National Science Foundation (Digital Goverment Initiative)

Project Title: Knowledge Management Over Time-Varying Geospatial Datasets
Sponsoring Institution: University of Maine
Project Contact Person: Peggy Agouris (University of Maine)
Investigators at UC Riverside: Vassilis J. Tsotras, Dimitrios Gunopulos

WWW Page:
project web page

Project Award Information:
Award Number: EIA-9983445
Duration:  Aug. 1, 2000 - July 30, 2003

Project Summary:

Geospatial datasets are collected and processed by a variety of Federal Agencies.
Such data and the information contained therein are of use to a practically limitless
array of Federal and State Agencies, and private companies. Advancements in
sensor technology, computer hardware and software have resulted in the availability
of huge amounts of diverse types of geospatial datasets. Our objective in this project
is to facilitate the integration of those datasets across space and time, and to improve
knowledge management over such time-varying geospatial datasets. In doing so, we
will improve accessibility to the information they contain, making it more useful to
groups of users that are constantly increasing and diversifying. In this project we are
dealing specifically with four complementary challenging research issues which are
keys to realizing the integration and improved access to the information content of
heterogeneous time-varying geospatial datasets. Specifically, we address:

* The development of a geospatial knowledge management framework to provide
the syntax, context, and semantics for researching, understanding, and leveraging
technical and human behaviors related to spatial understanding and work.

* The development of novel meta-information concepts to convey summaries of
heterogeneous datasets (focusing especially on raster and vector spatial datasets).
This is a step towards next generation geospatial metadata, where we take advantage
of modern computer capabilities to convey the actual content of datasets.

* The development of efficient techniques for discovering sequential patterns in
spatio-temporal data sets. Sequential patterns are important as they take into
account not only the spatial characteristics of a sequential event but also the time
order by which the event components happened.

* The integration of the above issues to support spatio-temporal reasoning for the
extraction of complex information through scene modeling and analysis processes.
We are focusing on the identification of similarities in behavioral patterns and
the establishment of causality.