Record link: 
http://hdl.handle.net/20.500.12708/43866
-
Title: 
Geospatial Semantics for Spatial Prediction (Short Paper)
en
Citation: 
McCutchan, M., & Giannopoulos, I. (2018). Geospatial Semantics for Spatial Prediction (Short Paper). In S. Winter, A. Griffin, & M. Sester (Eds.), 10th International Conference on Geographic Information  Science (GIScience 2018) (pp. 45:1-45:6). LIPICS. https://doi.org/10.4230/LIPIcs.GIScience.2018.45
-
Publisher DOI: 
10.4230/LIPIcs.GIScience.2018.45
-
Publication Type: 
Inproceedings - Full-Paper Contribution
en
Language: 
English
-
Authors: 
McCutchan, Marvin 
Giannopoulos, Ioannis 
-
Organisational Unit: 
E120-02 - Forschungsbereich Geoinformation 
-
Published in: 
10th International Conference on Geographic Information Science (GIScience 2018) 
-
ISBN: 
978-3-95977-083-5
-
Volume: 
114
-
Date (published): 
2018
-
Event name: 
10th International Conference on Geographic Information Science (GIScience 2018) 
-
Event date: 
28-Aug-2018 - 31-Aug-2018
-
Event place: 
Melbourne, Australia
-
Number of Pages: 
6
-
Publisher: 
LIPICS, 114
-
Publisher: 
Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik, Dagstuhl
-
Peer reviewed: 
Yes
-
Keywords: 
machine learning; Geospatial semantics; spatial prediction; Linked Data
-
Abstract: 
In this paper the potential of geospatial semantics for spatial predictions is explored. Therefore data from the LinkedGeoData platform is used to predict landcover classes described by the CORINE dataset. Geo-objects obtained from LinkedGeoData are described by an OWL ontology, which is utilized for the purpose of spatial prediction within this paper. This prediction is based on an association analysis which computes the collocations between the landcover classes and the semantically described geo-objects. The paper provides an analysis of the learned association rules and finally concludes with a discussion on the promising potential of geospatial semantics for spatial predictions, as well as potentially fruitful future research within this domain.
de
 
In this paper the potential of geospatial semantics for spatial predictions is explored. Therefore data from the LinkedGeoData platform is used to predict landcover classes described by the CORINE dataset. Geo-objects obtained from LinkedGeoData are described by an OWL ontology, which is utilized for the purpose of spatial prediction within this paper. This prediction is based on an association analysis which computes the collocations between the landcover classes and the semantically described geo-objects. The paper provides an analysis of the learned association rules and finally concludes with a discussion on the promising potential of geospatial semantics for spatial predictions, as well as potentially fruitful future research within this domain.
en
Research Areas: 
außerhalb der gesamtuniversitären Forschungsschwerpunkte: 100%
-
Science Branch: 
Geodäsie, Vermessungswesen
-
Appears in Collections:
Conference Paper

Show full item record

Page view(s)

121
checked on Dec 1, 2023

Download(s)

1
checked on Dec 1, 2023

Google ScholarTM

Check