Document Type


Publication Date



Transportation -- Planning, Land use -- Data processing, Land use -- Simulation methods, Data integration (Computer science)


There is an urgent need for improved models that address the interdependencies between land use and transportation, and considerable new work is underway to develop such models in Oregon and elsewhere. These models and planning practices to integrate land use into the process, however, require the integration of massive amounts of land use data that is messy and incomplete. There have been considerable advances in the treatment of such data problems in other domains, drawing on data mining and machine-learning techniques to address issues in various domains. To date, however, little systematic effort has applied these technological advances to the problem domain of land use and transportation data. Experience suggests that as much as 70% of the total effort in developing integrated land use and transportation models is directly or indirectly associated with data development, integration and cleaning, yet there is remarkably little systematic research focused on the development of reusable methods and tools to support this problem domain.

In coordination with an ongoing project of similar theme funded by University of California Transportation Center (UCTC), this project will focus on bringing interdisciplinary methods to develop land use datasets for integrated land use and transportation planning and modeling, with special attention on preserving temporal dimension of the data and monitoring data quality through indicators. Utilizing statistics and machine-learning techniques, we will develop reusable tools that will create a harmonized and coherent land use database from various public and private sources. These tools will be made available to the public and can be used by cities, counties, metropolitan planning agencies, state agencies, universities or anyone else needing to develop a usable database for use in integrated planning and modeling. All of the resulting data, with the exception of proprietary or confidential input data where there is no viable alternative, would be public and reusable for planning and research.


This is a final report, NITC-RR-581, from the NITC program of TREC at Portland State University, and can be found online at:



Persistent Identifier