Towards an activity-based approach for estimating travel destinations



Transportation demand models rely heavily on destination information. The activity-based model especially requires high resolution and disaggregated information of activity destinations. Recent developments in spatially-detailed, GIS-based data sources are making it practical to consider new methods for modeling urban activity in ways that can facilitate travel demand estimation. Massive amounts of data on land use, points of interest, public events, urban sensing, etc. are becoming available online. These data, together with modern techniques for geo-processing and data fusion, offer new possibilities for deriving activity destinations. In urban settings, such analyses can also link travel patterns with different activity patterns in ways that can be usefully incorporated into models of land use and transportation interactions. This paper develops and analyzes data fusion and estimation methods that use such data to estimate the location and size of the urban activity destinations, which are key to activity-based land use and transportation modeling. The methods are developed and illustrated using six towns in the Boston metropolitan Area, USA, as examples. Data sources include online derived points of interest from Yahoo!, proprietary business establishment data, Census Block and Census Block Group boundary data, and census employment data. This new approach for estimating activity destinations and incorporating them into travel demand can be beneficial for cities that lack current detailed business survey data for building activity-based models but wish to test the sensitivity of travel behavior to policy options and ITS implementations that are likely to alter activity patterns.


Intelligent Transport Systems


World Conference in Transport Research (open track), July 2010

Cited by

Year 2014 : 1 citations

 R Mansour, N Refaei, V Murdock, Augmenting Business Entities with Salient Terms from Twitter., COLING, 2014