking availability at the stations, right-of-way acquisition cost, accessibility to the stations, and many other factors. It also requires the development of an efficient algorithm to search for the optimal location and number of stations along a rail line. The progress in this area has been slow primarily because it turns out to be a relatively complex problem when one attempts to consider factors that are difficult to model. For example, how to formulate the problem as an optimization problem by itself is quite challenging. Developing an efficient algorithm is another challenge coupled with the formulation of key factors in the decision-making. In this paper a model is developed for optimizing station locations along a given transit line. The model uses genetic algorithms, one of the artificial intelligence-based optimization techniques. It also uses geographic information systems. The approach seems promising. Factors which will be modeled in future work, include: (1) simultaneous optimization of rail lines and station locations; (2) development of a system of rail lines to serve a metro area with efficient transfer of passengers on connecting rails; and (3) effects of future land use changes in estimating the demand.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 13 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.