MIT Investigator(s): Moshe BEN-AKIVA
Develop a multi-modal network state estimation and prediction system that utilizes heterogeneous real-time data from a variety of sources to assess the impact of congestion-causing planned and unplanned events and optimize interventions/network management strategies to facilitate the real-time deployment of measures to mitigate congestion.
- The key objectives are to (1) extend DynaMIT2.0 to a multi-modal traffic state estimation and prediction system; (2) develop online calibration methodologies within a multi-modal environment utilizing aggregate and disaggregate data; and (3) apply and operationalize DynaMIT2.0 for the Singapore urban network.
- These objectives will be achieved by first developing and extending the demand, supply and data models within DynaMIT to model multiple modes including bus, mass rapid transit (MRT), taxi, mobility on demand, motorcycle, bicycle, walk, and ride-sharing. This will involve substantial additions to the DynaMIT system on both the modeling and software side. Enhanced online calibration methodologies will be developed (that build on the existing methods) and implemented within DynaMIT2.0, and extensive testing will be carried out. Concurrently, the multi-modal DynaMIT system will be applied to the Singapore urban network and calibrated/validated using available data from Singapore.