Abstract
Abstract. This paper proposes an ontology to structure and describe processing chains in the remote sensing field. These chains are made up of elementary elements (operations) organized in collections. The collection notion, including information about order and repeatability of the elements, is widely defined by using the relations between their constituting items and relations to the whole data store. Applications of the ontology are illustrated with web services provided by a platform for users and providers of processing chains. A graphical interface facilitates data integration in a RDF triple store. Thanks to the management of metadata (ISO19115-3), relevant information can be requested by intelligent search engines. Graph analysis, errors management and consistency rules are computed in order to gather coherent information from the different sources. Results of these analyses are then used by machine learning algorithms for new knowledge discovery.
Highlights
Nowadays, remote sensing is increasingly used in administrations and private sector
We develop the methodology to create and manage the creation of a formal ontology dedicated to the structuring of processing chains in remote sensing
Several projects propose a semi-automatic creation of processing chains for web services using semantic web technologies (Sirin, Hendler, and Parsia, 2003; Srivastava and Koehler, 2003)
Summary
The pooling of knowledge engaged with the apparition of web platforms dedicated in remote sensing increases. Such platforms are used both by users for specific services retrieval and by providers to publish tools and applications. All the difficulty in such a use lies in the fact that the conceptualization and the terms definitions needs to be considered with the most relevant vocabulary according to the users and the providers. Modification and removal of instances in the database are available and this is a step further for ontologies integration in many tools These considerations are illustrated through the creation of a user-friendly interface and knowledge graph mining
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have