Combining machine learning and ontological data handling for multi-source classification of nature conservation areas |
| |
| Institution: | 1. Geoinformation in Environmental Planning Lab, Technische Universität Berlin, Straße des 17. Juni 145, 10623 Berlin, Germany;2. Dept. Environmental Systems, RLP AgroScience – Institute for Agroecology, Breitenweg 71, 67435 Neustadt, Germany;1. School of Computer Science and Engineering, Southeast University, Nanjing, China;2. Key Laboratory of Computer Network and Information Integration, Southeast University, Ministry of Education, Nanjing, China;3. Department of Computer Science, Vrije Universiteit, Amsterdam, The Netherlands;1. Department of Spatial Sciences, Curtin University of Technology, GPO Box U1987, Perth, WA 6845, Australia;2. IPI – Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover, Nienburger Str. 1, 30167 Hannover, Germany;1. German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), Oberpfaffenhofen, Germany;2. University of Osnabrueck, Institute for Geoinformatics and Remote Sensing, Germany;1. Instituto Politécnico Nacional, CIC, Mexico UPALM-Zacatenco, 07320 Mexico City, Mexico;2. Computer Science Department, King Abdulaziz University, Jeddah, Saudi Arabia |
| |
| Abstract: | Manual field surveys for nature conservation management are expensive and time-consuming and could be supplemented and streamlined by using Remote Sensing (RS). RS is critical to meet requirements of existing laws such as the EU Habitats Directive (HabDir) and more importantly to meet future challenges. The full potential of RS has yet to be harnessed as different nomenclatures and procedures hinder interoperability, comparison and provenance. Therefore, automated tools are needed to use RS data to produce comparable, empirical data outputs that lend themselves to data discovery and provenance. These issues are addressed by a novel, semi-automatic ontology-based classification method that uses machine learning algorithms and Web Ontology Language (OWL) ontologies that yields traceable, interoperable and observation-based classification outputs. The method was tested on European Union Nature Information System (EUNIS) grasslands in Rheinland-Palatinate, Germany. The developed methodology is a first step in developing observation-based ontologies in the field of nature conservation. The tests show promising results for the determination of the grassland indicators wetness and alkalinity with an overall accuracy of 85% for alkalinity and 76% for wetness. |
| |
| Keywords: | Remote sensing Ontology Biotope classification Machine learning Nature conservation OWL EUNIS GEOBIA Grasslands |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
